Agent skill

Pm Tests

by wei63w in wei63w/pm-manager

List missing unit-test companions for core/changed sources. An agent skill from wei63w/pm-manager.

MITAuto-check passedTesting & QA

Install Pm Tests

skills CLI
$ npx skills add wei63w/pm-manager --skill pm-tests -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install wei63w/pm-manager pm-tests --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/wei63w/pm-manager.git skills-src && mkdir -p .claude/skills && cp -r skills-src/adapters/cursor/skills/pm-tests .claude/skills/pm-tests && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
pm-tests
GitHub stars
107
Token cost
~197 tokens
SKILL.md length
40 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

List missing unit-test companions for core/changed sources. An agent skill from wei63w/pm-manager.

  • Works in 5 steps: Require .pm/。缺则建议 /pm-init。 → 先读 .pm/architecture/map.json 与… → 运行 pm tests,列出核心源 / 本轮变更缺少的配套测试,以及建议落点。 → …
  • Tasks that involve Unit testing
  • SKILL.md covers User Input, Outline, Done When and Shared Workflow
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Pm Tests is an agent skill from wei63w/pm-manager. List missing unit-test companions for core/changed sources. Do not write tests into the business tree unless the user confirms.

Its SKILL.md is about 200 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering Unit testing and Test generation. The repository describes itself as: Know what to fix next — local .pm governance skill pack for AI coding agents (Spec Kit–inspired). The licence is MIT.

When your agent uses it

  • Tasks that involve Unit testing
  • Tasks that involve Test generation

Example prompts

  • “/pm-tests”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Require .pm/。缺则建议 /pm-init。
  2. 先读 .pm/architecture/map.json 与 .pm/state/test-gaps.md(若有)。禁止为找测试做无过滤全库递归。
  3. 运行 pm tests,列出核心源 / 本轮变更缺少的配套测试,以及建议落点。
  4. 只报告。若用户要求起草,先给出方案,停下等确认后再写测试文件。
  5. Closing:_closing.md 轻量档。指向 test-gaps.md。

What it can do on your machine

Read from SKILL.md and the folder at commit ecfaf1f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Pm Tests loads about 197 tokens when it runs. Until then it costs about 34 tokens; SKILL.md has 40 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~34
When it runs · the whole SKILL.md, loaded when a task matches
~197

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from wei63w/pm-manager at commit ecfaf1f, republished under its MIT licence (© wei63w). 40 words, ~197 tokens.

Download SKILL.mdSave it as .claude/skills/pm-tests/SKILL.md (or your agent's skills folder).
name
pm-tests
description
List missing unit-test companions for core/changed sources. Do not write tests into the business tree unless the user confirms.

User Input

text
$ARGUMENTS

Outline

/pm-tests 只管单测缺口。用户以中文交互时用中文回复。未确认不得把测试文件写入业务树。

  1. Require .pm/。缺则建议 /pm-init。
  2. 先读 .pm/architecture/map.json 与 .pm/state/test-gaps.md(若有)。禁止为找测试做无过滤全库递归。
  3. 运行 pm tests,列出核心源 / 本轮变更缺少的配套测试,以及建议落点。
  4. 只报告。若用户要求起草,先给出方案,停下等确认后再写测试文件。
  5. Closing:_closing.md 轻量档。指向 test-gaps.md。

Done When

  • 缺口已列出(或明确没有)
  • 未自动创建业务树测试文件

Shared Workflow

Map-first. Confirm-before-write for test files. Design baseline: docs/prd.md + 宪章。

© wei63w, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in adapters/cursor/skills/pm-tests of wei63w/pm-manager.

Open the folder on GitHubat commit ecfaf1f

Compare with similar skills

Pm Tests next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Pm Tests compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Pm Tests this skillwei63w/pm-manager107—~197Automated safety check: PassMIT
Atmos Testscloudposse/atmos1.4k—~1.9kAutomated safety check: PassApache-2.0
Memstack Development Test Writercwinvestments/memstack423—~3.7kAutomated safety check: PassProprietary
Frappe Testing UnitImpertio-Studio/Frappe_Claude_Skill_Package187—~3kAutomated safety check: PassMIT
TestingItamarZand88/CLI-Anything-WEB231—~3.3kAutomated safety check: PassMIT
Test Suite Curationpetrkindlmann/qa-skills165—~6.3kAutomated safety check: PassMIT

Similar skills

  • Atmos Tests

    cloudposse/atmos

    Author Atmos smoke tests, post-deployment stack checks, and integration tests using type: test, HTTP assertions, shell or script/interpreter checks, require gates, parallel dependencies, matrix…

    1.4k GitHub stars~1.9k tokensUpdated today
    Testing & QAAuto-check passed
  • Memstack Development Test Writer

    cwinvestments/memstack

    A skill your agent uses when the user says 'write tests', 'add tests', 'test coverage', 'unit tests', 'integration tests', 'component tests', 'mocking', 'edge cases', or needs to generate tests with…

    423 GitHub stars~3.7k tokensUpdated 12 days ago
    Testing & QAAuto-check passed
  • Frappe Testing Unit

    Impertio-Studio/Frappe_Claude_Skill_Package

    A skill your agent uses when writing unit tests, integration tests, creating test fixtures, or running tests with bench run-tests.

