index

Files (1)

• SKILL.md

SKILL.md (first lines)

---
name: index
description: Skill index -- generated catalog of every local skill under ~/.agents/skills so agents can discover and invoke them.
version: 0.3.0
execution-mode: advisory
---

# Skill Index (1379 skills)

Generated from live `~/.agents/skills/*/SKILL.md` frontmatter on 2026-09-27. This file is intentionally exhaustive: every directory with a `SKILL.md` is listed so fleet agents can discover all preserved skills.

## Inventory

- Total local skills: 1379
- Source root: `~/.agents/skills`
- Inclusion rule: one row per immediate child directory containing `SKILL.md` (`_index` excluded -- self-reference)
- Regenerate: `python _regen_index.py` from `~/.agents/skills`
- Freshness gate: `python _regen_index.py --check` (wired into end-session step 1b2)

## #

| Skill | Directory | Mode | Version | Description |
|---|---|---|---|---|
| 1password | skills/1password/ | side_effecting | 1.0.1 | Retrieve API keys, tokens, passwords, and other credentials via the 1Password CLI (op) using a scoped service account (api-keys/bots/infrastructure vaults only). Use when an agent needs a credential to authenticate a service and no value is already present in the environment. |

## A

| Skill | Directory | Mode | Version | Description |
|---|---|---|---|---|
| a11y-audit | skills/a11y-audit/ | advisory | 0.1.0 | Web accessibility audit against WCAG 2.1 AA standards |
| a11y-fix | skills/a11y-fix/ | remedial | 0.1.0 | Generate specific fixes for accessibility audit findings with code patches |
| aar | skills/aar/ | advisory | 0.1.2 | Generate an After Action Report with Base120 references and receipts. |
| aar-followthrough | skills/aar-followthrough/ | side_effecting | 0.4.1 | Run AFTER [aar] completes to elaborate and plan every §7 recommendation into an owned, verifiable goal that feeds into [goal-selection]. Use whenever the operator says 'elaborate on and plan for all recommendations', 'plan the recommendations', 'follow through on the AAR', 'turn the AAR recommendations into plans', 'what do we do with these recommendations', or 'make the AAR recommendations actionable'. This is the bridge between AAR (what we learned) and goal-selection (what we do next) — it closes the retrospective→prospective loop so recommendations do not rot. |
| ab-test-analyzer | skills/ab-test-analyzer/ | advisory | 0.1.0 | Analyze A/B test results for statistical significance, effect size, and practical importance. Supports frequentist (t-test, chi-square, z-test) and Bayesian approaches. Produces a verdict table with confidence intervals, p-values, and recommendations. Use when an A/B test has concluded and you need to decide whether to ship the variant. |
| absence-audit | skills/absence-audit/ | advisory | 0.1.0 | Find what's MISSING from a system -- unhandled cases, missing tests, absent monitoring, silent failures. Maps to IN5. |
| accelerated-computing-cudf | skills/accelerated-computing-cudf/ | advisory | 0.1.0 | Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads. |
| active-learning | skills/active-learning/ | advisory | 0.1.0 | Select high-value unlabeled samples for annotation using uncertainty, diversity, or query-by-committee strategies |
| adapter-status | skills/adapter-status/ | advisory | 0.1.0 | Check which service adapters are wired and operational. |
| admission-gate | skills/admission-gate/ | side_effecting | 0.1.0 | Redaction gate for publishing fleet artifacts to external remotes. Hard-fails on local paths, machine names, Tailscale/SSH identifiers, secrets, bus paths, and live fleet directory references. Auto-normalizes home paths to placeholders. Produces machine-readable receipt + human audit summary. |
| adr-review | skills/adr-review/ | advisory | 0.1.0 | Review Architecture Decision Records for staleness, superseded decisions, missing outcomes, and unlisted alternatives |
| agent | skills/agent/ | side_effecting | 0.1.0 | Initialize any agent by name -- looks up the dispatch table and runs the right primitive (skill, daemon, integration, external). |
