Use agent-experience-capitalization as a project-owned, team-shareable engineering memory layer for coding agents. Use it to activate prior experience before work, save reusable lessons after work, inspect save/get/log health, and diagnose Milvus-centric retrieval.
Autonomous intent delivery - agent takes over How and Exec. Use when user says "auto", "take it from here", "deliver this", or when brainstorming-grill-me concludes and user confirms autonomous execution. Requires an active intent in INDEX.md.
Use to exercise the running app in a real browser — after UI changes, before ship, or when the user asks to QA the site, smoke-test a branch, or check "does it actually work". Drives affected routes headlessly via Playwright, captures console errors, failed requests, and screenshots, and produces a report with a…
Use when encountering any bug, test failure, unexpected behavior, or performance regression — before proposing any fix. Root-cause discipline plus a feedback-loop method; applies at every tier.
Use when work is verified and ready to leave the machine — branch/PR/merge/deploy/smoke-check. Triggers on "ship it", "deploy", "merge the PR", "push this", "release", "go live", "cutover". Covers git hygiene, PR and merge discipline, deploy-target detection (Cloudflare Workers/Pages via wrangler, Vercel, Convex…
Use for task-driven Codex work that should preserve agent memory and durable results in an Obsidian or Markdown LLM+wiki vault: query planning, source boundaries, project workbench notes, checkpoints, decision logs, result writeback, and lint. Always use this skill when the user mentions Codex plus Obsidian, LLM+wiki…
Use when resuming work after chat loss, switching AI models, migrating context to a new agent or workspace, or maintaining long-running research and project memory across sessions. Manages roadmap, decision log, hypotheses, research evidence, and recovery checkpoints as separate canonical files so no single transcript…
Evidence-based deep analysis of one repo — onboards a stub into a real note, or verifies and corrects a drifted note. The only place milestone boxes get checked, always with citations. Use to onboard a repo, after a stale-thread warning, or when a note seems wrong.
Checkpoint the session into the second-brain — records what actually happened (git-anchored) and what is next, updates the dashboard, syncs git facts. Use before ending a working session or before /clear.
Resume work from the second-brain — vault dashboard brief plus the per-repo thread (what happened last, what is next) with a mechanical staleness check. Use at the start of a working session.
Create, register, ingest, search, review, publish, validate, serve, and synchronize a citation-backed Windows company knowledge repository shared safely across projects through Local Knowledge Suite. Use when Codex must answer company questions from PDF or scanned PDF, DOCX, XLSX, PPTX, EML, Markdown, text, folders…
Initialize, route, recall, and safely transfer reusable local knowledge across Windows projects using Local Knowledge Suite. Use when Codex must start a Memory-only project without a company, connect several projects to one registered company repository, choose global or vendored installation, check or migrate…
Recall, capture, correct, organize, validate, export, and restore durable Memory isolated to one Windows project through Local Knowledge Suite. Use when Codex is asked to remember a preference, correction, habit, decision, commitment, entity fact, or project convention; needs earlier project context; must inspect…
Use this skill when working in a large repository and you want Claude Code to avoid reading too many files. First consult the project context map or MCP tools, identify the most relevant files for the task, and only then inspect or edit code.