测试
单元测试、集成测试与测试自动化
fix-stream
iterate
Turn a broken agent-stream URL (os.iterate.com/projects/<slug>/agents/streams/agents/<id>) into a red repro test, then a green fix, then a minimal fixture. Use when user says "fix <stream url>", pastes a stream URL with a complaint, or reports an agent chat that went wrong/silent.
forecast-premortem
lyndonkl
Use to stress-test predictions by assuming they failed and working backward to identify why. Invoke when confidence is high (>80% or <20%), need to identify tail risks and unknown unknowns, or want to widen overconfident intervals. Use when user mentions premortem, backcasting, what could go wrong, stress test, or black swans.
financial-unit-economics
lyndonkl
Use when evaluating business model viability, analyzing profitability per customer/product/transaction, validating startup metrics (CAC, LTV, payback period), making pricing decisions, assessing scalability, comparing business models, or when user mentions unit economics, CAC/LTV ratio, contribution margin, customer profitability, break-even analysis, or needs to determine if a business can be profitable at scale.
memory-retrieval-learning
lyndonkl
Use when long-term knowledge retention is needed (weeks to months), studying for exams or certifications, learning new job skills or technology, mastering substantial material that requires systematic review, combating forgetting through spaced repetition and retrieval practice, or when user mentions studying, memorizing, learning plans, spaced repetition, flashcards, active recall, or durable learning.
debt-audit
wcygan
Re-audit regularly - debt grows; quarterly audits prevent accumulation
spec-team
wcygan
Exploratory prototyping (use /research instead)
postmortem-team
wcygan
Blameless language guide
onboard
wcygan
Explore an unfamiliar codebase and generate an ARCHITECTURE.md with component diagrams, pattern catalog, and dev workflow guide. Use when joining a new project, picking up an OSS repo, or needing to understand how a codebase works. Keywords: onboard, architecture, explore, understand, codebase, new project, map, document, how does this work
spike
wcygan
Quick prototype or investigation in an isolated git worktree. Creates a worktree, spawns agents to explore a technical approach, and opens a draft PR with findings. Use for time-boxed technical exploration, feasibility testing, library evaluation, or codebase audits. Keywords: spike, prototype, worktree, explore, feasibility, proof of concept, PoC, try, experiment, can we use, audit, investigate, trace, wired up
interview
wcygan
Conduct an in-depth requirements interview to flesh out a plan or spec file. Ask non-obvious questions about technical implementation, UI & UX, tradeoffs, and concerns — then write the finalized spec back to the file. Use when you need to flesh out requirements, refine a spec, clarify a plan, or gather details before implementation. Keywords: interview, spec, plan, requirements, flesh out, questions, clarify spec, requirements gathering.
fix-issue
wcygan
Take a GitHub issue number, investigate it, implement a fix, write tests, and open a PR. End-to-end workflow from assigned issue to merged PR. Use when you want to fix a specific GitHub issue. Keywords: fix issue, github issue, resolve issue, close issue, implement issue, issue to PR, bug fix
agent-team
wcygan
Launch and coordinate Claude Code agent teams for complex tasks. Use when the user wants to parallelize work across multiple agents, needs a team for review, debugging, design, or feature development, or asks to "create a team" or "spawn agents." Keywords: agent team, team, spawn, teammates, parallel agents, coordinate, collaborate, multi-agent
migration-team
wcygan
Stakeholders satisfied with outcome
expand-tests
wcygan
Analyze existing test patterns and create comprehensive, idiomatic tests to expand coverage. Detects framework (Jest, Vitest, pytest, Go, Rust, JUnit), matches project conventions, and fills coverage gaps. Use when adding tests, improving coverage, expanding test suite, or writing tests for untested code. Keywords: test, tests, testing, coverage, unit test, integration test, expand tests, test coverage, write tests, add tests, test gaps
symfony:e2e-panther-playwright
MakFly
Drive Symfony delivery with deterministic tests and strong regression protection. Use for e2e panther playwright tasks.
symfony:functional-tests
MakFly
Drive Symfony delivery with deterministic tests and strong regression protection. Use for functional tests tasks.
symfony:form-types-validation
MakFly
Strengthen Symfony authorization and validation boundaries with explicit, test-backed enforcement. Use for form types validation tasks.
symfony:symfony-voters
MakFly
Strengthen Symfony authorization and validation boundaries with explicit, test-backed enforcement. Use for symfony voters tasks.
symfony:tdd-with-pest
MakFly
Drive Symfony delivery with deterministic tests and strong regression protection. Use for tdd with pest tasks.
symfony:test-doubles-mocking
MakFly
Drive Symfony delivery with deterministic tests and strong regression protection. Use for test doubles mocking tasks.
symfony:tdd-with-phpunit
MakFly
Drive Symfony delivery with deterministic tests and strong regression protection. Use for tdd with phpunit tasks.
elixir-code-review
existential-birds
Reviews Elixir code for idiomatic patterns, OTP basics, and documentation. Use when reviewing .ex/.exs files, checking pattern matching, GenServer usage, or module documentation.
elixir-writing-docs
existential-birds
Guides writing Elixir documentation with @moduledoc, @doc, @typedoc, doctests, cross-references, and metadata. Use when adding or improving documentation in .ex files.
exunit-code-review
existential-birds
Reviews ExUnit test code for proper patterns, boundary mocking with Mox, and test adapter usage. Use when reviewing _test.exs files or test helper configurations.