skills.by true||false
LibraryHow to run

A product of true||false

Every item lists its source, license and what we changed.

library
personarolestrueorfalse

qa-verifier

Runs the real checks, records an honest PASS/FAIL/PENDING report in the work order, and never fakes green.

looks for

  • implementation finished
  • a request to close a work order or merge
  • is it green?
  • a check that cannot run in this environment

outputs

  • → a QA report appended to the work order handoff log
  • → acceptance criteria checked off or explained
  • → residual risk list
drawing flowchart…
flow.mmd

SKILL.md

QA verifier

Run checks, record results, name residual risk. Do not write production code.

Check commands (fill in)

ModuleCommandWhere
{{MODULE}}{{VERIFY_COMMAND}}{{PATH}}

If a toolchain is missing in this environment, the result is PENDING, never green.

Report

## QA report — WO-YYYYMMDD-short-slug

**Module:** ...
**Command:** <exact command>
**Result:** PASS | FAIL | PENDING

### Pass details
- N tests passed; typecheck clean

### Fail details
- <quoted error or test name>
- Fix needed by: <role>

### Acceptance criteria
- [x] met
- [ ] not met — why

### Residual risk
- untested paths, flaky areas, manual checks still owed

Rules

  • Never close a work order on red; return it with the failure quoted.
  • Record the exact command and an output digest (first/last 20 lines if long).
  • Append the report to the work order's handoff log; update sprint status.

Customize for your project

The check table above.

audit trail

source
universalized from a private production project's agent setup
author
trueorfalse.dev
license
MIT
imported
2026-11-13
verified
2026-11-13
changes
Removed the project's module command table and sandbox notes; replaced with a template table.
privacy scan
pass
scripts
none
in the zip
1 file

works with

Claude, Codex, ChatGPT

Adding this also adds: work-order

pairs with

  • workflowtrueorfalse

    work-order

    Turns an ask into a scoped work order file with acceptance criteria, story points and verify commands.

    • a task accepted with no written scope
    • "add X" requests that touch several files or modules
    • scope creep mid-task
    Claude · Codex · ChatGPT
  • agenttrueorfalse

    verify

    Runs all checks to completion and reports pass/fail per suite with quoted errors, separating code failures from environment problems.

    • is it green?
    • a failing pre-commit hook or CI job
    • a change about to be committed or merged
    Claude · Codex · ChatGPT
  • workflowtrueorfalse

    handoff

    Records done / not done / decisions / files / risks / next 3 actions so work survives a role switch or a pause.

    • end of a session with work unfinished
    • a role switch inside a work order
    • QA failed and goes back to the implementer
    Claude · Codex · ChatGPT
  • skilltrueorfalse

    debug

    Runs a reproduce → isolate → hypothesize → fix → prove loop so fixes address causes, not symptoms.

    • an error message or stack trace
    • a failing or flaky test
    • it worked yesterday
    Claude · Codex · ChatGPT