Loading...
Loading...
Found 33 Skills
Updates an existing docs/.scrolls/ project-memory system (STARTER.md, SPEC.md, HANDOFF.md, GAP_ANALYSIS.md, GAP_CONTEXT.md, PLAN.md, WISDOM.md, and any project-specific scrolls beyond that core set) to reflect what actually happened in the current session, following each file's own update rule instead of appending blindly. Use this whenever the user runs /scrolls-update, or asks to update the scrolls, refresh HANDOFF.md, write session handoff notes, record what was just done, close out or wrap up a session, log a new gap or trap, or update project memory / STARTER.md's docs. This is the counterpart to /scrolls-setup (which creates the system once) — use this one for every session afterward. Supports -p/--path for a custom docs location, -t/--reporoot to look under the git repository's top level regardless of which subdirectory you're in, -l/--local to look explicitly in the current directory, and -r/--recurse to search recursively for the scrolls folder if it isn't at the obvious exact location. Defaults to the current directory, but warns first if that differs from the repo root so a subdirectory invocation doesn't silently miss the real scrolls. Works on macOS, Linux, and Windows (bash or PowerShell). If no scrolls folder is found, say so and point at /scrolls-setup instead of inventing files here.
Route durable graph-building requests into one honest mode: assistant-native install, local Python build, incremental refresh, graph query follow-up, or a graphify-style structural fallback for markdown-heavy corpora. Use when the user wants `GRAPH_REPORT.md`, `graph.json`, `graph.html`, repo/corpus relationship tracing, mixed code+docs+asset graphing, or graph-backed architecture understanding that should persist across sessions. Route simple locate/reference work to `codebase-search`, narrative knowledge-base work to `llm-wiki`, and project-memory handoff to `opencontext`.
Extract successful patterns from the current session and write to project_memory.json
Provides comprehensive memory file management capabilities including auditing, quality assessment, and targeted improvements for files such as CLAUDE.md. Use when user asks to check, audit, update, improve, fix, maintain, or validate project memory files. Also triggers for "project memory optimization", "CLAUDE.md quality check", "documentation review", or when a project memory file needs to be created from scratch. This skill scans memory files, evaluates quality against standardized criteria, outputs detailed quality reports with scores and recommendations, then makes targeted updates with user approval.
steering skill Trigger terms: steering, project memory, codebase analysis, auto-update context, generate steering, architecture patterns, tech stack analysis, project structure, analyze codebase, understand project Use when: User requests involve steering tasks.
Write structured experiment report documents from ML/research experiment notes, configs, logs, metrics, tables, and figures. Use this skill whenever the user asks to write an experiment report, research update, mentor update, weekly experiment summary, result analysis document, or presentation-ready experiment writeup, especially when the output should explain motivation, setup, algorithms, metrics, results, figures, interpretation, conclusions, limitations, and next steps.
Create lightweight, living game design documents for AI-built games. Use when writing a game design brief, system spec, feature contract, content schema, implementation handoff, decision log, or when a coding agent needs durable project memory.
Project memory system - save and search past decisions, preferences, context, and notes. Use when user says "remember this", asks "what did we decide about X", or wants to recall/store information.
Creating and maintaining CLAUDE.md project memory files that provide non-obvious codebase context. Use when (1) creating a new CLAUDE.md for a project, (2) adding architectural patterns or design decisions to existing CLAUDE.md, (3) capturing project-specific conventions that aren't obvious from code inspection.
Use when the user asks to "remember project context", review saved findings, initialize runtime memory, archive stale work, reconcile notes, or erase a subject; manages authorized HOT/WARM/COLD working memory across all disciplines while preserving registry event ownership and privacy controls. Not for changing canonical registry facts - route those through the owning registry. 项目记忆/跨会话
Write, create, and improve CLAUDE.md project memory files for Claude Code. Use when: (1) Creating or bootstrapping a new CLAUDE.md, (2) Improving, refactoring, or splitting a bloated CLAUDE.md, (3) Questions about CLAUDE.md structure, imports, or modular rules, (4) After significant codebase exploration—cache discoveries to avoid re-crawling.
Reconcile session outcomes into persistent project memory files. Updates project state, backlog, and status via section-aware merging -- not a session dump. Use at the end of any significant work session. Use when: 'session close', 'close session', 'save session', 'update memory', 'wrap up', 'end of session', or before ending a big session.