Acceptance Tester logo

Acceptance Tester

Community
Firstp1ck
acceptance-tester

Agents should invoke this skill as the final gate before release, handoff, or claiming completion for substantial changes. Runs acceptance/readiness checks, determines pass/fail, and gives a go/no-go recommendation.

Overview

PublisherFirstp1ck
Repositorypi-coding-agent-forge
Skill nameacceptance-tester
Stars
93
Forks
22
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Firstp1ck on GitHub. Read the source before you install it.

Installation

Install the Acceptance Tester AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Firstp1ck/pi-coding-agent-forge/tree/main/pi-skill-acceptance-tester/skills/acceptance-tester
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Firstp1ck/pi-coding-agent-forge.git /tmp/pi-coding-agent-forge
mkdir -p .claude/skills
cp -r /tmp/pi-coding-agent-forge/pi-skill-acceptance-tester/skills/acceptance-tester .claude/skills/acceptance-tester
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Acceptance Tester in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Acceptance Tester on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Acceptance Tester is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Acceptance Tester

Final quality gate — determines whether a project is ready to proceed.

Acceptance Criteria Source

The definition of done comes from the combined plan (section 8), which typically includes:

  • All modules implemented
  • All tests passing
  • Linting clean
  • Application starts and core flows work
  • Documentation updated
  • Security constraints verified

Acceptance Checklist

Run through this checklist systematically:

1. Build Verification

  • Project builds without errors
  • No compiler/linter warnings (or all are documented exceptions)
  • All dependencies resolve correctly

2. Test Suite

  • Full test suite passes (cargo test / npm test / pytest)
  • Coverage meets target from combined plan (default: 80%)
  • No skipped or ignored tests without documented reason

3. Core Flow Verification

For each core user flow defined in the spec:

  • Happy path works end-to-end
  • Primary error paths handled gracefully
  • Data persists correctly across operations

4. Spec Completeness

  • All P0 spec requirements verified (from spec-vs-impl checker)
  • No Blocker or Critical bugs outstanding
  • All Major bugs either fixed or explicitly deferred with user approval

5. Security Constraints

For each constraint from Zero's review:

  • Constraint is implemented
  • Constraint is tested
  • No obvious bypasses found during functional testing

6. Integration Points

  • Cross-module integrations work correctly
  • Error propagation across module boundaries is handled
  • Data format consistency across interfaces

Verdict Determination

PASS — Ready for Next Phase

All of these must be true:

  • Build succeeds
  • All tests pass
  • Coverage target met
  • Zero Blocker bugs
  • Zero Critical bugs
  • All P0 spec requirements verified
  • All security constraints verified

CONDITIONAL PASS

  • Minor or some Major bugs remain but none are blockers
  • User has approved deferring specific issues to v2
  • Core flows work, edge cases may have issues

FAIL — Return to Forge

Any of these triggers a fail:

  • Build fails
  • Tests fail
  • Blocker bugs found
  • Critical bugs found
  • P0 spec requirement missing or broken
  • Security constraint not met

Output Format

markdown
# Acceptance Test Report — <Project Name>

**Date:** YYYY-MM-DD
**Verdict:** PASS / CONDITIONAL PASS / FAIL
**QA Engineer:** Watchdog

## Checklist Results

| Category | Status | Details |
|---|---|---|
| Build | PASS/FAIL | [details] |
| Test Suite | PASS/FAIL | X/Y tests passing, Z% coverage |
| Core Flows | PASS/FAIL | X/Y flows verified |
| Spec Completeness | PASS/FAIL | X% requirements verified |
| Security | PASS/FAIL | X/Y constraints verified |
| Integration | PASS/FAIL | [details] |

## Outstanding Issues

| Bug | Severity | Status | Decision |
|---|---|---|---|
| BUG-003 | Minor | OPEN | Deferred to v2 |

## Recommendation

[PASS]: Project is ready for documentation (Ink) and release.
[CONDITIONAL PASS]: Project can proceed with noted caveats.
[FAIL]: Return to Forge. Fix items: [list].

Handoff

  • On PASS: Control returns to Clawpick, who invokes Ink for documentation.
  • On CONDITIONAL PASS: Clawpick presents conditions to user for approval. If approved, proceeds to Ink.
  • On FAIL: Clawpick routes bug reports to Forge. After fixes, Watchdog re-tests failed items only (not full re-test unless regression is suspected).

Watchdog skill — Acceptance testing and release readiness assessment

Frequently asked questions

What does the Acceptance Tester AI skill do?

Agents should invoke this skill as the final gate before release, handoff, or claiming completion for substantial changes. Runs acceptance/readiness checks, determines pass/fail, and gives a go/no-go recommendation.

Why use Acceptance Tester on TypingMind?

Because you install it once and use it with any model. Acceptance Tester is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Acceptance Tester in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Firstp1ck/pi-coding-agent-forge/tree/main/pi-skill-acceptance-tester/skills/acceptance-tester. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Acceptance Tester?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Acceptance Tester?

As many as you like. As long as a model supports skills, you can use Acceptance Tester with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Acceptance Tester AI skill free?

Yes. It is published on GitHub by Firstp1ck under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