Explorar skills

Trace the root cause of a bug or unexpected behaviour. Use when the user says "why is this broken", "why does this fail", "whybroken", "something's wrong with X", or pastes an error. Never patches symptoms — always finds the cause first.

Run the repo's make targets in dependency order (setup → lint → test → end-to-end) and verify each command's terminal output against its `logs/dev-<ts>-<cmd>.log` archive. Supports a full audit and a fast variant. Use whenever the user wants to validate the toolchain is clean, run lint+test locally before pushing, or reconcile terminal output against the dev-runner log archives — phrasings like "r

Analyze pending git changes and write a structured, conventional-commit plan to COMMITS.md so the user can review and stage commits in batches before committing. Use whenever the user wants to group working-tree or staged changes into sensible commits, draft commit messages for a dirty working tree, or prepare a commit plan from a diff.

Audit the latest GitHub Actions workflow runs on the current branch/PR for warnings, errors, failures, deprecation notices, and other log noise — then fix what's fixable in-repo (workflow YAML, configs, source, tests). Hands commit + push back to the developer. Use after CI finishes and before merge, or whenever the user asks about failing/noisy CI — phrasings like "audit the PR", "why did CI fail

Cross-repo drift audit across linked repos listed in `~/.claude/techne.toml` (configurable per-user). Read-only inspection of CI action pins, toolchain pins in pyproject.toml, skill-context structural parity, GitHub merge settings, open PRs, and branch hygiene. Triggers on phrases like "audit the sisters", "are the sisters in sync", "check cross-repo drift", or when multiple sister repos are menti

Use when building Python 3.11+ applications requiring type safety, async programming, or robust error handling. Generates type-annotated Python code, configures mypy in strict mode, writes pytest test suites with fixtures and mocking, and validates code with black and ruff. Invoke for type hints, async/await patterns, dataclasses, dependency injection, logging configuration, and structured error h

Use this skill when naming or renaming a GitHub repository, product, CLI, plugin, skill pack, framework, app, or public developer project. It reverse-engineers association-based open-source naming patterns and produces product name, repo slug, tagline, About description, topics, rejected names, and README hero copy.

Rewrite GitHub repository names, About descriptions, README intros, and website tool cards so they communicate practical user value.

Translate natural-language requests about modifying an AI coding agent, its skills, MCP tools, MCP servers, prompts, routing, tool descriptions, context loading, memory, portability, or other agentic behavior into the concrete mechanics of the target system. Use when a request is underspecified, phrased in human terms instead of runtime terms, or risks making the wrong change because the agent mus

Use when comparing two versions of agent output to determine which is better, or when evaluating whether a skill produces higher quality results than baseline

Structured feedback session analyzing Claude Code usage over a configurable time window. Gathers evidence from git history, memory files, and project state, then delivers an honest 5/5/5 report (going well, not going well, what to improve) with specific evidence and trend tracking against previous sessions. Use when asked to "run feedback", "how am I doing", "feedback session", "usage review", "se

Run multiple skills on the same task in parallel and compare outputs side by side. A creative pitch room -- give it a brief, and it finds skills (local + trusted community repos) to work on it independently, then presents all outputs for comparison. Use when asked to "skill battle", "compare skills", "run multiple skills", "pitch room", "get different takes", "split test this", "give me options",