Skill Registry

Use when a PR has review feedback and the user wants it addressed — pull the review comments, triage each one, apply the changes it warrants, and draft replies. Closes the loop between a review and the follow-up commit; it does not re-review the code from scratch.

Use when the user reports an error, bug, or unexpected behavior in this repo and wants help diagnosing it. Five phases — reproduce, diagnose root cause (read-only), write a failing test, fix, verify against the full suite.

Use when the user wants to upgrade the project's dependencies safely — bump versions, read changelogs for breaking changes, and verify the suite still passes. Upgrades incrementally and stops on the first break; it does not add new dependencies (that's a design decision to raise separately).

Use when the user wants code, a concept, or the current diff explained in this repo. With no specific target, explains the current branch diff; with a target, traces call chains and data flow end-to-end and explains in plain language.

Use when the user wants lint, format, and type errors fixed in the current changes. Reads CLAUDE.md for the repo's lint/format/type-check commands, runs each, and fixes only style/format/type issues — no behavior changes.

Use when the user pastes a ticket, design doc, or task description and wants it implemented. Multi-phase flow — understand, investigate (in plan mode), plan, implement, verify. Enforces strict scope rules and writes failing tests first for bug fixes.

Use when the user wants a PR description generated for the current branch. Reads commit history, file changes, and CLAUDE.md, then writes a Summary / Changes / Test Plan / Notes block to pr-description.md.

Use when the user wants to restructure code while preserving behavior exactly. Establishes a passing test baseline first, then makes incremental moves that each leave the suite green. Refuses to change behavior and structure in the same step.

Use when the user wants to cut a release — bump the version, update the changelog from conventional commits, and tag. Detects where the version lives, derives the next version from the commits since the last tag, and stages the release locally; it does not push or publish unless explicitly asked.

Use right before declaring an implementation done — a last-pass review of your OWN uncommitted change against a fixed checklist (reuse, stdlib, comments, dead code, tests, scope). Catches the things that make a diff read as AI-written before a human ever sees it. Reviews the current diff; it does not write new features.

Use when the user wants tests written for current changes (uncommitted diff or recent feature). Matches the repo's existing test framework, fixtures, and assertion style. Covers happy path, edge cases, and error paths without over-mocking.

Use when a PR has review feedback and the user wants it addressed — pull the review comments, triage each one, apply the changes it warrants, and draft replies. Closes the loop between a review and the follow-up commit; it does not re-review the code from scratch.

Use when the user reports an error, bug, or unexpected behavior in this repo and wants help diagnosing it. Five phases — reproduce, diagnose root cause (read-only), write a failing test, fix, verify against the full suite.

Use when the user wants to upgrade the project's dependencies safely — bump versions, read changelogs for breaking changes, and verify the suite still passes. Upgrades incrementally and stops on the first break; it does not add new dependencies (that's a design decision to raise separately).

Use when the user wants code, a concept, or the current diff explained in this repo. With no specific target, explains the current branch diff; with a target, traces call chains and data flow end-to-end and explains in plain language.

Use when the user wants lint, format, and type errors fixed in the current changes. Reads CLAUDE.md for the repo's lint/format/type-check commands, runs each, and fixes only style/format/type issues — no behavior changes.

Use when the user wants a PR description generated for the current branch. Reads commit history, file changes, and CLAUDE.md, then writes a Summary / Changes / Test Plan / Notes block to pr-description.md.

Use when the user wants to restructure code while preserving behavior exactly. Establishes a passing test baseline first, then makes incremental moves that each leave the suite green. Refuses to change behavior and structure in the same step.

Use when the user wants to cut a release — bump the version, update the changelog from conventional commits, and tag. Detects where the version lives, derives the next version from the commits since the last tag, and stages the release locally; it does not push or publish unless explicitly asked.

Use right before declaring an implementation done — a last-pass review of your OWN uncommitted change against a fixed checklist (reuse, stdlib, comments, dead code, tests, scope). Catches the things that make a diff read as AI-written before a human ever sees it. Reviews the current diff; it does not write new features.

Use when the user wants tests written for current changes (uncommitted diff or recent feature). Matches the repo's existing test framework, fixtures, and assertion style. Covers happy path, edge cases, and error paths without over-mocking.

Vast.ai CLI to manage GPU instances, volumes, serverless endpoints, and billing.

Create a new Langfuse integration page in the langfuse-docs repo. Use this skill whenever the user wants to add, create, draft, or scaffold an integration page, cookbook, or docs page for a new tool/framework/model-provider/gateway in Langfuse — triggers include "new integration", "integration page", "docs page for <X>", "cookbook for <X>", "add <X> to langfuse docs", or any request that results in a new `cookbook/integration_*.ipynb`. Also use when the user pastes working integration code, a link to a partner's docs, or rough notes and wants them turned into the standard Langfuse integration notebook. The skill produces a correctly formatted Jupyter notebook, updates `cookbook/_routes.json`, and tries to fetch the partner logo into `public/images/integrations/`.

An advanced, autonomous AI agent skill designed to execute complex, multi-step, and long-horizon tasks with high reliability and minimal human interruption.