Agent skill

QA Planning

Generate QA Contract with numbered Gherkin scenarios (GN) and acceptance criteria (ACN)

MITAuto-check passedProduct & Project Management

Install QA Planning

skills CLI

$ npx skills add WellApp-ai/Well --skill qa-planning -a claude-code

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

GitHub CLI

$ gh skill install WellApp-ai/Well qa-planning --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/WellApp-ai/Well.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cursor-rules/skills/qa-planning .claude/skills/qa-planning && 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/

Paste into Claude Code

Install the "qa-planning" agent skill from https://github.com/WellApp-ai/Well/tree/main/cursor-rules/skills/qa-planning into .claude/skills/qa-planning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qa-planning", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/WellApp-ai/Well/tree/main/cursor-rules/skills/qa-planning

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add WellApp-ai/Well --skill qa-planning -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install WellApp-ai/Well qa-planning --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/WellApp-ai/Well.git skills-src && mkdir -p .agents/skills && cp -r skills-src/cursor-rules/skills/qa-planning .agents/skills/qa-planning && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "qa-planning" agent skill from https://github.com/WellApp-ai/Well/tree/main/cursor-rules/skills/qa-planning into .agents/skills/qa-planning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qa-planning", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add WellApp-ai/Well --skill qa-planning -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install WellApp-ai/Well qa-planning --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/WellApp-ai/Well.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/cursor-rules/skills/qa-planning .cursor/skills/qa-planning && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "qa-planning" agent skill from https://github.com/WellApp-ai/Well/tree/main/cursor-rules/skills/qa-planning into .cursor/skills/qa-planning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qa-planning", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/WellApp-ai/Well.git --path cursor-rules/skills/qa-planning

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add WellApp-ai/Well --skill qa-planning -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install WellApp-ai/Well qa-planning --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/WellApp-ai/Well.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/cursor-rules/skills/qa-planning .gemini/skills/qa-planning && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "qa-planning" agent skill from https://github.com/WellApp-ai/Well/tree/main/cursor-rules/skills/qa-planning into .gemini/skills/qa-planning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qa-planning", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install WellApp-ai/Well qa-planning

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add WellApp-ai/Well --skill qa-planning -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/WellApp-ai/Well.git skills-src && mkdir -p .github/skills && cp -r skills-src/cursor-rules/skills/qa-planning .github/skills/qa-planning && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "qa-planning" agent skill from https://github.com/WellApp-ai/Well/tree/main/cursor-rules/skills/qa-planning into .github/skills/qa-planning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qa-planning", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add WellApp-ai/Well --skill qa-planning -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install WellApp-ai/Well qa-planning --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/WellApp-ai/Well.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/cursor-rules/skills/qa-planning .opencode/skills/qa-planning && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "qa-planning" agent skill from https://github.com/WellApp-ai/Well/tree/main/cursor-rules/skills/qa-planning into .opencode/skills/qa-planning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "qa-planning", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: qa-planning
GitHub stars: 345
Token cost: ~3.9k tokens
SKILL.md length: 909 words
Files: 1
Skills in repo: 36
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Generate QA Contract with numbered Gherkin scenarios (GN) and acceptance criteria (ACN)

Works in 11 steps: Identify ALL Data Sources (CRITICAL) → Define Pre-conditions Matrix (Given) → Map When (Method + Path) → …
Tasks that involve User stories
SKILL.md covers When to Use, Output: QA Contract, Instructions and Output Format: QA Contract
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

QA Planning is an agent skill from WellApp-ai/Well. Generate QA Contract with numbered Gherkin scenarios (GN) and acceptance criteria (ACN)

Its SKILL.md is about 3.9k 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 Product & Project Management, covering User stories. The repository describes itself as: No more Sundays on Finance. We build the infrastructure that retrieves, processes, and routes your financial and business data to your FinOps stack, so founders can ship, not… The licence is MIT.

When your agent uses it

Tasks that involve User stories

Example prompts

“/qa-planning”

Workflow steps

11 steps, taken from the step headings in SKILL.md.