| agent-audit | skills/agent-audit/ | advisory | 0.2.0 | Audit a specific agent's bus activity, commit history, trust score, and guardrail compliance. |
| agent-browser | skills/agent-browser/ | advisory | 0.1.0 | Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools. |
| agent-compare | skills/agent-compare/ | advisory | 1.0.0 | Side-by-side comparison of agent outputs on identical tasks — quality, speed, cost, accuracy |
| agent-cost-track | skills/agent-cost-track/ | advisory | 0.1.0 | Track per-agent token usage and API costs with budget alerts and cost attribution |
| agent-design | skills/agent-design/ | advisory | 0.1.0 | Design agentic workflows -- tool selection, loop structure, guardrails, memory, termination conditions |
| agent-grade | skills/agent-grade/ | advisory | 0.1.0 | Grade an agent's work on a 100-point rubric that scores verified, authorized state change — not activity, token volume, or apparent confidence. Produces a mission status (Delivered/Partial/Blocked/Failed/Valid Abort) separate from a letter grade, applies critical caps and automatic-failure rules, weights by stakes, tracks rolling 7/14/30-day profiles, and recommends authority tier changes. Use when grading an agent's day, session, assignment, or rolling reliability; when comparing agents for authority calibration; or when reviewing fleet performance. |
| agent-guardrail | skills/agent-guardrail/ | advisory | 0.1.0 | Configure and test agent guardrails for input/output validation, tool-use constraints, and safety boundaries |
| agent-memory | skills/agent-memory/ | advisory | 0.1.0 | Design agent memory systems with short-term, long-term, episodic, and semantic memory and retrieval strategies |
| agent-metrics | skills/agent-metrics/ | advisory | 0.1.0 | Aggregate agent performance metrics from bus, git, and CI history |
| agent-roster | skills/agent-roster/ | side_effecting | 0.2.0 | Live probe of all known agents and models -- registry, bus activity, process status, model tiers. |
| agent-trace | skills/agent-trace/ | advisory | 0.1.0 | Trace and debug agentic workflows by logging tool calls, decision points, and state transitions |
| agent-usage-report | skills/agent-usage-report/ | advisory | 0.1.0 | Report named-agent usage telemetry, citation counts, first/last use, and backfill coverage for Apex/ARCANA-style agent promotion decisions. Use when asked about agent usage, lens telemetry, who is getting cited, citation counts, or named-agent promotion evidence. |
| agents-md-update | skills/agents-md-update/ | side_effecting | 0.1.0 | >- Update AGENTS.md files with learned project information. Discovers useful build commands, test commands, verification steps, platform quirks, and user preferences during a session and appends them to the appropriate AGENTS.md file. Use when the user says "update AGENTS.md", "save this learning", "remember this", "document this quirk", or when you discover information that would help future sessions avoid repeating the same mistakes. |
| agents-sdk | skills/agents-sdk/ | advisory | 0.1.0 | Build Cloudflare Workers agents with Agents SDK: stateful agents, WebSockets, MCP servers, chat/voice agents, scheduled tasks, Workflows, queues, RPC, observability, and React hooks. |
| ai-cost-optimize | skills/ai-cost-optimize/ | advisory | 0.1.0 | Reduce AI API costs through caching, batching, model downsizing, prompt compression, and response truncation strategies |
| ai-policy-review | skills/ai-policy-review/ | advisory | 1.0.0 | Review and grade an existing internal AI use policy against NIST AI RMF, ISO 42001, and EU AI Act requirements. Produces gap list, grade, and rewrite recommendations. Saves to _internal/compliance/. Powered by compliance-advisor agent. |
| ai-regulation | skills/ai-regulation/ | advisory | 0.1.0 | Track AI-specific regulations -- EU AI Act, US executive orders, state bills, sector-specific rules |
| ai-risk-assessment | skills/ai-risk-assessment/ | advisory | 1.0.0 | Full AI system risk assessment aligned to NIST AI RMF. Maps risks across GOVERN/MAP/MEASURE/MANAGE, scores severity, and produces a board-ready audit artifact. Saves to _internal/compliance/. Powered by compliance-advisor agent. |
