instruction-eval
claudeMeasure whether an LLM instruction changes model behavior.
11 skills
Software engineering discipline skills, agent-agnostic: outermost-test-first signature-first TDD, systematic debugging, bug triage, architecture improvement, and receiving code review. Used ad hoc or by dev-cycle.
Plugin dev-discipline from marketplace my-claude-skills in ryzhakar/claude-skills. Commands read from the repo's manifest — 23 days ago.
improve-architectureFind architectural friction — places where understanding a codebase breaks down — explore in parallel several designs for a deepened module — one hiding more implementation behind a smaller interface — and write an RFC — a proposal document — recommending one. "improve the architecture", "find refac
receiving-code-reviewAct on code review feedback — each item being one change a reviewer asks for, so a comment asking for two changes holds two items — by verifying each against the code, clarifying every unclear item before implementing any, pushing back with evidence, and implementing one item at a time. "address the
systematic-debuggingFind the root cause of a bug, a test failure, an error, or an unexpected behavior before changing any code, then fix the cause once. "debug this", "why does this fail", "the test is failing", "find the root cause", "this keeps breaking", "the fix didn't work", a build or integration failure, or any
tddBuild code by writing one failing test through the surface its callers use before any code, designing the functions beneath that surface before filling them, and refactoring once every test passes. "tdd", "write tests first", "test-driven development", "red-green-refactor", "implement using tdd", "w
triage-issueDiagnose a reported bug to its root cause and write an issue document carrying a test-first fix plan, without fixing the code. "triage this", "this is broken", "investigate a bug", "find the root cause and file it", "write up this bug", "file an issue", or any bug report that asks for a diagnosis ra
Measure whether an LLM instruction changes model behavior.
11 skills
Domain-free skills governing how an agent conducts itself while working, independent of orchestration, memory, or any specific engineering domain.
6 skills · hooks
Development cycle orchestration: specify, plan, implement, review, integrate. A spec-capturer that interviews the owner, worktree-isolated implementers, spec and code-quality reviewers, and a review chain enforced by hooks.
1 skill · 4 agents · hooks
Cost-tiered development cycle over dev-cycle: an opus prescriber writes prescriptions that leave no decision, a sonnet suborchestrator runs the loop and both reviews, disposable haiku executors follow the prescription literally. No hooks.
2 skills · 3 agents
Playwright test lifecycle orchestrator. One skill drives the full loop: plan from live browser exploration, generate accessible .spec.ts files, execute with failure classification, and self-heal broken locators via deterministic ten-tier recovery with confidence-based PR routing.
1 skill · 4 agents
Agent delegation framework and multi-agent research orchestration. Decompose work across model tiers, manage parallel swarms, and govern quality.
2 skills
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
8 skills · 1 MCP server
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
Use Alibaba Open Code Review from local Codex.
2 skills
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.