AI Agent Skills

Generates an accurate API reference from source and handlers: endpoints, params, request and response shapes, status codes, and auth.

Builds a Keep a Changelog section from a commit range — groups Conventional Commits into Added / Fixed / Changed and links the PRs behind them.

Turns a staged git diff into a clean Conventional Commits message — correct type, tight summary, and a body that explains why, not what.

Turns a raw meeting transcript or messy notes into a clear summary — decisions, action items with owners, and open questions — without inventing anything.

Reviews a PR diff for correctness, security, and clarity — reporting concrete, prioritized findings with file:line, not vague praise.

Generates a runnable pytest module for a target function or class — happy path, edge cases, and error cases with fixtures and parametrize.

Proposes a refactor plan, then a minimal behavior-preserving diff — insisting tests pass before and after, in small safe steps.

Reads a slow query and its EXPLAIN plan, finds the bottleneck, and proposes a safe rewrite or index that preserves the results.

Audits UI against WCAG 2.2 AA — contrast, keyboard, focus, ARIA, alt text, labels — reporting each issue with severity and a fix.

Reproduces a bug with a failing test first, isolates the root cause, then applies a minimal fix and confirms the test passes.

Reads a failing CI log, pinpoints the failing step and root cause, then tells you whether it's a real bug, a build/lint issue, or a flaky test.

Produces a guided walkthrough of an unfamiliar codebase — entry points, key modules, data flow, and where to make a change.

Reviews a database migration for safety: locking, backfills, non-reversible operations, downtime risk, and missing rollback steps.

Audits project dependencies for known CVEs and outdated packages, reporting severity and a concrete upgrade path without auto-upgrading.

Given a function's spec or signature, enumerates boundary, empty, null, unicode, overflow, and concurrency cases and turns them into test cases.

Guides a safe branch, PR, rebase and merge flow — explains trunk-based vs git-flow and stops you from force-pushing a branch other people share.

Turns a rough bug or feature note into a well-formed ticket — title, context, repro steps, expected vs actual, and acceptance criteria — ready for Jira, Linear, or GitHub.

Turns a described system or flow into a valid, readable Mermaid diagram embedded in Markdown, with the right diagram type.

Writes Playwright end-to-end tests from a described user flow using role-based selectors and web-first assertions, with no arbitrary waits.

Rewrites a vague prompt into a clear, testable one — adding role, context, constraints, output format, and success criteria — and explains each change.

Drafts a clear, honest README from a project's actual files — what it does, how to install and run it, and how to contribute — without inventing features.

Turns a version's merged PRs and commits into human-facing release notes — highlights, breaking changes and upgrade steps, honest about what changed.

Explains what a SQL query does in plain English, step by step, and flags likely performance traps — without running it against your database.

Turns yesterday's git activity into a concise standup update — what shipped, what's in progress, and any blockers — grouped and readable, not a raw commit dump.

Writes focused unit tests for a function or module — covering the happy path, edge cases, and error handling — in the project's existing test framework.