Loading...
Loading...
Found 8,189 Skills
Use when preparing or performing a review delegated to a subagent, or coordinating its findings, authorized fixes, and re-review. Applies to reviewer subagents invoked through the host application’s delegation features or through CLI tools, including review phases within another task. Don’t use merely for a main agent’s direct review or self-review, reports supplied from another conversation, or standalone findings verification.
Use when a user wants to understand a concrete STEM, AI, software, data, scientific, or engineering task while completing it: they ask to be taught as they work, request a step-by-step walkthrough with reasons, lack one or more prerequisites, or say an explanation is too abstract. Provide task-driven, just-in-time teaching from first principles and verify each practical step. Do not use for systematic course or curriculum design, simple fact retrieval without learning intent, or artifact-only requests where the user does not want explanation.
Audit, prune, and improve agent guidance markdown files in repositories. Use when the user asks to check, audit, update, improve, or fix AGENTS.md, CLAUDE.md, or related guidance files. Adds missing commands and gotchas, removes stale entries, deduplicates, and keeps the file small and relevant. Scan for guidance files, evaluate quality against templates, output a quality report, then make targeted updates.
Read a local source file or synthesize conversation context, then integrate admitted content directly into topic, entity, concept, and analysis pages in existing memory (the wiki substrate). Use this when the user wants to add a source to the wiki, add a document, ingest a local note, transcript, article, report, or PDF, or explicitly preserve the current conversation as a topic note. For session-learning routing across wiki, guidance, checkpoint, task annotation, or discard, use /loam::learning-from-session. Must not ingest a goal wholesale; admit only independently reusable findings.
Sculpt reference-image objects into procedural Three.js models. Use for reconstruction feasibility, procedural build planning, code-native implementation, or animation-, collider-, and destruction-ready structure from one or more object views.
Research this project against the real code and write a detailed report.
Finds repeated manual work in activity records and proposes automations with source evidence. Starts from a team Slack channel, a mailbox, an issue tracker, or supplied work records. The owner reviews each proposal. Use when the user wants automation opportunities found in their own or their team's actual activity: "mine this channel", "what could we automate", "find repeated manual work in these records". Do not use when the user already knows what to build, or wants ideas without granting read access; that is an interview, answer it directly.
Assess findings and feature opportunities, preserve related evidence and decisions, and recommend scoped next actions. Use for Just, Yak or Explore handoffs and decisions about a fix, improvement or PR.
Use when producing the final output a person will read — a chat reply, summary, status update, handoff, or a PR, issue, or commit message — not your private reasoning. Triggers on wrapping up a task or reporting back to the user.
Codex 連接 Obsidian。說「連接 Obsidian」時載入。
Perform a read-only audit of an existing product interface, prove UI findings from governing design evidence and runtime paths, and prepare implementation-ready recommendations or plans. Use for review and design-system drift analysis; do not use when the user asks to implement fixes directly.
Query pro-workflow wikis via SQLite FTS5 BM25 retrieval. Returns top-K passages with citations. Use when answering a question that any of the user's wikis already covers, when the user says "what does the wiki say about X", "ask wiki", "search wikis", or before drafting a new wiki page (to avoid duplication).