Identify ALL Data Sources (CRITICAL)
Define Pre-conditions Matrix (Given)
Map When (Method + Path)
Define Then (Response Contract)
Write Gherkin Scenarios (G#N)
Build-time Static Scenarios (G#N)
Middleware/Routing Scenarios (G#N)
Frontend QA (Acceptance Criteria - AC#N)
Integration Points
Coverage Summary
Artifact Validation (Poka-Yoke)

What it can do on your machine

Read from SKILL.md and the folder at commit c740217. 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 (its code samples are markdown, gherkin and typescript).
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

QA Planning loads about 3.9k tokens when it runs. Until then it costs about 25 tokens; SKILL.md has 909 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~25
When it runs · the whole SKILL.md, loaded when a task matches: ~3.9k

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 WellApp-ai/Well at commit c740217, republished under its MIT licence (© WellApp-ai). 909 words, ~3,949 tokens.

Download SKILL.mdSave it as .claude/skills/qa-planning/SKILL.md (or your agent's skills folder).

name: qa-planning
description: Generate QA Contract with numbered Gherkin scenarios (G#N) and acceptance criteria (AC#N)

QA Planning Skill

Generate the QA Contract - exhaustive Gherkin BDD scenarios (G#N) for all data sources and acceptance criteria (AC#N) for frontend. This contract is consumed by Plan Mode and verified by qa-commit skill.

When to Use

During Ask mode Phase 2 (CONVERGE) for any feature work
Before implementation to define testable acceptance criteria
When documenting expected behavior for QA team

Output: QA Contract

The QA Contract is the primary artifact, consisting of:

G#1, G#2, ... - Numbered Gherkin scenarios (backend/data)
AC#1, AC#2, ... - Numbered acceptance criteria (frontend)

These IDs are referenced in Plan Mode's Commit Plan (Satisfies field) and verified by qa-commit skill.

Instructions

Phase 0: Identify ALL Data Sources (CRITICAL)

STOP. Before writing any Gherkin, exhaustively map ALL data sources for the feature.

Categorize each data source:

Category	Description	Gherkin Type
Runtime API	Fetched at request time from server	API scenarios (G#N)
Build-time Static	Generated during build, served as static files	Build script scenarios (G#N)
Database	Direct DB queries (Hasura, Postgres)	Query scenarios (G#N)
External API	Third-party services	Integration scenarios (G#N)
Middleware	Request routing, auth, transforms	Routing scenarios (G#N)

Data Source Inventory Template:

markdown

## Data Source Inventory

### Runtime APIs
| Endpoint | Method | Auth | Resource | Status |
|----------|--------|------|----------|--------|
| `/v1/resource` | GET | Yes | Resource | Existing |
| `/public/resource` | GET | No | Resource | New |

### Build-time Static
| Output Path | Source | Generator | Content |
|-------------|--------|-----------|---------|
| `/components.json` | Codebase | Build script | Component metadata |
| `/charts/[slug].json` | Codebase | Build script | Chart config + examples |

### Database Queries
| Query | Source | Auth | Purpose |
|-------|--------|------|---------|
| `connectors` | Hasura | Yes | List connectors |

### Middleware
| Route | Behavior | Auth |
|-------|----------|------|
| `developers.*` | Rewrite to public routes | Skip |

### External APIs
| Service | Endpoint | Purpose |
|---------|----------|---------|
| (none for this feature) | | |

Validation: Count total data sources. If < 3 for a non-trivial feature, you likely missed something. Re-examine the feature scope.

Phase 2: Define Pre-conditions Matrix (Given)

For each service, treat it as a black box. Based on the contract interface or data model, list all pre-condition parameters:

markdown

### [Method] [Path] Pre-conditions

| Parameter | Type | Source | Possible Values |
|-----------|------|--------|-----------------|
| `Authorization` | header | request | valid_token, invalid_token, expired_token, missing |
| `id` | path | URL | existing_uuid, non_existing_uuid, malformed, deleted |
| `status` | query | URL | enum values from data model |
| `[field]` | body | JSON | valid, null, empty, wrong_type, too_long |

Sources:

header: Authorization, Content-Type, custom headers
path: URL parameters (:id, :slug)
query: Query string filters, pagination
body: Request payload fields

Phase 3: Map When (Method + Path)

Each scenario has exactly ONE action:

When [METHOD] [/path/to/resource]

Examples:

When GET /v1/connectors
When POST /v1/connectors
When GET /v1/connectors/{id}
When DELETE /v1/connectors/{id}

Phase 4: Define Then (Response Contract)