| ai-safety-check | skills/ai-safety-check/ | advisory | 0.1.0 | Validate AI outputs for safety, bias, and robustness with comprehensive testing. [Maps to P9.] |
| aiq-deploy | skills/aiq-deploy/ | side_effecting | 0.1.0 | \| Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure. |
| aiq-research | skills/aiq-research/ | side_effecting | 0.1.0 | \| Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend. |
| alert-digest | skills/alert-digest/ | advisory | 0.1.0 | Summarize and deduplicate recent alerts, identify fatigue patterns |
| alert-noise-reduce | skills/alert-noise-reduce/ | advisory | 0.1.0 | Deduplicate and correlate alerts to reduce noise. Groups similar alerts by signature, suppresses flaps, and surfaces the signal through the noise. |
| alert-rule | skills/alert-rule/ | side_effecting | 0.1.0 | Create and manage alert rules for health probes, cost thresholds, and CI failures |
| alert-triage | skills/alert-triage/ | side_effecting | 0.1.0 | >- Triage incoming alerts, suppress duplicates, correlate related alerts, route to the right responder, and escalate stale alerts. Use when alert volume is high and needs structured triage. Distinct from alert-rule (which creates alerting rules) and alert-noise-reduce (which reduces false positives) — this is the operational triage step for alerts that have already fired. |
| algorithmic-art | skills/algorithmic-art/ | advisory | 0.2.0 | Create original, self-contained, and verified p5.js generative art from an algorithmic philosophy. Hardened for reproducibility, safety, and measurable quality. |
| alignment-check | skills/alignment-check/ | advisory | 1.0.0 | Verify agent outputs align with stated goals — detect goal drift, reward hacking, specification gaming |
| alphafold-database-fetch-and-analyze | skills/alphafold-database-fetch-and-analyze/ | advisory | 0.1.0 | > Retrieve and analyze AlphaFold predicted structures for a protein. Use when the user provides a specific UniProt Accession ID and wants structural confidence metrics (pLDDT), domain boundary analysis, or disorder assessment. Do not use if the user only has a protein name, gene name, or amino acid sequence — ask for a UniProt ID first. |
| alphagenome-single-variant-analysis | skills/alphagenome-single-variant-analysis/ | advisory | 0.1.0 | > Analyzes genetic variant effects on gene expression (RNA-seq), chromatin accessibility (DNASE), histone marks (ChIP), and transcription factors using the AlphaGenome API. Use when the user asks about non-coding variant effects, pathogenicity, clinical significance, disease associations, functional effects, gene expression changes, splicing disruption, or regulatory effects in promoters and enhancers. Also use for resolving biological terms to tissue/cell-type ontologies (UBERON/CL) or analyzing variants in |
| amazon-bedrock | skills/amazon-bedrock/ | advisory | 5 | >- Builds generative AI applications on Amazon Bedrock. Covers model invocation (Converse API, InvokeModel), RAG with Knowledge Bases, Bedrock Agents, Guardrails, and AgentCore (including the Harness managed agent loop). Applies when invoking models, setting up Knowledge Bases, creating agents, applying guardrails, deploying to AgentCore, migrating/porting/converting a Bedrock Agent (including inline agents) to an AgentCore Harness, troubleshooting Bedrock errors (ThrottlingException, AccessDeniedException), or choosing models (Claude, Llama, Nova, Titan). Also for prompt caching, quota and throttling diagnosis, cost tracking, migrating between Claude model generations (4.5 to 4.6 to 4.7), chunking strategies, API selection (Converse vs InvokeModel), guardrail capabilities, and model selection. Also covers AgentCore Payments (x402, microtransactions, Payment Manager, Connector, Instrument, Coinbase CDP, Stripe Privy, paid endpoints, agent payments). NOT for custom model training, Rekognition, or Comprehend. |
| amberteam | skills/amberteam/ | advisory | 0.1.0 | Supply chain security -- security of dependencies, third-party libraries, build pipelines, and artifact provenance. The builder team that secures what other builders build with. |
