Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ouonet-tdd
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/tdd
What's inside
- Skill name
tdd- Description
- Use when implementing or fixing production code with tests.
- License
- MIT
- Instructions
- 46 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# TDD If `topology=multi-module` (triage announcement or coordinator spec/plan declaration), read `../references/multi-module.md`. Run implementation and local acceptance inside the task's registered repository/module. Update that module's spec and plan; update the coordinator only for shared-contract reality or workspace state. ## Acceptance mode Read the current plan task's `acceptance:` (or equivalent). **Automated acceptance** (test, command, or script that must fail before the change and pass after): - **No production code without a failing check first.** Wrote code before the failing check? Delete it. Rewrite from the check. - RED (fail for the *right reason*) → GREEN (minimum to pass) → refactor → **sync docs** → commit → flip the plan checkbox. **Manual acceptance** (explicit steps + expected result in the plan — config, docs, infra, prompts, content, or other non-testable deliverables): - Do **not** invent an automated test solely to satisfy RED-GREEN. - Perform the manual check; keep the change minimal; run any declared mechanical checks; **sync docs**; commit when appropriate; flip the plan checkbox. **No acceptance at all** (prototypes, generated code, throwaway scripts only): ask the user before writing production code. ## After green / manual pass **edit `docs/staging/plans/YYYY-MM-DD-<topic>.md` and change this task's `- [ ]` to `- [x]`. Do not start the next task without this edit.** **Sync docs** means: - If staging spec exists (`docs/staging/specs/*.md`): update it to match code reality. - If no staging spec (small task): update living docs (README, tech-spec, comments) directly. When local module tasks are complete and green, run the coordinator's cross-module acceptance against the current workspace contents before handing off to `ship`. For a linked multi-repository change, defer commits until integration passes, then follow the commit protocol in `../references/multi-module.md`. This is the exception to the per-cycle commit order above. If any commit fails, stop at `partial-commit`; never rewrite or discard completed commits automatically. ## Refactor Passing tests are not a quality bar. `<gate>` Before committing: (1) run lint/format/typecheck — green if declared; (2) evaluate against `convention`; (3) assess design — coupling, cohesion, abstraction, idiomatic for the stack. State what you ran, assessed, and changed — or why not. See `../references/quality.md`. `</gate>` ## Don't - Test passes without the impl (tests nothing). - Mock the unit under test (tests the mock). - Assert many behaviors in one test (split). - Skip "watch it fail" when acceptance is automated (you don't know what it tests). - Edit the test to match buggy code (tests the bug). - Add abstractions not required by the current acceptance (GREEN phase — not refactor). - Edit files outside the failing check's scope. - Create ad-hoc summary, notes, or analysis files not defined in the plan or required by a loaded skill.
From ouonet/praxis, MIT.
More from ouonet/praxis
- 0.594score
onboard
ouonet
Use when taking over an existing codebase that has no living document.
SkillBFreshness: B★ 12Claude Code +9 - 0.593score
ship
ouonet
Use when all plan tasks are done and green to review, archive planning artifacts, and ask how to finish.
SkillBFreshness: B★ 12Claude Code +9 - 0.593score
subagents
ouonet
Use when a plan has parallel tasks and the harness supports dispatching subagents.
SkillBFreshness: B★ 12Claude Code +9 - 0.591score
archive
ouonet
Use at ship time to merge the spec into the living documentation, delete the staging spec and plan, and ask how to finish.
SkillBFreshness: B★ 12Claude Code +9 - 0.588score
plan
ouonet
Use after design approval for milestone plans with executable acceptance.
SkillBFreshness: B★ 12Claude Code +9 - 0.588score
design
ouonet
Use for standard or complex new work before coding or planning.
SkillBFreshness: B★ 12Claude Code +9 - 0.588score
using-praxis
ouonet
Use at session start to learn how Praxis skills are invoked and why triage runs before every task.
SkillBFreshness: B★ 12Claude Code +9 - 0.585score
review
ouonet
Use before merge, after subagents, or for spec/plan review.
SkillBFreshness: B★ 12Claude Code +9 - 0.583score
worktree
ouonet
Use for non-trivial or parallel work that should happen in a separate git worktree.
SkillBFreshness: B★ 12Claude Code +9 - 0.583score
debug
ouonet
Use for bugs, unexpected behavior, regressions, or failing tests you did not write.
SkillBFreshness: B★ 12Claude Code +9 - 0.513score
release
ouonet
Use when the user asks to release, version, tag, or publish.
SkillCFreshness: C★ 12Claude Code +9
Signals
- Stars
- 12
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Aug 4, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ouonet/praxis
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ouonet
- 0.594score
onboard
ouonet
Use when taking over an existing codebase that has no living document.
SkillBFreshness: B★ 12Claude Code +9 - 0.593score
ship
ouonet
Use when all plan tasks are done and green to review, archive planning artifacts, and ask how to finish.
SkillBFreshness: B★ 12Claude Code +9 - 0.593score
subagents
ouonet
Use when a plan has parallel tasks and the harness supports dispatching subagents.
SkillBFreshness: B★ 12Claude Code +9 - 0.591score
archive
ouonet
Use at ship time to merge the spec into the living documentation, delete the staging spec and plan, and ask how to finish.
SkillBFreshness: B★ 12Claude Code +9 - 0.588score
plan
ouonet
Use after design approval for milestone plans with executable acceptance.
SkillBFreshness: B★ 12Claude Code +9 - 0.588score
design
ouonet
Use for standard or complex new work before coding or planning.
SkillBFreshness: B★ 12Claude Code +9
Cite this page
tdd skill. Agent Mart. https://agentmart.dev/skills/ouonet-tdd (last updated 2026-10-24)