Specify expected response object. Response varies based on pre-conditions:

gherkin

Then status [code]
And response.[field] is [type]
And response.[field] equals [value]
And response.[field] in [array of valid values]
And response does NOT include [sensitive_field]

Response Schema Template:

typescript

// Success response
{
  data: {
    type: string,
    id: UUID,
    attributes: { ... }
  },
  meta?: { count: number }
}

// Error response
{
  error: {
    code: "NOT_FOUND" | "UNAUTHORIZED" | "VALIDATION_ERROR",
    message: string
  }
}

Phase 5: Write Gherkin Scenarios (G#N)

For each method+path, write scenarios covering all pre-condition combinations:

gherkin

Feature: [Resource] API

  @G#1
  Scenario: G#1.1 - [Method] [path] - happy path
    Given Authorization header is "Bearer valid_token"
    And [pre-condition 1]
    And [pre-condition 2]
    When [METHOD] [/path]
    Then status 200
    And response.data.id is UUID
    And response.data.attributes.[field] is [type]

  @G#2
  Scenario: G#1.2 - [Method] [path] - missing auth
    Given no Authorization header
    When [METHOD] [/path]
    Then status 401
    And response.error.code equals "UNAUTHORIZED"

  @G#3
  Scenario: G#1.3 - [Method] [path] - not found
    Given Authorization header is "Bearer valid_token"
    And id is "non_existing_uuid"
    When [METHOD] [/path/{id}]
    Then status 404
    And response.error.code equals "NOT_FOUND"

Numbering Convention:

G#N = Feature-level ID (G#1, G#2...)
G#N.M = Scenario within feature (G#1.1, G#1.2...)
Use @G#N tag for traceability

Coverage Matrix per Endpoint:

Method	Required Scenarios
GET (list)	Valid, filtered, paginated, empty, unauthorized
GET (detail)	Found, not found, deleted, unauthorized, malformed ID
POST	Valid, each validation error, conflict, unauthorized
PUT/PATCH	Valid, partial, not found, conflict, unauthorized
DELETE	Success, not found, unauthorized, cascade

Phase 6: Build-time Static Scenarios (G#N)

For build-time generated data, write scenarios verifying the build script:

Pre-conditions for Build Scripts:

Parameter	Type	Possible Values
Source file exists	boolean	true, false
Source file valid	boolean	valid structure, malformed
Metadata complete	boolean	all fields, partial, missing
Export type	enum	default, named, none

Template:

gherkin

Feature: [Resource] Build Extraction

  @G#N
  Scenario: G#N.1 - Extract [resource] with complete metadata
    Given [source file] exists at [path]
    And [source file] has valid [structure]
    And [metadata fields] are documented
    When build script runs
    Then [output.json] includes [resource] entry
    And entry has [required fields]

  @G#N
  Scenario: G#N.2 - Skip internal/private [resources]
    Given [source file] has underscore prefix
    When build script runs
    Then [output.json] does NOT include entry

  @G#N
  Scenario: G#N.3 - Handle missing optional fields
    Given [source file] exists
    And [optional field] is not documented
    When build script runs
    Then entry has [optional field] as null

Coverage Matrix for Build Scripts:

Source Type	Required Scenarios
Component	Extract props, extract examples, skip internal, handle missing docs
Chart	Extract config schema, extract data schema, extract examples
Docs	Parse MDX, extract frontmatter, build navigation
Search Index	Index all sources, handle empty content, validate structure

Phase 7: Middleware/Routing Scenarios (G#N)

For middleware and routing logic:

Pre-conditions:

Parameter	Type	Possible Values
Host header	string	subdomain variants, main domain, unknown
Path	string	valid routes, invalid routes
Auth state	enum	authenticated, unauthenticated

Template:

gherkin

Feature: Hostname Routing

  @G#N
  Scenario: G#N.1 - Route [subdomain] to [target]
    Given Host header is "[subdomain].domain.com"
    And path is "[path]"
    When request arrives at middleware
    Then rewrite to [target route group]
    And [skip/require] authentication

  @G#N
  Scenario: G#N.2 - Unknown subdomain redirect
    Given Host header is "unknown.domain.com"
    When request arrives at middleware
    Then redirect to [default domain]

Show full SKILL.md (411 more words)Show less

Phase 8: Frontend QA (Acceptance Criteria - AC#N)

For each UI component/screen, define numbered testable criteria using AC#N format:

