Menu
SkillsMP a collecté 55 skills depuis JSai23/claude-tooling. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 40 skills collectés sur 55.
Write high-quality session prompts (SESSION_WORKER.md and SESSION_REVIEWER.md) for an agent loop. Reads repo context and follows the loop-author guide to produce targeted, effective prompts. Use when setting up a new loop or rewriting session prompts for an…
Langue du texte source : anglais
Pre-flight checks and launch for agent loops. Validates branch state, session prompts, creates loop directory structure, and launches run.sh in a tmux session. Use when the user wants to start a new agent loop in the current repo.
Langue du texte source : anglais
Cross-repo visibility for agent loops. Lists running, completed, and crashed loops. Reads the registry and per-repo tracking logs. Shows tmux attach commands. Use when checking what loops are active, what ran recently, or loop details.
Langue du texte source : anglais
Capture feedback about wf, util, or vault plugins and file it as a GitHub issue for improvement. Use after any session where the tooling fell short — wrong agent behavior, missing skill coverage, misleading prompts, workflow friction, or convention gaps. Only…
Langue du texte source : anglais
Write high-quality session prompts (SESSION_WORKER.md and SESSION_REVIEWER.md) for an agent loop. Reads repo context and follows the loop-author guide to produce targeted, effective prompts. Use when setting up a new loop or rewriting session prompts for an…
Langue du texte source : anglais
Pre-flight checks and launch for agent loops. Validates branch state, session prompts, creates loop directory structure, and launches run.sh in a tmux session. Use when the user wants to start a new agent loop in the current repo.
Langue du texte source : anglais
Cross-repo visibility for agent loops. Lists running, completed, and crashed loops. Reads the registry and per-repo tracking logs. Shows tmux attach commands. Use when checking what loops are active, what ran recently, or loop details.
Langue du texte source : anglais
Logging auditor focused on signal over noise. Use for /logging.
Langue du texte source : anglais
Add, fix, or update logging in project code
Langue du texte source : anglais
Add, fix, or update logging in project code
Langue du texte source : anglais
Use this agent for processing inbox, filing notes, organizing the vault, updating living docs, maintaining backlinks and tags, and running audit passes. The organizer that turns raw captures into structured knowledge.
Langue du texte source : anglais
This skill should be used when the user asks to "process inbox", "auto process", "file this note", "triage inbox", "route this to the right place", or needs to automatically move notes from 0-Inbox to their correct PARA destination.
Langue du texte source : anglais
Use this agent for thinking through problems, exploring what your notes say, discussing where projects stand, and synthesizing across areas. A research partner that reads your vault and thinks with you. Writes synthesis to inbox.
Langue du texte source : anglais
Use this agent for interactive writing sessions. Drafts notes from conversation, encodes filing intent for the librarian, writes to inbox only. A transcription partner that captures your thinking well.
Langue du texte source : anglais
This skill should be used when the user asks to "check tags", "update tags", "audit tags", "change tag", "list tags", "tag this note", "fix frontmatter tags", or needs to manage tags across notes.
Langue du texte source : anglais
This skill should be used when the user asks to "file a note", "organize vault", "PARA structure", "vault rules", "add frontmatter", "tag a note", "archive a note", "naming convention", or when working with Obsidian vault files.
Langue du texte source : anglais
Implementation session — execute milestones from a plan, write production code and tests, follow codebase patterns, surface deviations, maintain living docs. Launched via: claude --agent wf:builder
Langue du texte source : anglais
Maintenance session — continuous cleanup of LLM-generated technical debt in code and documentation. Keeps docs current, prunes stale plans, fixes drift. Launched via: claude --agent wf:gardener
Langue du texte source : anglais
Log decisions, progress, deviations, and discoveries during any workflow phase
Langue du texte source : anglais
Planning and design session — everything before code. Use when starting a feature, designing a system change, or breaking down complex work into an execution plan. Launched via: claude --agent wf:planner
Langue du texte source : anglais
Verification session — end-of-cycle quality review covering design, integrity, cleanliness, and production readiness. Delegates to specialized agents via Task tool. Launched via: claude --agent wf:verifier
Langue du texte source : anglais
Implementation practices — deviation protocol, progress tracking, code standards, codebase reflection
Langue du texte source : anglais
ALWAYS USE if you are the builder. Use after every implementation pass — update living docs, maintain diagrams (Mermaid for formal, ASCII for loose), reconcile plan with reality, update ARCHITECTURE.md when system shape changes. Documentation is a core…
Langue du texte source : anglais
The agent documentation system — doc types, folder structure, frontmatter conventions, agent roles, lifecycle
Langue du texte source : anglais
Log decisions, progress, deviations, and discoveries during any workflow phase
Langue du texte source : anglais
How to write implementation plans — code structure, module layout, component connections, with execution blocks at the end
Langue du texte source : anglais
ALWAYS USE if you are the verifier or gardener. Use after any build cycle to audit documentation accuracy — check diagram drift, living doc freshness, ARCHITECTURE.md currency, cross-link integrity, and plan status. Gardener uses broadly across the full doc…
Langue du texte source : anglais
Documentation writer focused on brevity. Use for /doc.
Langue du texte source : anglais
Capture feedback about wf, util, or vault plugins and file it as a GitHub issue for improvement. Use after any session where the tooling fell short — wrong agent behavior, missing skill coverage, misleading prompts, workflow friction, or convention gaps. Only…
Langue du texte source : anglais
How to think about design — product outcomes, system architecture, code structure, tradeoffs
Langue du texte source : anglais
Ask questions about design, architecture, or how code fits together
Langue du texte source : anglais
Answers design and architecture questions from plans and docs. Use for /ask.
Langue du texte source : anglais
Create session handoff document for transferring work to another session
Langue du texte source : anglais
Generate or update project documentation
Langue du texte source : anglais
Resume work from a previous handoff document
Langue du texte source : anglais
Rust code quality audit based on Apollo best practices
Langue du texte source : anglais
Token-efficient code analysis reference. Use when analyzing large codebases or needing structured code intelligence.
Langue du texte source : anglais
This skill should be used when the user asks to "search notes",
Langue du texte source : anglais
Generate or update standard code documentation — docstrings, rustdoc, API references, READMEs
Langue du texte source : anglais
This skill should be used when the user asks to "add backlinks", "find related notes", "what should this link to", "update backlinks", "suggest connections", or needs to find appropriate wikilinks for a note.
Langue du texte source : anglais