| amc-run-rtsp-calibration | skills/amc-run-rtsp-calibration/ | side_effecting | 1.0.0 | Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration. |
| amc-run-sample-calibration | skills/amc-run-sample-calibration/ | side_effecting | 1.0.0 | Run end-to-end calibration on the shipped sample dataset (sdg_08_2_sample_data_010926.zip) against a running AMC microservice. Use when user says 'test sample dataset', 'run sample calibration', 'verify AMC install', or 'launch and test'. |
| amc-run-video-calibration | skills/amc-run-video-calibration/ | side_effecting | 0.1.0 | Calibrates pre-recorded `cam_*.mp4` datasets through the AutoMagicCalib REST API. Use for user-supplied local MP4s; route live RTSP streams to `amc-run-rtsp-calibration`. |
| amc-setup-calibration-stack | skills/amc-setup-calibration-stack/ | side_effecting | 1.0.0 | Launch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. Use when user says 'deploy auto calibration', 'launch auto calibration', 'launch AMC', 'start MS+UI', or 'set up auto-magic-calib'. Requires NGC API key. |
| anthropic-watch | skills/anthropic-watch/ | advisory | 0.1.1 | Track bleeding-edge Anthropic announcements -- model releases, API changes, Claude Code updates, partner programs, safety research, policy positions. |
| workstation-git-sync | skills/workstation-git-sync/ | side_effecting | 0.1.0 | >- Sync git repositories between Delta and Workstation using verified patterns. Encapsulates the correct approach for git operations involving Workstation, which has no GitHub credentials for SSH sessions. Uses gh auth token for cloning to agent-node, gh from agent-node for PR operations, and documents the known failure modes. Use when the user asks to "sync to agent-node", "push to agent-node", "clone on agent-node", "git on agent-node", or when git operations on agent-node fail with "could not read Username" or "/dev/tty: No such device". |
| workstation-remote-ops | skills/workstation-remote-ops/ | advisory | 0.1.0 | Run commands on agent-node from agent-node via SSH — PowerShell escaping, WSL path translation, scp exit-code checking, skills-full/ layout. |
| apex | skills/apex/ | advisory | 1.2.1 | Recon-first assessment mode — think before acting, produce a plan, delegate execution to the right mode. Advisory by default. |
| api-design | skills/api-design/ | advisory | 0.1.0 | Design REST/HTTP APIs with consistent patterns -- endpoints, errors, pagination, auth. |
| api-docs | skills/api-docs/ | advisory | 0.1.0 | Generate API documentation from FastAPI/Flask endpoints or Python function signatures |
| api-test | skills/api-test/ | side_effecting | 0.1.0 | Generate and run HTTP API tests against live or mocked endpoints |
| apply-review | skills/apply-review/ | advisory | 0.1.0 | Review application materials (resume, cover letter, LinkedIn copy, portfolio one-pager, outreach email, any first-person professional artifact) against memory + fabrication checks before they get sent or published in Reuben's name. Catches the v3-style fabricated-employment failure mode at the gate. |
| arcana-peer-review | skills/arcana-peer-review/ | advisory | 0.1.0 | Simulate independent non-author review by dispatching ARCANA-archetype subagents, each applying a different philosophical or analytical lens to the same work product, blind to author intent and gold labels. Use before sending a framework, architecture, or proposal to a human reviewer, or when the user wants diverse critical perspectives / names a specific lens / asks "what would a skeptic say?" / "red-team this" (on a written work product, not code). |
| arcana-review | skills/arcana-review/ | side_effecting | 0.1.0 | Multi-agent peer review using diverse epistemological lenses. Dispatches N subagents (subagent_general, GLM-5.2 via direct API) to independently review a document, collects findings, severity-ranks P1/P2/P3, and synthesizes a verdict. |
