aio-tdd
Skill0 starsChanged 32 days agoMITView on GitHub
Implement changed backend behavior through observed failing tests, minimal fixes and refactoring.
In this repository54 other files it gives its agents.
- agent-workflowsSkill
- aio-agentsSkill
- aio-algorithmsSkill
- aio-apiSkill
- aio-architectureSkill
- aio-autoplanSkill
- aio-benchmarkSkill
- aio-brainstormSkill
- aio-canarySkill
- aio-checkpointSkill
- aio-ciSkill
- aio-commitSkill
- aio-compoundSkill
- aio-dataSkill
- aio-debugSkill
- aio-devex-reviewSkill
- aio-doc-reviewSkill
- aio-explainSkill
- aio-feedbackSkill
- aio-handoffSkill
- aio-ideateSkill
- aio-observeSkill
- aio-optimizeSkill
- aio-pipelinesSkill
- aio-plan-reviewSkill
- aio-planSkill
- aio-proofSkill
- aio-prototypeSkill
- aio-qa-onlySkill
- aio-qaSkill
- aio-releaseSkill
- aio-resumeSkill
- aio-reviewSkill
- aio-securitySkill
- aio-shipSkill
- aio-simplifySkill
- aio-specSkill
- aio-test-auditSkill
- aio-testSkill
- aio-verifySkill
- aio-workSkill
- aio-worktreeSkill
- all-in-oneSkill
- apple-appstore-reviewerSkill
- backend-algorithmsSkill
- backend-debugSkill
- backend-pipelinesSkill
- backend-planSkill
- backend-reviewSkill
- backend-verifySkill
- complete-destructionSkill
- launch-readinessSkill
- play-policy-insightsSkill
- reverse-engineer-anythingSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Write the boundary test first, run it and inspect the failure.
- Distinctive: line 15
When writing persistence fixtures, check setup/teardown independently before the behavioral suite and read the resource-lifecycle guidance …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AIO Tdd
Implement changed backend behavior through observed failing tests, minimal fixes and refactoring.
Protocol
- Choose the smallest observable behavior from the accepted unit and verification playbook. State the invariant before selecting a test.
Write the boundary test first, run it and inspect the failure. Confirm the failure is the absent/wrong behavior, not broken setup. For a defect capture the actual reproducer; for an algorithm use an independent small-input oracle.
When writing persistence fixtures, check setup/teardown independently before the behavioral suite and read the resource-lifecycle guidance in aio-test. A database transaction context is not necessarily a connection-closing context.
Implement the minimum correct behavior and rerun the test. Include duplicate delivery, races, crash/restart, invalid input and access boundaries that the changed contract exposes; avoid tests that merely repeat implementation details.
For serialized tool/provider output, test the contract's actual JSON-serializable domain, including nested shapes and mixed key types when permitted. Keep canonical identity encoding separate from payload serialization: sorting mixed integer/string keys in a Python dict can reject a valid
json.dumpsinput. Compare with an independent JSON roundtrip, then verify durable replay and copy isolation.- Refactor with relevant tests green, then exercise integration boundaries changed by the refactor. Record the observed red and green evidence and changed files for aio-review.
- Reversible changes with no behavioral effect, such as formatting or documentation, may use appropriate nonbehavioral validation. Behavior-changing configuration still needs an observed failing boundary check. Isolated exploratory spikes are nonproduction experiments; hardening them requires the relevant behavioral proof. Record the concrete exception. Never delete user code merely to enforce a ritual.
Return and handoff
A tested behavior change with red/green observations, refactor evidence and explicit exceptions. Unit completion still requires review and accepted checks.
In a pipeline, use the stage contract and return to the integrating controller. Run only this specialist's owned scope; preserve the user's accepted decisions and existing authorization.
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.

