AGENT SKILL

test-runner-discovery

Reads the manifests and lockfiles to decide whether a project's test runner has a parallel mode with its prerequisite installed, and emits a JSON record that paqad-ai checks record-runner validates. Use when checks run reported that the parallel mode is unknown.

License 许可
MIT
所属仓库
Eliyce/paqad-ai
最近更新
2026-11-13
Stars
★ 8
Forks
0

01 前言 Front Matter

name
test-runner-discovery
metadata
{ "cacheable": "false", "model_tier": "fast", "paqad-meta": "skill.meta.yaml", "output_format": "json" }
description
Reads the manifests and lockfiles to decide whether a project's test runner has a parallel mode with its prerequisite installed, and emits a JSON record that paqad-ai checks record-runner validates. Use when checks run reported that the parallel mode is unknown.

02 资源文件 3

03 SKILL.md 正文

What It Does

Decides how the project's own test runner parallelizes when paqad's script detection could not (checks plan printed test: sequential (unknown)). It reads the project's manifests and lockfiles, identifies the runner the project's test script invokes, and decides whether a parallel mode exists and its prerequisite is installed: never assuming, never installing anything. It emits a small JSON record; the paqad-ai checks record-runner verb validates and stores it.

Use This When

  • A feature-development checks run reported test ran sequentially: parallel mode unknown, and you want the next run to be fast. Run this once; the recorded decision makes every later run fast.

Do not run this when checks plan already shows parallel, native, or a concrete sequential (<reason>): the script has already decided.

Inputs

  • project_root: the project to inspect.
  • test_command: the project's commands.test, the base the parallel command builds on.
  • Read references/allowed-flags.md for the exact tokens a test_parallel may add.

Procedure

  1. Read the ecosystem manifest and lockfile: composer.json/composer.lock, package.json and its lockfile, pyproject.toml/requirements*.txt/poetry.lock/uv.lock, Gemfile.lock, build.gradle(.kts), go.mod, Cargo.toml, pubspec.yaml.
  2. Identify the runner the project's own test script invokes (mocha, tap, ava, …).
  3. Decide whether a parallel mode exists AND its prerequisite is present in the lockfile. If the prerequisite is missing, the mode is unavailable: never propose installing it.
  4. When available, build test_parallel from test_command by adding only tokens listed in references/allowed-flags.md, with <processes> exactly once. Never add any other token.
  5. Write <scratch>/test-runner.json (see Output Contract) and hand it to the pipeline: paqad-ai checks record-runner <scratch>/test-runner.json. That verb runs the deterministic guard and rejects anything outside the allowlist: do not re-implement that check here.

Output Contract

A JSON object with exactly these keys:

{
  "schema_version": 1,
  "runner_id": "mocha",
  "parallel": "available",
  "reason": null,
  "test_parallel": "pnpm test -- --parallel --jobs=<processes>",
  "single_test_selector": "file",
  "evidence": ["package.json", "pnpm-lock.yaml"]
}
  • parallel is one of available, unavailable, native.
  • test_parallel is required when available, and must start with the project's own runner invocation, then add only allowlisted tokens with <processes> exactly once.
  • reason is a short sentence when unavailable/unknown, else null.
  • evidence is a non-empty list of files you read that exist under the project.

Escalate / Stop Conditions

  • Emit parallel: "unavailable" with a plain reason when no parallel mode exists or its prerequisite is missing. Never propose installing a package.

Resources

  • references/allowed-flags.md: the exact argv tokens a test_parallel may add.
  • agents/openai.yaml: the agent interface metadata.

04 同仓库更多 Skills

Eliyce
Eliyce/paqad-ai

sample-skill

Sample bundled skill fixture

★ 8
Eliyce
Eliyce/paqad-ai

processing-invoices

Turns a supplier invoice into one ledger line. Use when a supplier invoice arrives and needs booking.

★ 8
Eliyce
Eliyce/paqad-ai

processing-invoices

Turns a supplier invoice into one ledger line. Use when a supplier invoice arrives and needs booking.

★ 8
Eliyce
Eliyce/paqad-ai

understand-idea

Chat and Claude Code: Step 1 of the discover journey: clarifies the goal, who benefits, success and constraints into the idea block. Use when the journey directs it to step 1, not directly.

★ 8
Eliyce
Eliyce/paqad-ai

size-work

Chat and Claude Code: Suggest a size for a ticket from comparable finished work, as a labelled suggestion the team still owns. Use it when someone asks "how big is this?", "roughly how much work is ABC-12?", or wants a backlog item sized. It finds the team's sizing scale at first use, picks two to five of the closest finished tickets with links, and gives a size or range with the drivers behind it and a confidence of low, medium or high, lowered and explained when the area's documents are template text. Every result is labelled a suggested size, never a date or a commitment. It writes nothing into the size field unless the user says "set it", and it refuses to overwrite an existing size unless the user asks to replace it. Produces the sizing block of the record.

★ 8
Eliyce
Eliyce/paqad-ai

refine-ticket

Chat and Claude Code: Improve one or more existing tracker tickets without losing the author's intent. Use it when someone wants a ticket read, diagnosed and tidied up ("this ticket is vague", "fix up ABC-12", "split this, it's too big"). It reads each ticket in full and snapshots it with its last-updated time, says what is wrong with evidence, and proposes a field-by-field before and after change set limited to summary, description, labels, parent, links and new child tickets on a split. It writes nothing until an explicit "apply it" bound to that exact change set, re-checks the ticket for conflicting edits just before writing, never replaces rich descriptions with plain text, never deletes or closes a ticket, and reads each ticket back after applying. Produces the existing and changes blocks of the record.

★ 8