| arcana-to-pitch | skills/arcana-to-pitch/ | advisory | 1.0.0 | Transform ARCANA multi-lens synthesis outputs into HUMMBL pitch materials. Converts philosophical research findings into email openers, one-pagers, discovery call talk tracks, and deck slides. Sources each claim from its originating ARCANA lens for credibility trail. |
| arch-diagram | skills/arch-diagram/ | advisory | 0.1.0 | Generate interactive architecture diagrams as self-contained HTML/SVG files. |
| aria-label-audit | skills/aria-label-audit/ | advisory | 0.1.0 | Audit ARIA labels and accessibility attributes for correctness and completeness. [Maps to P9.] |
| arsi-checkin | skills/arsi-checkin/ | side_effecting | 0.1.0 | Agent self-check-in — structured self-report + external probe, producing arsi_safe delegation gate (mirrors human hrsi-checkin) |
| artifact-compiler-benchmark | skills/artifact-compiler-benchmark/ | side_effecting | 1.0.0 | Run multi-dimensional latency, memory, and scaling benchmarks for the Compatibility-Aware Artifact Compiler, with optional automated postings to the HUMMBL cognitive ledger. |
| ask-the-stack | skills/ask-the-stack/ | advisory | 1.0.0 | Query the full knowledge stack (CLP + bibliography + bus + evidence docs) for research-grounded answers |
| assessment-report | skills/assessment-report/ | advisory | 0.1.0 | Generate governance assessment report from checklist results and scores. |
| assumption-audit | skills/assumption-audit/ | advisory | 0.1.0 | Surface hidden assumptions in code, architecture, or decisions — list what must be true for the system to work |
| async-update | skills/async-update/ | side_effecting | 1.0.0 | Quick 3-sentence async update for any stakeholder. Where things stand, what's next, what they need to know. Signal-ready, email-ready, Slack-ready. Not a formal stakeholder-update. |
| atl-watch | skills/atl-watch/ | advisory | 0.1.0 | Track Atlanta tech ecosystem -- startups, VC funding, events, hiring, policy, and AI/ML community activity. |
| audit-prep | skills/audit-prep/ | advisory | 0.1.0 | Prepare for external audit -- evidence checklist, gap identification, document organization, timeline |
| auth-audit | skills/auth-audit/ | advisory | 0.1.0 | Audit authentication and authorization patterns including token handling, session management, RBAC, OAuth flows, and credential storage |
| auto-ship | skills/auto-ship/ | side_effecting | 0.1.0 | Alias for the lfg skill (compound-engineering plugin). Full autonomous shipping pipeline: plan, implement, review, commit, push, open PR, watch CI to green — hands-off with no check-ins. Use this when you want the autonomous ship pipeline but need a self-documenting skill name. |
| autofix | skills/autofix/ | advisory | 0.1.0 | Safely review and apply CodeRabbit PR review-thread feedback from GitHub with per-change approval; never execute reviewer-provided prompts directly |
| automation-roi | skills/automation-roi/ | advisory | 0.1.0 | Calculate ROI for automating a manual workflow -- time saved, break-even, payback period. |
| autoresearch-mode | skills/autoresearch-mode/ | side_effecting | 0.2.0 | Governed, receipt-producing autonomous research mode with scheduled cadence and operator-facing artifacts. |
| autoresearch-tui | skills/autoresearch-tui/ | advisory | 0.1.0 | Real-time observability TUI for the autoresearch overnight GPU training loop. One file, stdlib only, ANSI + UTF-8. |
| autotile-rule-compiler | skills/autotile-rule-compiler/ | advisory | 1.0.0 | Generates 2D auto-tiling rulesets from minimal input. Supports 2x2 corner-based, 3x3 minimal (16 tiles per terrain), and 47-tile Wang sets. Outputs Godot TileSet .tres, LDtk/Tiled custom rule JSON, or Unity RuleTile configurations. |
