ワンクリックで
tasks-spec-update
Use when updating specifications, comparing branches, or ensuring documentation reflects current implementation.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Use when updating specifications, comparing branches, or ensuring documentation reflects current implementation.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Production prompt-engineering pipeline for GPT-Image-2 / OpenAI image generation. Pairs a 'media-designer' agent with a hosted searchable corpus of 3,238 community-vetted prompts, decomposed across 10 controlled vocabularies (subjects, styles, lighting, cameras, moods, palettes, compositions, mediums, techniques, usecases). Each record carries: full prompt body, twitter/X attribution link, downloaded reference image. Workflow: agent diagnoses the user brief → searches the corpus → picks a mood-aligned base → refactors the chosen prompt into a parameterised {argument} template → resolves arguments from user intent → returns the final paste-ready prompt with attribution + reference image. Use when the user wants a polished image-generation prompt for ads, posters, product shots, portraits, character sheets, UI mockups, infographics, exploded-view diagrams, or any other GPT-Image-2 / OpenAI image task.
Write and optimize prompts for AI-generated outcomes across text and image models. Use when crafting prompts for LLMs (Codex, GPT, Gemini), image generators (Midjourney, DALL-E, Stable Diffusion, Imagen, Flux), or video generators (Veo, Runway). Covers prompt structure, style keywords, negative prompts, chain-of-thought, few-shot examples, iterative refinement, and domain-specific patterns for marketing, code, and creative writing.
Search technical documentation using executable scripts to detect query type, fetch from llms.txt sources (context7.com), and analyze results. Use when user needs: (1) Topic-specific documentation (features/components/concepts), (2) Library/framework documentation, (3) GitHub repository analysis, (4) Documentation discovery with automated agent distribution strategy
Package entire code repositories into single AI-friendly files using Repomix. Capabilities include pack codebases with customizable include/exclude patterns, generate multiple output formats (XML, Markdown, plain text), preserve file structure and context, optimize for AI consumption with token counting, filter by file types and directories, add custom headers and summaries. Use when packaging codebases for AI analysis, creating repository snapshots for LLM context, analyzing third-party libraries, preparing for security audits, generating documentation context, or evaluating unfamiliar codebases.
Apply structured, reflective problem-solving for complex tasks requiring multi-step analysis, revision capability, and hypothesis verification. Use for complex problem decomposition, adaptive planning, analysis needing course correction, problems with unclear scope, multi-step solutions, and hypothesis-driven work.
Starter template for creating new skills. Use when defining a new skill scaffold with frontmatter and concise execution instructions.
| name | tasks-spec-update |
| description | Use when updating specifications, comparing branches, or ensuring documentation reflects current implementation. |
| allowed-tools | Read, Write, Edit, Grep, Glob, Bash, Task |
# Compare branches
git diff main..feature-branch --name-only
# Get detailed diff
git diff main..feature-branch
# List commits with messages
git log main..feature-branch --oneline
# Find files changed since date
git log --since="2024-01-01" --name-only --oneline
# Find all spec files
find . -name "*.spec.md" -o -name "*-specification.md"
# Find implementation files
grep -r "class.*Command" --include="*.cs" -l
# Cross-reference
grep -r "SaveEmployee" --include="*.md" # In specs
grep -r "SaveEmployee" --include="*.cs" # In code
# Specification Gap Analysis
## Date: [Date]
## Feature: [Feature Name]
## Implementation Status
| Component | Specified | Implemented | Gap |
