Security

Maintainer-only workflow for handling GitHub Secret Scanning alerts on Enclawed.

Review a set of code changes against two separate axes, Standards (does it follow this repo's documented rules?) and Spec (does it do what the issue/PRD…

Write and optimize B2B cold email outreach sequences that get replies, covering personalization, follow-up cadence, deliverability, and compliance.

Audit Microsoft Excel (.xlsx) workbooks for formula density, external references, named ranges, hidden sheets, and data validation.

Claude Code auto-memory 与 CLAUDE.md 的管理方法 — 判断值不值得记、记到哪一层(行内注释 / .claude/rules / memory / CLAUDE.md)、怎么写 frontmatter 与 description、何时 update 何时拆分、索引 MEMORY.md…

Use this skill when you need to QA audit and fix a plugin skill file.

Wires APP_VARIANT builds: per-variant ids, names, icons, schemes, EXPO_PUBLIC_* as public, secrets in EAS/CI, test code out of store bundles.

Weekly interactive audit of the AI-agent setup shared across Claude Code and OpenAI Codex — AGENTS.md rules, skills, MCP servers, settings, subagents…

Audit local and remote Git branches, classify each as safe to delete, deletion candidate, needs rebase, ice, or keep active, and extract unique work as dated…

Audits a third-party or freshly cloned repo before install or run for install hooks, auto-run files, CVEs, typosquats, and malicious code, graded A-F with a…

Audits a test suite, or a named part, for low-value tests and marks each retain, fix, consolidate, or delete with verified removal evidence.

Research a name or handle for a person or a brand, or audit one already in use: where it exists (domains through RDAP, code hosts, package registries, video…

Create, update or audit a project's AGENTS.md so that any AI tool works from the same, verified conventions: what the project is, where its architecture is…

Harness, QA-review and environment standards plus a report-only audit (parallel tests, pinned linters CI really runs, gate rules that can fail, QA environment…

Run a Brain Check — audit your second brain across Setup, Connections, Beads, Memory, Rules, and Inbox.

Author and manage Product Requirements Documents (PRDs) under "2.

Reclaim local disk by offloading cloud-backed Apple Music downloads.

CONNECT-leg: evidence-based swap of a scaffolded mock Foundry tool for a real endpoint.

Use when a Threadlight pilot needs native ACS/Rego policy, SAFE business invariants, selected tool or lifecycle bindings, approval requirements, signed policy…

Use when a pilot needs consequential-action runtime implementation or evidence: selected native hooks, gateway effect closure, action inventory, pre-deploy…

Classify, reproduce, and prepare safe upstream Monica contributions, including application misuse, documentation defects, framework bugs, design discussions…

Trace observed viewpoints from source material through stance summaries and publication drafts, producing an editor-inspectable perspective ledger with…

Edits or audits prose that the caller supplies as text or a file, preserves its claims and voice, removes machine-writing patterns, and verifies the result…

Use when the user wants to author / validate / debug / test / tune / pin-as-frequent a Cue 搭子(buddy) research template for a recurring scenario…