    187 GitHub stars~3k tokensUpdated 21 days ago
    Testing & QAAuto-check passed
  • Testing

    ItamarZand88/CLI-Anything-WEB

    Writes and documents the test suite for a generated cli-web- CLI (Phase 3): unit tests with mocked HTTP, live E2E tests, subprocess tests via resolvecli, and the TEST.md plan/results record.

    231 GitHub stars~3.3k tokensUpdated 7 days ago
    Testing & QAAuto-check passed
  • Test Suite Curation

    petrkindlmann/qa-skills

    Audit a whole regression suite and prune/restructure it with evidence: per-test coverage fingerprinting, AST near-duplicate clustering, CI-history mining for never-failing and flaky tests, prune…

    165 GitHub stars~6.3k tokensUpdated 4 mo ago
    Testing & QAAuto-check passed
  • Testing Safe Protocol

    archibate/dotfiles-opencode

    Safe testing practices to prevent real-world side-effects. An agent skill from archibate/dotfiles-opencode.

    108 GitHub stars~3.2k tokensUpdated 5 mo ago
    Testing & QAAuto-check: notes

More from wei63w/pm-manager

All 11 skills in this repo
  • Pm Export

    wei63w/pm-manager

    Export desensitized governance summary markdown for sharing or machine switch.

    107 GitHub stars~554 tokensUpdated 1 mo ago
    Auto-check passed
  • Pm Manager

    wei63w/pm-manager

    Project governance workbench (/pm-). An agent skill from wei63w/pm-manager.

    107 GitHub stars~730 tokensUpdated 1 mo ago
    Auto-check passed
  • Pm Next

    wei63w/pm-manager

    Claim the single next governance todo (marks inprogress). An agent skill from wei63w/pm-manager.

    107 GitHub stars~495 tokensUpdated 1 mo ago
    Auto-check passed
  • Pm Outline

    wei63w/pm-manager

    Generate detailed project outline and draft charter from user intent (empty/new projects).

    107 GitHub stars~570 tokensUpdated 1 mo ago
    Auto-check passed
  • Pm Charter

    wei63w/pm-manager

    Create, import, discover, approve, or skip project charter. An agent skill from wei63w/pm-manager.

    107 GitHub stars~428 tokensUpdated 1 mo ago
    Auto-check passed
  • Pm Check

    wei63w/pm-manager

    Diagnose .pm/ health (missing files, broken audit, stale map, unconfirmed PRD) and repair or increment without overwriting confirmed content.

    107 GitHub stars~412 tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Pm Tests

What does Pm Tests do?

List missing unit-test companions for core/changed sources. An agent skill from wei63w/pm-manager. Pm Tests is an agent skill from wei63w/pm-manager. List missing unit-test companions for core/changed sources.

When should I use Pm Tests?

Pm Tests fits situations like: tasks that involve Unit testing; tasks that involve Test generation.

How do I install Pm Tests in Claude Code?

Run `npx skills add wei63w/pm-manager --skill pm-tests -a claude-code`. Or copy the skill folder (adapters/cursor/skills/pm-tests in wei63w/pm-manager) into .claude/skills/pm-tests in your project. Claude Code loads it when a task matches its description.

How do I install Pm Tests in Codex?

Run `npx skills add wei63w/pm-manager --skill pm-tests -a codex`. Or copy the skill folder (adapters/cursor/skills/pm-tests in wei63w/pm-manager) into .agents/skills/pm-tests in your project. Codex loads it when a task matches its description.

Can I use Pm Tests in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add wei63w/pm-manager --skill pm-tests -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pm-tests, .gemini/skills/pm-tests, .github/skills/pm-tests and .opencode/skills/pm-tests in your project.

What does Pm Tests need to run?

SKILL.md names no scripts, command-line tools or credentials: Pm Tests is instructions for the agent only.

Does Pm Tests access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Pm Tests safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Pm Tests use?

Pm Tests is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Pm Tests use?

About 197 tokens (SKILL.md is roughly 788 characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Pm Tests?

Skills that share tags, products or a category with Pm Tests: Atmos Tests (cloudposse/atmos, 1.4k stars), Memstack Development Test Writer (cwinvestments/memstack, 423 stars), Frappe Testing Unit (Impertio-Studio/Frappe_Claude_Skill_Package, 187 stars) and Testing (ItamarZand88/CLI-Anything-WEB, 231 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Pm Tests?

wei63w (a GitHub user) maintains it in wei63w/pm-manager, which has 107 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on August 30, 2026.

Source: wei63w/pm-manager on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.