taches-toolkit
claudetaches commands + agents: consider:* thinking models, /audit-* (+3 auditor agents), /heal-skill, /create-*, /run-*, /whats-next, /ask-me-questions. As-is, reshape deferred.
7 skills · 28 commands · 3 agents
Pack a folder as single AI-readable file for cross-project context.
Plugin repomix from marketplace lars-cc-skills in lars-hh/lars-cc-skills. Commands read from the repo's manifest — 19 days ago.
repomixPack an entire repository (or a subdirectory / a curated file set) into a single AI-friendly file, ready to feed into a long-context LLM session. Wraps the `repomix` CLI (https://github.com/yamadashy/repomix) for use inside Claude Code. Use when you want to bring an external project into the current
taches commands + agents: consider:* thinking models, /audit-* (+3 auditor agents), /heal-skill, /create-*, /run-*, /whats-next, /ask-me-questions. As-is, reshape deferred.
7 skills · 28 commands · 3 agents
Generate Keep-a-Changelog-conformant CHANGELOG.md from git log.
1 skill
Keep a coding project pointed at its goal: records direction in .compass/, captures ideas the moment they surface, reports drift. Modes start/check/capture/wrap. Adopts an existing roadmap instead of duplicating it.
1 skill
Generate Mermaid diagrams (flowchart, sequence, ERD, C4, state, Gantt) from text descriptions.
1 skill
Audit a skill or plugin folder for supply-chain risks (LICENSE, allowed-tools, bash calls).
1 skill
Run a time-boxed spike answering one falsifiable question: charter gate, prediction before evidence, iteration budget, counter-checked verdict, enforced capture into a spike index. Parks questions via --stub.
1 skill
A second brain for Claude Code + Obsidian inspired by Karpathy's LLM Wiki gist. Turn any LLM CLI into a disciplined wiki maintainer: incrementally ingest sources into a persistent, interlinked markdown vault; update entity/concept/source pages; flag contradictions; maintain index and append-only log. Knowledge compounds instead of being re-derived by RAG on every query. Ships 3 sub-agents (wiki-ingestor, wiki-librarian, wiki-linter), 5 slash commands (/wiki-init, /wiki-ingest, /wiki-query, /wiki-lint, /wiki-log), 8 Python tools (stdlib only: init_vault, ingest_source, update_index, append_log, wiki_search BM25, lint_wiki, graph_analyzer, export_marp), 8 reference docs, full vault templates (CLAUDE.md, AGENTS.md, cursorrules, 5 page templates), and a worked example vault. Cross-tool compatible with Claude Code, Codex CLI, Cursor, Antigravity, OpenCode, and Gemini CLI.
1 skill · 5 commands · 3 agents
Brainstorm, plan, debug, review, and compound learnings with AI agents
39 skills
Stop re-explaining your notes to Claude. Turns your Obsidian vault into memory Claude can actually search, and keeps it true: new sources rewrite existing pages, contradictions reconcile, and stale facts get flagged. AI note-taking and PKM for Claude Code.
1 skill · 49 commands · 1 MCP server · hooks
Audit and upkeep skills that keep the rules and skills in a Claude Code setup from piling up and going stale. Ask "audit my skills" and skill-stocktake proposes keep, merge or retire for each skill with a reason; the audit skills change a file only after you confirm it. Skills only: no hooks, no MCP servers, no settings. Some skills run bundled Python scripts with uv, and skill-comply and skill-stocktake start separate claude -p sessions with the shell and subagent tools denied.
20 skills
Generate research-backed knowledge systems from natural conversation. 15 kernel primitives, 26 commands, 249 research claims, 3 presets.
26 skills · 1 agent · hooks
Complete Obsidian integration skill pack with 24 skills covering vault management, plugins, sync, templates, and knowledge management. Flagship tier vendor pack.
24 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.