ID	Screen	Criteria	Test Method	Priority
AC#1	[Component]	Renders without error	Storybook	P0
AC#2	[Component]	Displays loading state	Storybook	P0
AC#3	[Component]	Displays error state with retry	Storybook	P0
AC#4	[Component]	Displays empty state with CTA	Storybook	P1
AC#5	[Component]	Keyboard navigation works	Browser MCP	P1
AC#6	[Component]	Screen reader accessible	Manual	P1
AC#7	[Component]	Mobile responsive	Browser MCP	P2

Numbering Rules:

Use sequential IDs: AC#1, AC#2, AC#3...
IDs are feature-scoped (reset for each feature)
Include ID in first column for traceability

Data Source Mapping for AC: Each AC must indicate which data source it consumes:

ID	Screen	Criteria	Data Source	Priority
AC#1	ConnectorsList	Renders list	API: /public/connectors	P0
AC#2	ComponentsList	Renders list	Static: /components.json	P0

State Coverage:

State	Required Tests
Initial	Default render, correct layout
Loading	Skeleton/spinner visible, no interaction
Success	Data displayed correctly, actions enabled
Error	Error message visible, retry available
Empty	Empty message visible, CTA available

Phase 9: Integration Points

Identify cross-cutting concerns:

Concern	Test Approach
Auth token handling	Gherkin: expired token, refresh flow
Optimistic updates	Frontend: show immediate, rollback on error
Cache invalidation	Frontend: data refreshes after mutation
Error boundaries	Frontend: component failure doesn't crash app

Phase 10: Coverage Summary

markdown

## Coverage Summary

### Data Sources
| Category | Count | Items |
|----------|-------|-------|
| Runtime APIs | [N] | [list endpoints] |
| Build-time Static | [N] | [list outputs] |
| Middleware | [N] | [list routes] |
| Database | [N] | [list queries] |
| External APIs | [N] | [list services] |
| **Total** | [N] | |

### Gherkin Scenarios
| Category | Count | IDs |
|----------|-------|-----|
| API scenarios | [N] | G#1 - G#[N] |
| Build scenarios | [N] | G#[N] - G#[M] |
| Middleware scenarios | [N] | G#[M] - G#[P] |
| **Total** | [N] | |

### Frontend Acceptance
| Category | Count | IDs |
|----------|-------|-----|
| Acceptance criteria | [N] | AC#1 - AC#[N] |

### Validation Checklist
- [ ] Every data source has at least 1 G#N scenario
- [ ] Every AC#N maps to a data source
- [ ] All error cases covered (401, 404, 400, 500)
- [ ] Build scripts have extraction + skip + missing scenarios
- [ ] Middleware has all subdomain variants

Phase 11: Artifact Validation (Poka-Yoke)

Before Gate transition, validate artifacts silently. Only show output if validation fails.

Gate 1 Validation (DIVERGE -> CONVERGE)

Check:

All wireframes have status (OK/KO/DIG, or no comment = OK)
No orphan references (#{N} mentioned but not defined)
At least 1 wireframe validated (OK)

Gate 2 Validation (CONVERGE -> PLAN)

Check:

QA Contract has at least 1 G#N (Gherkin scenario)
QA Contract has at least 1 AC#N (acceptance criteria)
Each phase has at least 1 commit planned
No circular dependencies in phasing order
All G#N and AC#N are assigned to phases

Validation Output

If all pass: (silent, no output - proceed normally)

If validation fails:

R | [Feature] | VALIDATION ERROR
---
Cannot proceed to [NEXT_PHASE]:
- [Missing: wireframe #4 has no status]
- [Missing: QA Contract needs at least 1 G#N]

Fix: [Specific action to resolve]

Integration

This validation runs automatically before:

Gate 1 presentation (ask.mdc Phase 1 - DIVERGE)
Gate 2 presentation (ask.mdc Phase 2 - CONVERGE)

Output Format: QA Contract

markdown

## QA Contract: [Feature Name]

### Data Source Inventory

#### Runtime APIs
| Endpoint | Method | Auth | Resource | Status |
|----------|--------|------|----------|--------|
| `/v1/resource` | GET | Yes | Resource | Existing |
| `/public/resource` | GET | No | Resource | New |

#### Build-time Static
| Output Path | Source | Generator |
|-------------|--------|-----------|
| `/components.json` | Codebase | Build script |

