Defines how the TestDriver agent reviews pull requests, onboards from issues, and responds to @mentions on GitHub.
Build and train self-learning agents using AgentDB's nine reinforcement learning plugin templates.
Teaches Claude AgentDB's advanced stack — QUIC sync, hybrid vector+metadata search, multi-DB sharding, MMR and production hardening.
A Python/Pillow skill that crops an image to 50% from the center and rotates it 90 degrees clockwise in one command.
A layered troubleshooting playbook that uses the mcptoon CLI to find and fix broken MCP servers.
An FDEOps-style skill for implementing a scoped customer software change and verifying that it actually works.
Decomposes a public company's organic and inorganic growth drivers from SEC filings and earnings calls into an analyst-grade, fully cited growth-strategy report.
Decomposes how a public company actually makes money into an analyst-grade report grounded in XBRL facts and SEC filings.
Generates analyst-grade competitive landscape reports — peer comparison, market-share dynamics and moat assessment — from SEC filings and earnings calls.
Battle-tested configuration patterns for running Playwright tests fast and reliably on GitHub Actions, GitLab CI, Docker, and other CI providers.
A disciplined refactoring playbook that drives trace-mcp tools to assess risk, map impact, rename atomically, and verify results.
A 5-minute onboarding skill that profiles your transferable skills, assigns a starting tier (S0–S3), and saves it to .skill-state.json for later job-scan and study-plan steps.
Turns one target job role into an executable plan: gap analysis, phased learning path, portfolio list, application timeline, and stop-loss rules.
Publishes whatever was just produced as-is to a live, shareable URL in seconds via ReportRoom.
A disciplined playbook for splitting work across multiple agents with dependency graphs, handoff contracts, approval gates, and verified synthesis.
Runs a read-only, parallel audit of git, PRs, CI, releases, plan docs and logs, presents a grouped checklist, and fixes only what you explicitly confirm.
A QA lane that opens your rendered HTML deck, inspects every slide through a skeptical-audience lens, applies scoped fixes to slides.html/custom.css, and rebuilds.
The codeck publisher lane that exports assembled HTML decks to PDF or PPTX and runs a mandatory visual QA loop.
An end-to-end npm release runbook: local verification, tag push, approval-gated GitHub Actions publish, then post-publish verification and cleanup.
A gated end-to-end runbook for releasing Compass: sync main, bump versions, open the PR, tag the merge commit, build six platforms, and verify every download.