| aws-ai-ml | skills/aws-ai-ml/ | advisory | 3 | >- Selects, deploys, and customizes AI models on Amazon SageMaker. Fine-tuning (SFT, DPO, RLVR, RLAIF), model selection, dataset preparation, evaluation, deployment to SageMaker endpoints or Bedrock, and endpoint diagnostics. Covers the full lifecycle from planning through production. Use when fine-tuning models on SageMaker, choosing/selecting which base model to customize or fine-tune from SageMaker Hub, finding a model to deploy without fine-tuning, transforming datasets for training, checking data readiness, evaluating model quality, deploying to endpoints, setting up IAM roles and S3 buckets for training jobs, or managing a SageMaker Managed MLflow app. Also use to check endpoint health, diagnose failures, debug latency or errors, or view container logs and CloudWatch metrics. Covers Serverless Model Customization, Nova and OSS deployment paths, and PySDK v3 usage. NOT for Ground Truth labeling, Feature Store, or general-purpose AWS infrastructure. |
| aws-auth | skills/aws-auth/ | advisory | 1 | >- Adds user authentication to web and mobile apps with Amazon Cognito (user pools and identity pools) and the AWS Amplify client auth libraries. Covers sign-up/sign-in flows and the login page (Cognito-hosted UI / managed login), MFA, password policies, OAuth 2.0 / OIDC flows (auth-code + PKCE, client credentials), social/SAML federation, tokens (ID/access/refresh, rotation, revocation, storage), Cognito Lambda triggers, identity pools (temp AWS creds), and gating API Gateway (or ALB) routes to signed-in users via Cognito/JWT authorizers. Applies when adding a login or sign-up page, configuring a user pool or app client, choosing user pool vs identity pool, wiring social/SAML, refreshing tokens, requiring sign-in on an API Gateway or ALB, or debugging redirect_uri/token/MFA/CORS/federation errors. Does NOT cover Amplify Gen2 backend definitions (defineAuth, npx ampx → aws-amplify), IAM/STS/Identity Center (→ aws-iam), or API Gateway/Lambda resource config beyond the authorizer (→ aws-serverless). |
| aws-billing-and-cost-management | skills/aws-billing-and-cost-management/ | advisory | 1 | >- Analyze AWS costs, find savings, manage budgets, evaluate Savings Plans and Reserved Instances, right-size EC2/Lambda/RDS/EBS with Compute Optimizer, look up service pricing, query CUR with Athena, detect cost anomalies, scope costs to billing views, and monitor Free Tier usage. Triggers on: AWS bill, cost analysis, reduce spend, savings plan, reserved instance, right-size, budget alert, cost optimization, pricing, free tier, cost anomaly, CUR, cost audit, billing view, billing view ARN. |
| aws-blocks | skills/aws-blocks/ | advisory | 1 | >- Guides building full-stack applications with AWS Blocks — an Infrastructure-from-Code framework. Applies when creating APIs, selecting Building Blocks (KVStore, DistributedTable, Database, AuthBasic, AuthCognito, Realtime, AsyncJob, FileBucket, etc.), running local development, or deploying AWS Blocks applications. Also covers AWS Blocks topics with validated, version-specific patterns that prevent common mistakes. Triggers when user mentions AWS Blocks; project has aws-blocks/ directory; code imports @aws-blocks packages. |
| aws-cdk | skills/aws-cdk/ | advisory | 2 | >- Authors, deploys, and troubleshoots AWS infrastructure using CDK with TypeScript or Python. Covers best practices, stack architecture, and construct patterns. Applies when writing CDK constructs, bootstrapping environments, running cdk deploy/synth/diff, fixing CDK or CloudFormation errors, planning stack structure, importing existing resources, resolving drift, or refactoring stacks without resource replacement. |
| aws-cloudformation | skills/aws-cloudformation/ | advisory | 2 | >- Authors, validates, and troubleshoots AWS CloudFormation templates. Covers template authoring with secure defaults, pre-deployment validation (cfn-lint, cfn-guard, change sets), CloudFormation Express mode for faster deployments, and root-cause diagnosis of failed stacks using CloudFormation events and CloudTrail correlation. |
