write-tests
Skill1 starsChanged 11 days agoMITView on GitHub
Phase 4, the first step of every plan task. Writes that task's tests from the PLAN.md test plan (pytest, Vitest, Playwright or Cypress) before its code, and shows them failing (red). Use at the start of each task, including a bug's regression test.
76 other projects use a version of this.
Adopted by
Most recently taken up by
- Doist/todoist-aitheir own version, first seen Nov 9, 2026
- CheckPickerUpper/skillstheir own version, first seen Nov 8, 2026
- Doist/todoist-clitheir own version, first seen Nov 8, 2026
- helmut-hoffer-von-ankershoffen/heinzeltheir own version, first seen Nov 8, 2026
- unlockers-ai/unlockers-skills-librarytheir own version, first seen Nov 8, 2026
- jocarrd/crux-agentstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use close-spec, design-with-images and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
dzhngSkillclose-spec
When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).
Also in 5 projects that use this
dzhngSkilldesign-with-images
Explore UI and visual design with image generation, then iterate the real implementation against the user-selected concept. Use when brainstorming visual directions, offering mockup variants, or implementing an approved generated design; do not stop at the mockups or the first code approximation.
Also in 5 projects that use this
transitive-bullshitSkillcompare-screenshots
Compare screenshots against the intended design, distinguishing approved references from historical baselines. Use for iterative implementation matching, before/after visual review, objective image telemetry, or checking a lone capture for flat, empty, or badly framed content.
Also in 5 projects that use this
LucasMatuszewskiSkillaudit-agents
Audit and maintain agent configuration files (.claude/agents, AGENTS.md, CLAUDE.md, agent-memory). Checks for duplicates, outdated info, naming conflicts, wrong technical facts, and files over 200 lines. Fixes all issues and commits.
Also in 5 projects that use this
wolverin0Skillaudit-decisions
Standardize remediation decisions, baseline-policy entries, and legal-review banners for accepted, deferred, or policy-blocked audit findings.
Also in 4 projects that use this
rhnfzlSkillexplore-unknowns
Walk the user through mapping the unknowns of a task before, during, and after they build it, and hand them a four-quadrant map (settled ground, open decisions, taste, and landmines) they keep. Reach for this eagerly whenever a request is ambiguous or underspecified, the codebase or domain is unfamiliar, the user will "know it when they see it", a reference implementation must be understood before porting, a build-queue or architecture-changing task is about to start, a mid-build deviation needs capturing, or a finished change needs buy-in or verified understanding before merge. Trigger even when the skill is not named: "do a blindspot pass", "find my unknown unknowns", "interview me about this change", "brainstorm the approach for a task I am about to build", "help me scope this", "what am I missing here", "plan this before I build", "I know nothing about X in this codebase". When a territory profile is present it reads memory and the graph first and feeds the map into the build pipeline; without one it degrades to a plain general map. Not for trivial or mechanical tasks with clear acceptance criteria, single-fact lookups, pure debugging of a known symptom, or pure code review, those have their own tools. Do not use it to run the build itself; the map is the deliverable and implementation remains a separate task, whether it has not started or is already underway.
Also in 5 projects that use this
- +5 more from dzhng
Other versions76 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 76
- remix-run/remix★ 33ksame name
- elie222/inbox-zero★ 13ksame name
- getsentry/sentry-javascript★ 8.8ksame name
- dzhng/jevgrep★ 3.2ksame name
- meta-pytorch/OpenEnv★ 2.8ksame name
- huggingface/OpenEnv★ 2.8ksame name
- JamieMason/syncpack★ 2.1ksame name
- dzhng/skills★ 1.5ksame name
- clice-io/clice★ 1.4ksame name
- ryokun6/ryos★ 1.3ksame name
66 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/00-ticket-workflow.mdcCursor rule
- .cursor/rules/10-general-standards.mdcCursor rule
- .cursor/rules/20-backend-standards.mdcCursor rule
- .cursor/rules/30-frontend-standards.mdcCursor rule
- .cursor/rules/40-database-standards.mdcCursor rule
- .cursor/rules/50-testing-standards.mdcCursor rule
- backend-implementSkill
- chatSkill
- codebase-exploreSkill
- db-migrationSkill
- frontend-implementSkill
- gitlab-mrSkill
- implementation-planSkill
- jira-createSkill
- mr-feedbackSkill
- mr-reviewSkill
- quick-fixSkill
- run-checksSkill
- self-reviewSkill
- ticket-intakeSkill
- ticket-qaSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 71 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 7
Write exactly the Test plan rows for the current task, before its code.
