Loading...
Loading...
Found 36 Skills
Expert at analyzing documentation quality, coverage, and completeness. Auto-invokes when evaluating documentation health, checking documentation coverage, auditing existing docs, assessing documentation quality metrics, or analyzing how well code is documented. Provides frameworks for measuring documentation effectiveness.
Guide Test-Driven Development workflow (Red-Green-Refactor) for new features, bug fixes, and refactoring. Identifies test improvement opportunities and applies pytest best practices. Use when writing tests, implementing features, or following TDD methodology. **PROACTIVE ACTIVATION**: Auto-invoke when implementing features or fixing bugs in projects with test infrastructure (pytest files, tests/ directory). **DETECTION**: Check for tests/ directory, pytest.ini, pyproject.toml with pytest config, or test files. **USE CASES**: Writing production code, fixing bugs, adding features, legacy code characterization.
Session management — restores terminal tab name, user preferences, and context bookmarks on session start. Auto-invoked at session start via AGENTS.md. Also invokable manually to change preferences or bookmark context for the next session.
Plan-then-execute implementation against SPEC.md. Native single-thread loop, no sub-agents. On test or build failure, auto-invokes the backprop skill before retrying — a failed verification always considers whether a new §V invariant would prevent recurrence. Triggers when the user asks to build, implement, execute the spec, or tackle a specific §T task (`build §T.3`, `build --next`, `implement next task`, `run the build`). Expects SPEC.md to exist; if not, defers to the spec skill.
Scaffold development rules for AI coding agents. Auto-invoked when user asks about setting up rules, coding conventions, or configuring their AI agent environment.
Creates system prompts, writes tool descriptions, and structures agent instructions for agentic systems. Use when the user asks to create, generate, or design prompts for AI agents, especially for tool-using agents, planning agents, or autonomous systems. **PROACTIVE ACTIVATION**: Auto-invoke when designing prompts for agents, tools, or agentic workflows in AI projects. **DETECTION**: Check for agent/tool-related code, prompt files, or user mentions of "prompt", "agent", "LLM". **USE CASES**: Designing system prompts, tool descriptions, agent instructions, prompt optimization, reducing hallucinations.
Comprehensive thoroughness framework. Auto-invoked when planning features, implementing code, fixing bugs, writing tests, analyzing existing code, auditing features, reviewing architecture, or investigating issues. Forces systematic consideration of all edge cases, failure modes, error scenarios, security implications, state transitions, and hidden assumptions so nothing gets missed. Do NOT invoke for trivial changes like typos, renames, single-line fixes, adding imports, or updating config values.
Expert at analyzing the quality and effectiveness of Claude Code components (agents, skills, commands, hooks). Assumes component is already technically valid. Evaluates description clarity, tool permissions, auto-invoke triggers, security, and usability to provide quality scores and improvement suggestions.
Issue creation expertise and convention enforcement. Auto-invokes when creating issues, writing issue descriptions, asking about issue best practices, or needing help with issue titles. Validates naming conventions, suggests labels, and ensures proper metadata.
Always Auto-invoked skill that creates/updates workspace AGENTS.md to instruct the agent to always search for existing skills before attempting any scientific task.
TDD-based code simplification that preserves behavior through tests. Use Red-Green-Refactor cycles to simplify code one test-verified change at a time. **DISTINCT FROM**: General code review or AI rewriting—this skill requires existing tests and only proceeds when tests confirm behavior is preserved. **PROACTIVE**: Auto-invoke when test-covered code has complexity (functions >50 lines, high cyclomatic complexity, duplication) and user wants to simplify it safely. Trigger phrases: 'clean up code', 'make code simpler', 'reduce complexity', 'refactoring help'. **NOT FOR**: Adding features or fixing bugs—use /tdd skill instead.
TDD enforcement during implementation. Reads `tdd:` setting from CLAUDE.md. Modes - strict (human approval for escape), soft (warnings), off (disabled). Auto-invoked by /implement.