Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
ask-questions-if-underspecified
Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.
zby/llm-do 18
-
seed
Add a source file to the processing queue. Checks for duplicates, creates archive folder, moves source from inbox, creates extract task, and updates queue. Triggers on "/seed", "/seed [file]", "queue this for processing".
zby/llm-do 18
-
graph
Interactive knowledge graph analysis. Routes natural language questions to graph scripts, interprets results in domain vocabulary, and suggests concrete actions. Triggers on "/graph", "/graph health", "/graph triangles", "find synthesis opportunities", "graph analysis".
zby/llm-do 18
-
revisit
Update old notes with new connections. The backward pass that /connect doesn't do. Revisit existing notes that predate newer related content, add connections, sharpen claims, consider splits. Triggers on "/revisit", "/revisit [note]", "update old notes", "backward connections", "revisit notes".
zby/llm-do 18
-
decomplect-py
Architectural code analysis for Python design quality. Evaluates simplicity (Rich Hickey), functional core/imperative shell (Gary Bernhardt), and coupling (Constantine & Yourdon). Use for design review or architectural assessment of Python code.
zby/llm-do 18
-
rethink
Challenge system assumptions against accumulated evidence. Triages observations and tensions, detects patterns, generates proposals. The scientific method applied to knowledge systems. Triggers on "/rethink", "review observations", "challenge assumptions", "what have I learned".
zby/llm-do 18
-
remember
Capture friction as methodology notes. Three modes — explicit description, contextual (review recent corrections), session mining (scan transcripts for patterns). Triggers on "/remember", "/remember [description]".
zby/llm-do 18
-
review
Combined verification — recite (description quality via cold-read prediction) + validate (schema compliance) + review (health checks). Use as a quality gate after creating notes or as periodic maintenance. Triggers on "/review", "/review [note]", "verify note quality", "check note health".
zby/llm-do 18
-
next
Surface the most valuable next action by combining task stack, queue state, inbox pressure, health, and goals. Recommends one specific action with rationale. Triggers on "/next", "what should I do", "what's next".
zby/llm-do 18
-
learn
Research a topic and grow your knowledge graph. Uses Exa deep researcher, web search, or basic search to investigate topics, files results with full provenance, and chains to processing pipeline. Triggers on "/learn", "/learn [topic]", "research this", "find out about".
zby/llm-do 18
-
stats
Show vault statistics and knowledge graph metrics. Provides a shareable snapshot of vault health, growth, and progress. Triggers on "/stats", "vault stats", "show metrics", "how big is my vault".
zby/llm-do 18
-
extract
Extract structured knowledge from source material. Two modes — `extract` (default) for comprehensive atomic claim extraction, and `analyze` for design proposals where one impact-analysis note replaces claim decomposition. A relevance filter ("does this change how we build our project?") applies to all modes. For `extract` mode on domain-relevant sources, skip rate must be below 10%. Triggers on "/extract", "/extract [file]", "extract insights", "mine this", "process this".
zby/llm-do 18
-
tasks-system
zby/llm-do 18
-
ask-questions-if-underspecified
Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.
zby/llm-do 18
-
decomplect-py
Architectural code analysis for Python design quality. Evaluates simplicity (Rich Hickey), functional core/imperative shell (Gary Bernhardt), and coupling (Constantine & Yourdon). Use for design review or architectural assessment of Python code.
zby/llm-do 18
-
validate-typescript
Run TypeScript compiler type-checking (tsc --noEmit) to validate type safety and catch type errors. Returns structured output with error counts, categories (type/syntax/import errors), and affected files. Used for quality gates and pre-commit validation.
BerryKuipers/claude-code-toolkit 6
-
validate-coverage-threshold
Validate test coverage meets minimum thresholds (default 80% overall, 80% statements, 75% branches, 80% functions). Parses coverage reports from coverage/coverage-summary.json or test output. Returns pass/fail status with detailed metrics and identifies uncovered files.
BerryKuipers/claude-code-toolkit 6
-
quality-gate
Comprehensive quality validation for TypeScript/JavaScript projects - runs TypeScript checks, tests, coverage analysis, build validation, and linting with structured JSON results
BerryKuipers/claude-code-toolkit 6
-
run-comprehensive-tests
Execute comprehensive test suite (Vitest/Jest) with coverage reporting and failure analysis. Returns structured output with test counts (total/passed/failed), coverage percentage, duration, and detailed failure information. Used for quality gates and CI/CD validation.
BerryKuipers/claude-code-toolkit 6
-
validate-build
Run production build validation (npm run build, vite build, tsc) to ensure code compiles and builds successfully. Returns structured output with build status, duration, size metrics, and error details. Used for quality gates and deployment readiness checks.
BerryKuipers/claude-code-toolkit 6
-
validate-lint
Run ESLint and Prettier validation to check code style, formatting, and best practices. Returns structured output with error/warning counts, rule violations, and affected files. Used for code quality gates and pre-commit validation.
BerryKuipers/claude-code-toolkit 6
-
validate-git-hygiene
Validate git commit messages, branch naming conventions, and repository hygiene. Returns structured output with validation results for commit format (conventional commits), branch naming, and best practices. Used for quality gates and git workflow validation.
BerryKuipers/claude-code-toolkit 6
-
audit-dependencies
Run npm audit and check for outdated/vulnerable dependencies. Returns structured output with vulnerability counts by severity, outdated packages, and recommended updates. Used for security validation and dependency health checks.
BerryKuipers/claude-code-toolkit 6
-
overlay-loader
BerryKuipers/claude-code-toolkit 6