#### Middleware
| Route Pattern | Behavior |
|---------------|----------|
| `developers.*` | Rewrite to public, skip auth |

---

### API Scenarios (G#1 - G#N)

#### G#1: [METHOD] [/path] ([Resource])

**Pre-conditions:**

| Parameter | Type | Possible Values |
|-----------|------|-----------------|
| `Authorization` | header | valid_token, invalid_token, missing |
| `id` | path | existing, non_existing, malformed |

**Scenarios:**

| ID | Given | When | Then |
|----|-------|------|------|
| G#1.1 | valid token | GET /path | 200, data array |
| G#1.2 | invalid token | GET /path | 401, UNAUTHORIZED |

---

### Build Scenarios (G#N - G#M)

#### G#N: [Resource] Extraction

**Pre-conditions:**

| Parameter | Type | Possible Values |
|-----------|------|-----------------|
| Source exists | boolean | true, false |
| Metadata complete | boolean | complete, partial |

**Scenarios:**

| ID | Given | When | Then |
|----|-------|------|------|
| G#N.1 | source exists, complete | Build runs | output.json includes entry |
| G#N.2 | internal file (underscore) | Build runs | output.json excludes entry |

---

### Middleware Scenarios (G#M - G#P)

#### G#M: Hostname Routing

| ID | Given (Host) | Given (Path) | Then |
|----|--------------|--------------|------|
| G#M.1 | developers.domain.com | /connectors | Rewrite to /(public), skip auth |
| G#M.2 | app.domain.com | /settings/* | Route to /(app), require auth |

