Loading...
Loading...
Found 119 Skills
Deep retro of retros - investigation pass that surfaces improvements across older retros and the current ax setup. External AI agent drives the reasoning with high thinking enabled. Triggers when user says "deep retro", "investigate ax", "what should I fix in my setup", "retro of retros", or invokes /ax:retro-meta. Use after `ax:retro` if proposals are sparse or you want broader exploration.
Sets up comprehensive GitHub Actions CI/CD workflows for modern web applications. This skill should be used when configuring automated lint, test, build, and deploy pipelines, adding preview URL comments on pull requests, or optimizing workflow caching. Use when setting up continuous integration, deployment automation, GitHub Actions, CI/CD pipeline, preview deployments, or workflow optimization.
Analyzes order data and order processing in Magento 2. Use when analyzing orders, retrieving order information, assessing order processing performance, or troubleshooting order issues. Masters order lifecycle analysis, payment data inspection, and fulfillment diagnostics.
Knowledge Blacksmith: Used to non-destructively merge and append new practical experience (new pitfalls encountered, new boundaries discovered, better solutions) into existing knowledge cards. The core principle is "extremely conservative minimally invasive surgery" - strictly prohibited from deleting or over-simplifying high-value experience (pain points, mistake records) in the original assets, and only upgrade old assets through Append and structured Merge. Trigger signals: `/asset-evolve`, `/asset-update`
Analyzes professions/jobs for Claude Code automation opportunities. Triggers: 'how can Claude help me', 'what can Claude do for', 'I'm a [profession]', 'help me as a [job]', 'I work as', describing their work + asking about Claude. Use whenever user mentions their profession/role and wants to discover what Claude can automate.
Analyze the user's manual rewrite or repeated correction of Codex-generated work and propose durable, carefully scoped lessons. Use when the user asks to improve future behavior from their corrections. Do not use for ordinary task requirements or one-off implementation feedback without a request for lasting guidance.
Capture and persist lessons learned from a session to compound knowledge over time. Triggers on "/lessons-learned", "what did we learn", "save lessons", "update skills with what we learned", or at the end of a complex multi-session task. PROACTIVE USE: This skill should also be suggested or invoked (1) when resuming from context compaction (the previous context likely contained unrecorded lessons), (2) after resolving a non-trivial bug or debugging session, (3) after significant friction or failed approaches that yielded insight, (4) after a council-of-bots review that surfaced fixes. Identifies reusable patterns, bug fixes, workflow insights, and tool quirks, then persists them to the right places: auto-memory (project-specific), skill files (reusable across projects), or both.
Configure multiple Obsidian environments for development, testing, and production. Use when managing separate vaults, testing plugin versions, or establishing a proper development workflow with isolated environments. Trigger with phrases like "obsidian environments", "obsidian dev vault", "obsidian testing setup", "multiple obsidian vaults".
Forensic audit of the user's recent Claude Code sessions to surface step-change workflow improvements — not marginal ones. Use when the user asks to "audit my Claude Code sessions", "analyze how I use Claude Code", "find patterns in my usage", "improve my Claude Code workflow", "review my sessions", "find leverage in my setup", or wants to understand where their Claude Code setup is leaking time. Samples dozens of real transcripts, extracts quantitative signal via scripts, uses parallel subagents for deep reads, then synthesizes into a short prioritized report with drafted implementations (new skills, CLAUDE.md rules, hooks, settings diffs) that the user can install directly. Trigger even when the user doesn't say the word "audit" — if they're asking about improving or reviewing their Claude Code habits at scale, use this skill.
Weekly Report Generation. Collect this week's git commits and work items supplemented by users, organize them into a structured Chinese weekly report with sections 'Completed/In Progress/Risks/Next Steps'. Facts are based on commits, no fabrication. Use to generate a weekly report from git history and work items.
Analyze workflow runs - frequency, duration, success rates, and efficiency
Use when running the CTO flow-optimization loop — WIP scan, epic focus, triage unlabeled issues, and dispatch.