Claude Skills

Delegate tasks to external LLM services (Gemini, Qwen) with quota, logging, and error handling.

Triggers: source, cite, reference, factual claim, verify, attribution Intelligent sourcing that requires citations only for high-value factual claims, balancing accuracy with token efficiency.

Triggers: KISS, YAGNI, SOLID, clean code, code quality, refactor, design principles Provides guidance on fundamental software design principles to reduce complexity, prevent over-engineering, and improve maintainability.

Automatic context management with graceful handoff to continuation subagent. Triggers: context pressure, 80% threshold, auto-clear, context full, continuation, session state, checkpoint Use when: Context usage approaches 80% during long-running tasks. This skill enables automatic continuation without manual /clear. The key insight: Subagents have fresh context windows. By delegating remaining work to a continuation subagent, we achieve effective "auto-clear" without stopping the workflow.

Gemini CLI delegation workflow implementing delegation-core for Google's Gemini models.

Triggers: writing style, voice, tone, style guide, exemplar, style learning Learn and extract writing style patterns from exemplar text for consistent application. Triggers: learn style, extract style, style profile, writing voice, tone analysis, style guide generation, exemplar analysis Use when: creating a style guide from existing content, ensuring consistency across documents, learning a specific author's voice, customizing AI output style DO NOT use when: detecting AI slop - use slop-detector instead. DO NOT use when: just need to clean up existing content - use doc-generator with --remediate. Use this skill to build style profiles from exemplar text.

TDD-style testing methodology for skills using fresh subagent instances to prevent priming bias and validate skill effectiveness. Triggers: test skill, validate skill, skill testing, subagent testing, fresh instance testing, TDD for skills, skill validation Use when: validating skill improvements, testing skill effectiveness, preventing priming bias, measuring skill impact on behavior DO NOT use when: implementing skills (use skill-authoring instead), creating hooks (use hook-authoring instead)

Generate language-specific Makefile with common development targets

Generate or remediate documentation with human-quality writing and style adherence. Triggers: documentation, generate docs, write docs, technical writing, generate documentation, write readme, create guide, doc generation, remediate docs, polish content, clean up docs. Use when creating new documentation, rewriting AI-generated content, or applying style profiles. Do not use for slop detection only (use slop-detector) or learning styles (use style-learner).

Configure comprehensive three-layer pre-commit quality system with linting, type checking, and testing enforcement

Surfaces expert frameworks and proven methodologies before creating OR evaluating skills, hooks, agents, or commands. Helps select approaches from domain masters. Triggers: methodology, framework, expert approach, best practices, masters, proven method, domain expertise, how should I approach, what's the best way, evaluate skill, review methodology, is this grounded, optimization check. Use when starting creation workflows, evaluating methodology gaps, or seeking domain expertise. Do not use if you already have a specific methodology or are fixing syntax/structural issues.

Enforces "prove before claim" discipline - validation, testing, and evidence requirements before declaring work complete. Triggers: validation, definition-of-done, proof, acceptance-criteria, testing, completion, finished, done, working, should work, configured, ready to use, implemented, fixed, improvement validated, workflow optimized, performance improved, issue resolved. Use when claiming work is complete, recommending solutions, or finishing implementations. Do not use when asking questions or for work clearly in-progress. MANDATORY: This skill is required before any completion claim.

Transform project brief into detailed, testable specifications using spec-driven development methodology

Multi-LLM deliberation framework for strategic decisions through pressure-based expert consultation

Prevents sycophantic reasoning through checklist-based analysis, categorical integrity, and evidence-following to uncomfortable conclusions. Triggers: conflict, disagreement, debate, ethical, controversial, pushback, interpersonal analysis, competing values, adjudication, "who is right", moral dilemma, harm assessment, ethical question, controversial claim. Red Flags: "I agree that", "You're right", "Great point", "Absolutely", "That's a fair point", "I can see why", agreement without validation, softening conclusions, hedging without evidence, retracting under pressure. Use when analyzing conflicts, evaluating ethical claims, or noticing sycophantic thought patterns. Do not use for routine implementation or simple factual questions. CRITICAL: This skill overrides conversational tendencies toward politeness. Agreement requires validity and accuracy.

Systematic task execution with checkpoint validation, progress tracking, and quality gates

Qwen CLI delegation workflow implementing delegation-core for Alibaba's Qwen models.

Triggers: workflow error, inefficient execution, workflow failure, execution monitor Monitor workflow executions for errors and inefficiencies. When issues are detected, automatically create GitHub issues for workflow improvements via /fix-workflow. Use when: workflows fail, timeout, or show inefficient patterns DO NOT use when: normal workflow execution, simple command errors