obsidian
claudecodexObsidian vault workflows (notes/markdown/diagrams/canvas) + LLM wiki layer (defuddle needs CLI).
23 skills · 1 agent
Self-contained toolkit to author Claude Agent Skills — create, score, check consistency, refactor, tune, dogfood.
Plugin skill-dev-toolkit from marketplace monkey-skills in kouko/monkey-skills. Commands read from the repo's manifest — 6 days ago.
dogfood-skill-testingBlind behavioral test of a drafted SKILL.md: does it fire when expected (not over-fire), and does its workflow meet its contract on real input? Use for 'dogfood this skill' or 'will it fire before I ship'. For static scoring use skill-judge.
skill-consistency-checkFinds rules that contradict each other inside a skill folder. Use for 'check this skill for contradictions' or 'do these instructions conflict?'.
skill-creator-advanceCreates skills, redesigns them, or optimizes description triggering. Triggers: "build a skill", "make a slash command", "redesign", "improve". About to create a new skill or improve an existing one.
skill-judgeScore Agent Skill design quality on an 8-dimension rubric (0-120 + grade A-F). Use when reviewing or scoring a SKILL.md / skill package, or 'is this skill well-designed?'. Behavioral testing → dogfood-skill-testing; redesign → skill-creator-advance.
skill-refactorToken/structure refactor of a skill, preserving output behavior — checks equivalence, ≥10% token cut, invariants. Use for 'shorten this skill', 'reduce tokens', '縮減 SKILL.md'. Output A/B → skill-tuning; redesign/create → skill-creator-advance.
skill-tuningOutput-quality A/B for an existing skill: generate variants, run blind on the same prompts, human picks the winner. Use to tune a skill's output style/voice/tone. For redesign use skill-creator-advance; for token refactor use skill-refactor.
Obsidian vault workflows (notes/markdown/diagrams/canvas) + LLM wiki layer (defuddle needs CLI).
23 skills · 1 agent
Google Workspace toolkit on the official gws CLI (drive/docs/sheets/gmail; Claude Code CLI only).
18 skills · 1 command
Pipeline copywriting toolkit — 14 skills from intake to audit, grounded in PASONA/Cialdini/FTC.
14 skills · 2 agents
Three-layer investing research toolkit — data, analysis, report skills.
15 skills · 1 agent
Domain-expert team skills (planning/code/design/research/copywriting) with quality-gate checkpoints.
11 skills · 2 agents
Multi-scope coach for the 4 Disciplines of Execution — Socratic coach + single-artifact audit modes.
12 skills
Install the "Skill Author" editorial skill bundle for Claude Code.
6 skills
Converts books, documentation folders, and source collections (PDF, EPUB, DOCX, HTML, Markdown, RST, AsciiDoc, RTF, MOBI/AZW) into structured agent skills: a master SKILL.md with core frameworks and a topic index, on-demand chapter files, a glossary, a patterns file, and a decision cheatsheet. Ships 4 stdlib-only tools (multi-format extractor with invisible-Unicode sanitization, four-family generated-skill validator covering frontmatter/safety/budget/index, pre- and post-flight token budget estimator with a worth-converting verdict, and a plugin emitter that wraps a compiled skill as an installable claude-skills package behind a rights gate), 5 references citing 7-8 sources each, a cs-book-to-skill agent, and /cs-book-to-skill + /cs-book-to-plugin commands. Derived from virgiliojr94/book-to-skill (MIT).
1 skill · 2 commands · 1 agent
制作新 Skill,或改进已有 Skill。先按改动规模给出方案并等待确认,再生成或修改文件,并用真实任务对比改动前后的表现。用户要求做 Skill、把反复出现的问题沉淀成 Skill、修改或修复 Skill、根据失败案例改进 Skill、检查或测试 Skill 时使用;只有用户明确要求分享或发布时,才准备 GitHub 仓库并验证 `npx skills add`。
1 skill
Turn raw PM content into a compliant, publish-ready skill.
1 skill
Turns the corrections and repeated workflows of your work sessions into small, reviewed skill updates: every change comes with its evidence and a written reason, and nothing touches a skill until you approve and install it.
1 skill
Write, upgrade or audit Claude skills so they change what gets generated: distil rules from real corrections, turn them into required artifacts, gates and scripts, and lint any skill folder with a 0-100 health score (name, trigger clause, orphan and dangling files, oversized body).
1 skill
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.