| aws-compute | skills/aws-compute/ | advisory | 2 | >- Provisions, scales, and operates Amazon EC2 virtual-machine workloads: instance-type selection (Graviton/Arm64, burstable T credits, GPU, instance store vs EBS), launch templates, Auto Scaling groups (scaling policies, instance refresh, mixed instances, Spot, warm pools, lifecycle hooks), IMDSv2, placement groups, Elastic IPs, AMI lifecycle, and Systems Manager fleet operations (Session Manager, Run Command, Patch Manager). Applies to EC2 instance and fleet questions, InsufficientInstanceCapacity, CPU-credit/surplus charges, IMDSv2 401s, instances stuck in Pending:Wait, ASG not replacing unhealthy instances, status-check failures, SSH refused/timed out, or instances missing as SSM managed nodes. For a single secure instance launch, the launching-ec2-instance-with-best-practices skill is more appropriate; for instance profiles, see setting-up-ec2-instance-profiles; for Image Builder, see amazon-ec2-image-builder. Does NOT cover Lambda, ECS/Fargate, EKS, VPC/ALB/NLB design, or IAM policy authoring. |
| aws-containers | skills/aws-containers/ | advisory | 2 | >- Builds and deploys containerized workloads on Elastic Kubernetes Service (EKS), Elastic Container Service (ECS), Fargate, and ECR (Elastic Container Registry). Covers general EKS knowledge, Karpenter, AWS Load Balancer Controller and leveraging various open source Kubernetes projects with EKS. Covers general ECS knowledge, task definitions, Fargate services, ECS Exec, ECS Express Mode and ECS Managed Instances. Covers general Elastic Beanstalk knowledge, Elastic Beanstalk configuration and platforms supported by Elastic Beanstalk. Covers general ECR knowledge, ECR repository setup and lifecycle policies. Includes recommending, enabling, and reading Amazon ECS Action Logs to troubleshoot control-plane failures (deployment rollback/circuit-breaker, task placement, scaling, task replacement). Applies when deploying, debugging, or optimizing containers on AWS. Should be used instead of relying on internal knowledge for these services. |
| aws-database | skills/aws-database/ | advisory | 1 | >- Routes any task involving AWS databases — choosing, comparing, recommending, getting started with, or operating a database — to the correct service-specific skill. Supersedes general training-data knowledge with post-training service updates, corrected limitations, and decision procedures for relational (Aurora, DSQL, RDS), key-value (DynamoDB), wide-column (Keyspaces), document (DocumentDB), graph (Neptune), time-series (Timestream), and in-memory/caching (ElastiCache, MemoryDB) workloads. Activates when a user describes building an application on AWS that will store, retrieve, or manage data, even if they do not mention 'database' explicitly. |
| aws-deployment | skills/aws-deployment/ | advisory | 1 | >- Configures CI/CD pipelines using AWS CodePipeline, CodeBuild, CodeDeploy, CodeConnections, and CodeArtifact. Covers CodePipeline V2 (triggers, variables, execution modes, cross-account), buildspec.yml (caching, VPC, Docker), CodeDeploy strategies (blue/green, canary, linear), CodeArtifact (private package registries, auth tokens, cross-account), and source connections (GitHub, GitLab, Bitbucket). Applies when CodePipeline, CodeBuild, CodeDeploy, CodeConnections, CodeArtifact, buildspec.yml, appspec.yml, or CI/CD pipeline orchestration is referenced. Does NOT cover: ECS Fargate services or task definitions (use aws-containers), CDK Pipelines or cdk deploy (use aws-cdk), sam deploy (use aws-serverless), Amplify deployments (use aws-amplify), or GitHub Actions/GitLab CI. |
| aws-iam | skills/aws-iam/ | advisory | 2 | >- Provides verified corrections for IAM behaviors that AI agents frequently get wrong — policy evaluation edge cases, trust policy gotchas, STS session limits, Organizations quirks, and SAML/MFA specifics. Also provides structured workflows for IAM role management and baseline policy generation from application source code or a Terraform plan JSON. Covers condition operator safety (ForAnyValue/ForAllValues with Null checks), bucket policy deny patterns (VPC endpoint restrictions, org paths), confused deputy protection, and service role creation for AWS services (Glue, CloudTrail, Lambda, ECS, etc.) with aws:SourceAccount/aws:SourceArn trust conditions. Applies when creating IAM roles, writing IAM or bucket policies, generating policies from application source code or a Terraform plan JSON, working with STS, Organizations, or condition operators, or any task needing a service or execution role. Does not cover non-IAM authorization like Cognito user-pool policies or app-level RBAC. |
