Agent building

Load recent prototypes, logs, plans, and artifacts from the repo-scoped Dropbox-synced cclogs dir so work started in an earlier session can be continued.

Set up and use the committed `_temp-resource/<issue>-<topic>/` convention for handing scratch resources (prototypes, design references, fixtures, sample data)…

Search or save to the user's shared local MemPalace memory (shared with Decisions, Claude Code, Codex, Cursor, Kilo).

Research a topic and build a beautiful, magazine-style PDF explainer written for a specific kid — designed cover, sections, cards, comparison tables…

Give your AI agent a professional health checkup (AgentVitals).

Measure and fix a slow coding-agent setup: status line, hooks, instruction bloat, effort, worktree pile-up, antivirus and indexer scans.

Implement A2A agents, MCP servers, and ACP editor integrations in Python.

Efficiently read and analyze pi agent session JSONL files.

Answer Zendesk customer support questions using Fivetran-synced data via BigQuery, Snowflake, or Databricks.

Plan and run multi-agent video production pipelines.

Routes requests to the BMad Method (v6.12.4) agile framework: persona agents, planning skills (brief, PRFAQ, PRD, UX, spec, architecture, epics, sprint…

This skill should be used when the user asks to review, referee, or critique an ML/AI paper for an A* venue or laboratory pre-review.

Stream a local video file to Pump.fun's livestream UI for the agent's coin.

Tool-first multi-agent runtime controls for the current conversation.

Suede AI agent-team orchestrator, the method behind multi-agent automation: split complex work into coordinated lanes with explicit file ownership, WIP…

Turns a docs site, local folder, PDF or book, YouTube video, playlist or channel, or a topic into a source-grounded, token-efficient agent skill (hub…

Drive a Claude Code session toward a verifiable goal until done or a hard cap fires - autonomous loop, no user intervention.

Capture a full DevTools-protocol trace of a locally driven browser automation - CDP firehose, screenshots, and DOM dumps - then bisect the stream into…

Review code with a sharp, encouraging voice - inline GitHub PR comments + a tight summary.

Create a new agent skill (or Claude Code slash command) from a plain-language description, using live spec fetching, pattern research, and an approval-gated…

Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code…

Use this built-in skill to execute readonly SQL through the OpenDataWorks agent API and shared odw-cli.

Build-focused skill for creating, updating, and installing standard Agent Skills, including remote HTTPS skill.md installation through a constrained…

Analyze a user's pi coding-agent session history for recurring behavior, prompting habits, workflow loops, friction, and preferences.