hypothesis-library
Curated repository of experiment hypotheses, assumptions, and historical
Browse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Curated repository of experiment hypotheses, assumptions, and historical
One-command skill contribution — generate a SKILL.md from your domain expertise and submit to GitHub Issues for maintainer review
To be used when the user explicitly requests to "generate a skill README", "write a user guide", or "update the skill documentation". Write a best-practice compliant README.md user guide for Agent Ski…
When updating the references/takt submodule, a skill to update the takt-* skill set (takt-task-builder, takt-piece-builder, takt-facet-builder, takt-analyzer, takt-optimizer) to follow the latest takt…
Choose the correct CLAUDE.md or LESSONS.md template for journalism projects. Use when starting a new project, setting up documentation, or unsure which template category fits best. Provides decision t…
Searches and recommends Claude Code skills and plugins from local database and SkillsMP API. Activates when user asks to find skills, search plugins, get recommendations for PDF/Git/code-review/fronte…
Creates, edits, and manages Obsidian vault content including notes, templates, daily notes, and dataview queries. Use when working with markdown files in an Obsidian vault, creating notes, writing tem…
This skill should be used when the user asks tax-related questions, wants advice on deductions or tax savings, or needs expert guidance equivalent to a tax accountant (税理士) or life planner. Trigger ph…
Check and update installed Claude Code skills from multiple sources (Claude plugins and npx skills). Scans for available updates, supports batch or individual updates with intelligent local change mer…
Extract a shareable runnable template under templates/NNN-slug/ from a real project: copy + de-brand + remove secrets + add env examples + docs, with minimal refactors. Use when you have a working pro…
Keep activity suggestions safe and respect local conditions
INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration options.
Evaluate a single skill's quality against 8 completeness categories derived from Anthropic's official skills repository. Scores preparation, progression, verification, scripts, examples, anti-patterns…
A package manager for AI knowledge. Meta-skill for on-demand skill discovery and installation — search curated local repositories or the global skills.sh registry. Self-teaching capability that finds,…
This skill should be used when the user asks to "demonstrate advanced skill structure", "show comprehensive skill patterns", "create skill with references", or needs a complete skill example with bund…
Write, review, or fix skills and AGENTS.md files. Use when creating a new skill, auditing an existing one, refactoring a bloated AGENTS.md, or reviewing whether content passes the authoring test. Do N…
When users request to "search for an app", "find an app", "install an app", "uninstall an app", "check for updates", "upgrade an app", "view app details", "report a problem", or mention the use of Lin…
Initialize the complete infrastructure for Spec-driven development of a project. This is called when a new project uses the Spec workflow for the first time, responsible for setting up the full projec…
Proactively discover AI rules, prompts, agents, skills, and skill bundles exposed by npm packages in a project, integrate them into editor-specific rule/config files (AGENTS.md, .cursor/rules, .rules,…
Transform infrastructure documentation, runbooks, and operational knowledge into reusable Claude Code skills. Convert Proxmox configs, Docker setups, Kubernetes deployments, and cloud infrastructure p…
Take any user output — prompt, story, procedure, analysis — and make it maximally effective through iterative intent extraction and focused questioning. Use when user says "sharpen this", "make this m…
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Background context for housing loan tax credit (住宅ローン控除) in the shinkoku tax filing plugin. Contains eligibility requirements, credit limits, calculation rules, and interaction with furusato-nozei for…
Autonomous judgment + autonomous discovery workflow (v2.0 - integrating Ralph Wiggum philosophy). Not 'nothing to do → terminate' but 'nothing to do → self-discovery'. 5-tier priority, 9 command auto-…