| aws-messaging-and-streaming | skills/aws-messaging-and-streaming/ | advisory | 4 | >- Guides general use of AWS messaging and streaming services. Covers Amazon SQS, Amazon SNS, Amazon EventBridge, Amazon MQ, Amazon Kinesis Data Streams, Amazon Data Firehose, Amazon Managed Service for Apache Flink, and Amazon Managed Streaming for Apache Kafka (MSK). Use when reasoning about messaging and streaming patterns. Also identifies which AWS service owns each customer communication channel: email (Amazon SES), and WhatsApp, SMS, MMS, RCS, voice and mobile push (the AWS End User Messaging family of services). Routes the request to the specialized skill for that channel. Defers to the channel's specialized skill when the user already named a specific channel. In general, use specific skills or documentation searches for detailed service-specific questions. Do NOT use for MSK or Managed Service for Apache Flink questions, prefer specific skills. Does not configure customer communication channels; defers to specific skills. |
| aws-networking | skills/aws-networking/ | advisory | 2 | >- Routes AWS networking requests to the correct service skill for implementation. Covers Route 53 (DNS, health checks, routing policies, Resolver, DNS Firewall), CloudFront (caching, edge, OAC, mTLS, signed URLs), Transit Gateway (multi-VPC hub, segmentation, centralized egress), Direct Connect (hybrid link, DX Gateway, MACsec), Site-to-Site VPN (IPsec tunnels, static or BGP), WAF (web ACLs, AWS Managed Rules, rate-based rules, Bot and Fraud Control), and Shield Advanced (L3/L4 DDoS). Applicable when creating, configuring, troubleshooting, or designing across these services, choosing between them, or diagnosing connectivity or traffic-filtering issues. Not for VPC subnets and route tables, load balancers, VPC endpoints, PrivateLink, API Gateway, IAM policy logic, container or serverless networking, or IaC authoring. |
| aws-observability | skills/aws-observability/ | advisory | 2 | >- Builds, configures, debugs, and optimizes AWS observability with CloudWatch (Log Insights, Metrics, Alarms, Dashboards, EMF), X-Ray, CloudTrail, and ADOT (AWS Distro for OpenTelemetry), AND enables/onboards services to Application Signals using ADOT auto-instrumentation SDKs. Covers Log Insights queries, alarms (metric, composite, anomaly), dashboards, custom metrics/EMF, X-Ray tracing and sampling, ADOT collector config, CloudTrail auditing, and end-to-end Application Signals enablement via ADOT SDKs (CloudWatch Observability EKS add-on, CloudWatch Agent IAM, OTLP endpoints, ServiceEvents, Dynamic Instrumentation), breakpoint and snapshot in Dynamic Instrumentation, live data capture in running service, debug without redeploying. Applies to CloudWatch, alarms, dashboards, EMF, X-Ray, traces, CloudTrail, ADOT, monitoring, synthetics/canaries, OR enabling/onboarding/instrumenting a service for Application Signals. Not for app logging or security threat detection. |
| aws-sdk-js-v3-usage | skills/aws-sdk-js-v3-usage/ | advisory | 1 | >- AWS SDK for JavaScript v3 development patterns. Use when writing JavaScript or TypeScript code that uses AWS services via @aws-sdk/* packages (aws-sdk-js-v3), or when asked about schemas, runtime validation, serialization, or code generation in the context of the JS/TS AWS SDK. |
| aws-sdk-python-usage | skills/aws-sdk-python-usage/ | advisory | 1 | >- AWS SDK for Python (boto3/botocore) development patterns. You MUST use this skill when writing Python code that uses AWS services via boto3 or botocore. This includes creating service clients or resources, configuring sessions and credentials, handling errors with ClientError, using paginators and waiters, S3 file transfers and presigned URLs, DynamoDB table operations, and any boto3/botocore client configuration. Use this skill whenever Python code imports boto3 or botocore, or when the user asks about AWS operations in Python. |

From hummbl-io/agent-skills, Apache-2.0.

More from hummbl-io/agent-skills