- Distinctive: line 11
Read PLAN.md: the current task (what its tests call) and its Test plan rows.
- Very specific: line 13
Look at one existing test of each type from the pattern source and copy its setup.
- Distinctive: line 25
Run only these tests:
- Distinctive: line 41
Write one test from REQUIREMENTS.md "Bug": follow the steps to reproduce, assert the Expected result.
- Distinctive: line 42
Put it where the pattern source keeps tests of that kind.
- Distinctive: line 43
Run only that test. It must FAIL, showing the Actual result.
“Common” is measured: kept by at least 6 in 10 of the 71 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Write tests first (phase 4, red step)
Write exactly the Test plan rows for the current task, before its code. Nothing unrelated.
A migration-only task skips this skill: check_migration.sh is its test.
Steps
- Read PLAN.md: the current task (what its tests call) and its Test plan rows. Read "Codebase notes" (test frameworks, E2E location).
- Look at one existing test of each type from the pattern source and copy its setup.
Find fixtures first:
rg -n "^def |^async def " backend/tests/conftest.py - Backend:
- Service tests →
backend/tests/unit/<feature>/ - Route tests →
backend/tests/integration/<feature>/ - Per endpoint at minimum: happy path, 422, 404, 401/403, 409 (if unique rule), pagination (if list).
- Service tests →
- Frontend component tests: put them where the pattern source keeps them. Cover: data rendered, loading, empty, error, validation message, successful submit.
- E2E: use ONLY the framework recorded for this screen in "Codebase notes". One spec per user-facing AC (happy path + the most important failure), written with the task that adds the page.
- Assert the row's exact expected result: status code, fields, message or visible text. Derive numbers from
the inputs in the test (
price * qty), not mental math. Never assert only "not None" or "truthy". - Run only these tests:
cd backend && pytest <test paths> -qcd frontend && npx vitest run <test paths>- E2E needs the LOCAL stack (
docker compose up -dwith the dev compose file only), thennpx playwright test <spec>ornpx cypress run --spec <spec>
- Each must FAIL (red) on its assertion, or because the route or screen doesn't exist yet (404, element not
found). Not on a typo, an import or a fixture error. A missing module or function → add a stub with the
planned signature (
raise NotImplementedError/throw new Error("not implemented")) and run again.check_guards.shfails if a stub is still there at the end. - A test that PASSES now tests nothing new: fix the test, or ask to fix the plan. Never keep it as it is.
- Log each
<test>: red: <the failing line>in PROGRESS.md and fill the Test plan "File" column. Then write the task's code (/db-migration, /backend-implement or /frontend-implement) until they pass. - Tests written red are locked. Change one later only if it contradicts REQUIREMENTS.md, and write why in PROGRESS.md and the MR.
Bug tickets: the regression test (plan task T1)
- Write one test from REQUIREMENTS.md "Bug": follow the steps to reproduce, assert the Expected result. Put it where the pattern source keeps tests of that kind.
- Run only that test. It must FAIL, showing the Actual result. Paste the failing output in PROGRESS.md.
- It passes? Then it doesn't reproduce the bug. STOP and tell the human what you tried.
Done when
- Every Test plan row of this task has a file and a logged red line
- The failing output is shown in this chat
- Test files ≤ 200 lines
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

