Skip to content
Agentmart
Submit a tool

papi-sdlc-task-acceptance-test

Plan and perform user-acceptance testing for user stories - exercise each story end-to-end through the real user interface in the appropriate role, with…

Skill by stainsby

IndexedMIT★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/stainsby-papi-sdlc-task-acceptance-test

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Plan and perform user-acceptance testing for user stories - exercise each story end-to-end through the real user interface in the appropriate role, with evidence. [PAPI SDLC]

Use cases: testing, productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/papi-sdlc-task-acceptance-test

What's inside

Skill name
papi-sdlc-task-acceptance-test
Description
Plan and perform user-acceptance testing for user stories - exercise each story end-to-end through the real user interface in the appropriate role, with evidence. [PAPI SDLC]
License
MIT
Instructions
110 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • acceptance-test-task-template.md · assets/

SKILL.md (first lines)

# SDLC Task - Acceptance Test

## Purpose

An acceptance test exercises each user story through the **real
user-facing interface** (UI, CLI, API, document, etc.) in the named
role, and records evidence that the story can in fact be performed
end-to-end.

**This needs the PAPI long task skill.**

## Role discipline

For each user story, the tester MUST assume the matching role(s)
and attempt to perform the story **only through the interfaces and
capabilities that would be available to that role in the real
world**.

This means:

- MUST use the production-equivalent interface (the actual UI, CLI,
  API, document, etc.) rather than internal tools, debug shims, or
  back-channel commands.
- MUST NOT consult implementation code, internal documents or other
  artefacts that the role would not normally have occasion to see.
- MUST reason in good faith whether the role would have the
  knowledge, context and access needed to discover and perform the
  steps unaided.
- Human assistance is allowable when the agent cannot physically
  reach the interface (e.g. a human clicks while the agent watches
  via screenshots); the role-discipline rules still apply.

If the role discipline is breached during a test, the test does NOT
count as passing and the breach MUST be recorded.

## Evidence

Each story attempt MUST produce evidence sufficient for an
independent reader to judge the result. Acceptable evidence
includes:

- Screenshots or screen recordings of the relevant UI flow
- Terminal transcripts for CLI flows
- Request/response captures for API flows
- Demo recordings
- Witness sign-off from a human performing or observing the flow

The classification of each story is:

- **Pass** — story performed end-to-end in role with evidence.
- **Partial** — story partially performed; specific steps blocked
  or unsatisfactory; evidence shows where.
- **Fail** — story cannot be performed in role.
- **Blocked** — cannot test (e.g., environment unavailable);
  explain.

## Relation to audits

- **Charter / fulfilment / compliance audits** check that documents
  and code line up. They do not run the system.
- **Acceptance test** runs the system. It is downstream of all
  three audits.
- A passing audit set with failing acceptance tests is meaningful:
  it suggests the alignment is correct on paper but the execution
  is broken somewhere outside the audited mappings (e.g.,
  integration, environment, UX).
- A passing acceptance test with failing audits is suspicious: it
  may indicate the audits found drift but the drift didn't (yet)
  break the user experience — the drift still needs resolving.

## Dependencies

Reading these skills is REQUIRED to understand and execute this
skill:

- PAPI skill `papi-tasks-understand`
- PAPI skill `papi-templates-understand`
- PAPI skill `papi-sdlc-user-stories`

Read these as needed:

- PAPI skill `papi-sdlc-task-fulfilment-audit` (typically run before)
- PAPI skill `papi-sdlc-task-compliance-audit` (typically run before)

## Actions

- Check if there is a custom acceptance-test template for the project;
  if not, use the one in `assets`.
- Copy the template verbatim and edit it section by section.
- For each story, identify the role(s) and the real interface(s)
  available to that role.
- Perform the story in role; capture evidence.
- Record Pass / Partial / Fail / Blocked with evidence and notes.

## Notes

- An acceptance test is NOT a substitute for automated unit,
  integration or end-to-end tests in the dev pipeline. It is a
  human-meaningful demonstration that the user-visible promise
  actually holds.
- If during testing you find yourself reading code or specs to
  decide whether something should work, stop: you are no longer
  doing acceptance testing. Either complete the test in role with
  what is visible, or switch to a fulfilment or compliance audit.

## Skill artefacts

- **Default acceptance-test template**: `assets/acceptance-test-task-template.md`

From stainsby/papi, MIT.

More from stainsby/papi

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
May 31, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from stainsby

Cite this page

papi-sdlc-task-acceptance-test skill. Agent Mart. https://agentmart.dev/skills/stainsby-papi-sdlc-task-acceptance-test (last updated 2026-10-24)