---

### Response Schemas

```typescript
// Success
{ data: { type, id, attributes }, meta: { count } }

// Error
{ error: { code, message } }

// Static file
{ data: [{ slug, name, ... }], meta: { count } }

Frontend Acceptance Criteria

ID	Screen	Criteria	Data Source	Priority
AC#1	[Component]	Renders list	API: /public/x	P0
AC#2	[Component]	Renders from static	Static: /x.json	P0

Coverage Summary

Category	Count	IDs
Runtime APIs	[N]	G#1 - G#[N]
Build Scripts	[N]	G#[N] - G#[M]
Middleware	[N]	G#[M] - G#[P]
Acceptance Criteria	[N]	AC#1 - AC#[N]
Total Scenarios	[N]

Validation

Every data source has ≥1 G#N
Every AC#N maps to data source
Error cases covered (401, 404, 400)


## Consuming the QA Contract

This QA Contract is used by:
- **Plan Mode**: Maps G#N and AC#N to commits via "Satisfies" field
- **qa-commit skill**: Verifies implementation against assigned criteria
- **test-hardening skill**: Converts passed criteria to automated tests

## Invocation

Invoke manually with "use qa-planning skill" or follow Ask mode Phase 2 (CONVERGE) which references this skill.

## Related Skills

- `state-machine` - Defines states that need testing
- `bpmn-workflow` - Uses Gherkin scenarios for process documentation
- `qa-commit` - Verifies implementation against QA Contract
- `test-hardening` - Converts passed scenarios to automated tests

Files

Just SKILL.md in cursor-rules/skills/qa-planning of WellApp-ai/Well.

Open the folder on GitHubat commit c740217

Compare with similar skills

QA Planning 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.

QA Planning compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
QA Planning this skillWellApp-ai/Well	345	—	~3.9k	Automated safety check: Pass	MIT	2 days ago
User Story Writerdeanpeters/Product-Manager-Skills	7.2k	2 repos	~2.9k	Automated safety check: Pass	Custom licence	1 mo ago
Ralph Tui Create Beadssubsy/ralph-tui	2.5k	1 repos	~2.6k	Automated safety check: Pass	MIT	1 mo ago
Agile Product Owneralirezarezvani/claude-skills	28k	3 repos	~3.2k	Automated safety check: Pass	MIT	1 mo ago
Ralph Tui Create Beads Rustsubsy/ralph-tui	2.5k	1 repos	~2.8k	Automated safety check: Pass	MIT	1 mo ago
To Specbestofjs/bestofjs	3.1k	21 repos	~757	Automated safety check: Pass	MIT	5 days ago

Similar skills

User Story Writer
deanpeters/Product-Manager-Skills
Writes user stories in Mike Cohn's format with Gherkin acceptance criteria, turning user needs into development-ready work with testable conditions.
7.2k GitHub starsUsed in 2 repos~2.9k tokens
Product & Project ManagementAuto-check passed
Ralph Tui Create Beads
subsy/ralph-tui
Convert PRDs to beads for ralph-tui execution. An agent skill from subsy/ralph-tui.
2.5k GitHub starsUsed in 1 repo~2.6k tokens
Product & Project ManagementAuto-check passed
Agile Product Owner
alirezarezvani/claude-skills
Writes INVEST-checked user stories with acceptance criteria, splits epics, plans sprints from velocity and ranks the backlog with a weighted score.
28k GitHub starsUsed in 3 repos~3.2k tokens
Product & Project ManagementAuto-check passed
Ralph Tui Create Beads Rust
subsy/ralph-tui
Convert PRDs to beads for ralph-tui execution using beads-rust (br CLI).
2.5k GitHub starsUsed in 1 repo~2.8k tokens
Product & Project ManagementAuto-check passed
To Spec
bestofjs/bestofjs
Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.
3.1k GitHub starsUsed in 21 repos~757 tokens
Product & Project ManagementAuto-check passed
Ralph Tui Create JSON
subsy/ralph-tui
Convert PRDs to prd.json format for ralph-tui execution. An agent skill from subsy/ralph-tui.
2.5k GitHub starsUsed in 1 repo~2.6k tokens
Product & Project ManagementAuto-check passed

Questions about QA Planning

What does QA Planning do?

Generate QA Contract with numbered Gherkin scenarios (GN) and acceptance criteria (ACN). QA Planning is an agent skill from WellApp-ai/Well.

When should I use QA Planning?

QA Planning fits situations like: tasks that involve User stories.

How do I install QA Planning in Claude Code?

Run `npx skills add WellApp-ai/Well --skill qa-planning -a claude-code`. Or copy the skill folder (cursor-rules/skills/qa-planning in WellApp-ai/Well) into .claude/skills/qa-planning in your project. Claude Code loads it when a task matches its description.

How do I install QA Planning in Codex?

Run `npx skills add WellApp-ai/Well --skill qa-planning -a codex`. Or copy the skill folder (cursor-rules/skills/qa-planning in WellApp-ai/Well) into .agents/skills/qa-planning in your project. Codex loads it when a task matches its description.

Can I use QA Planning 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 WellApp-ai/Well --skill qa-planning -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/qa-planning, .gemini/skills/qa-planning, .github/skills/qa-planning and .opencode/skills/qa-planning in your project.

What does QA Planning need to run?

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

Does QA Planning 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 QA Planning 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 QA Planning use?

QA Planning 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 QA Planning use?

About 3.9k tokens (SKILL.md is roughly 16k 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 QA Planning?

Skills that share tags, products or a category with QA Planning: User Story Writer (deanpeters/Product-Manager-Skills, 7.2k stars), Ralph Tui Create Beads (subsy/ralph-tui, 2.5k stars), Agile Product Owner (alirezarezvani/claude-skills, 28k stars) and Ralph Tui Create Beads Rust (subsy/ralph-tui, 2.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains QA Planning?

WellApp-ai (a GitHub organization) maintains it in WellApp-ai/Well, which has 345 GitHub stars. The repository holds 36 skills in this directory. The repository was last updated on October 7, 2026.

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

Install QA Planning

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

QA Planning Skill

When to Use

Output: QA Contract

Instructions

Phase 0: Identify ALL Data Sources (CRITICAL)

Phase 2: Define Pre-conditions Matrix (Given)

Phase 3: Map When (Method + Path)

Phase 4: Define Then (Response Contract)

Phase 5: Write Gherkin Scenarios (G#N)

Phase 6: Build-time Static Scenarios (G#N)

Phase 7: Middleware/Routing Scenarios (G#N)

Phase 8: Frontend QA (Acceptance Criteria - AC#N)

Phase 9: Integration Points

Phase 10: Coverage Summary

Phase 11: Artifact Validation (Poka-Yoke)

Gate 1 Validation (DIVERGE -> CONVERGE)

Gate 2 Validation (CONVERGE -> PLAN)

Validation Output

Integration

Output Format: QA Contract

Frontend Acceptance Criteria

Coverage Summary

Validation

Files

Compare with similar skills

Similar skills

More from WellApp-ai/Well

Related

Questions about QA Planning