|-----------|-----------|-------------|-----|
| Entity: Employee | ✅ | ✅ | None |
| Command: SaveEmployee | ✅ | ✅ | Missing validation doc |
| Query: GetEmployeeList | ✅ | ✅ | Filters not documented |
| Event: OnEmployeeCreated | ❌ | ✅ | Not in spec |
## New Implementations (Not in Spec)
1. `BulkUpdateEmployeeCommand` - Added in PR #123
2. `EmployeeExportQuery` - Added for reporting
## Spec Items Not Implemented
1. `EmployeeArchiveCommand` - Deferred to Phase 2
2. `EmployeeAuditTrail` - Pending requirements
## Documentation Updates Needed
1. Add BulkUpdateEmployeeCommand to spec
2. Document new query filters
3. Add event handler documentation
## Specification Updates
### Entities
- [ ] Update property list
- [ ] Document new computed properties
- [ ] Add validation rules
- [ ] Update relationships
### Commands
- [ ] Add new commands
- [ ] Update validation rules
- [ ] Document side effects
- [ ] Add error codes
### Queries
- [ ] Document new filters
- [ ] Update response schema
- [ ] Add pagination details
### Events
- [ ] Document entity events
- [ ] List event handlers
- [ ] Describe cross-service effects
### API Endpoints
- [ ] Add new endpoints
- [ ] Update request/response
- [ ] Document auth requirements
# Employee Entity Specification
## Properties
| Property | Type | Required | Description |
|----------|------|----------|-------------|
| Id | string | Yes | Unique identifier (ULID) |
| FullName | string | Yes | Employee full name (max 200) |
| Email | string | Yes | Email address (unique per company) |
| Status | EmployeeStatus | Yes | Current employment status |
| PhoneNumber | string | No | Contact phone (NEW in v2.1) |
## Computed Properties
| Property | Calculation |
|----------|-------------|
| IsActive | Status == Active && !IsDeleted |
| DisplayName | `{Code} - {FullName}` |
## Validation Rules
1. FullName: Required, max 200 characters
2. Email: Required, valid email format, unique within company
3. PhoneNumber: Optional, valid phone format (NEW in v2.1)
## Static Expressions
| Expression | Purpose |
|------------|---------|
| UniqueExpr(companyId, userId) | Find unique employee |
| ActiveInCompanyExpr(companyId) | Filter active employees |
| SearchExpr(term) | Full-text search |
# SaveEmployeeCommand Specification
## Overview
Creates or updates an employee record.
## Request
```json
{
"id": "string | null",
"fullName": "string",
"email": "string",
"status": "Active | Inactive | Terminated",
"phoneNumber": "string | null"
}
| Field | Rule | Error Code |
|---|---|---|
| fullName | Required | EMPLOYEE_NAME_REQUIRED |
| fullName | Max 200 chars | EMPLOYEE_NAME_TOO_LONG |
| Required | EMPLOYEE_EMAIL_REQUIRED | |
| Valid format | EMPLOYEE_EMAIL_INVALID | |
| Unique in company | EMPLOYEE_EMAIL_EXISTS |
{
"employee": {
"id": "string",
"fullName": "string",
"email": "string",
"status": "string"
}
}
PlatformCqrsEntityEvent<Employee> raised| Code | HTTP | Description |
|---|---|---|
| EMPLOYEE_NOT_FOUND | 404 | Employee ID not found |
| EMPLOYEE_EMAIL_EXISTS | 400 | Email already in use |
| EMPLOYEE_VALIDATION_FAILED | 400 | Validation error |
## Pattern 3: API Endpoint Specification
```markdown
# Employee API Endpoints
## Base URL
`/api/Employee`
## Endpoints
### GET /api/Employee
List employees with filtering and pagination.
**Query Parameters**
| Parameter | Type | Description |
|-----------|------|-------------|
| searchText | string | Full-text search |
| statuses | array | Filter by status |
| skipCount | int | Pagination offset |
| maxResultCount | int | Page size (max 100) |
**Response**
```json
{
"items": [...],
"totalCount": 100
}
Create or update employee.
Request Body See SaveEmployeeCommand specification.
Soft delete an employee.
Path Parameters
| Parameter | Type | Description |
|---|---|---|
| id | string | Employee ID |
Response: 204 No Content
All endpoints require authentication.
Use Authorization: Bearer {token} header.
| Endpoint | Required Role |
|---|---|
| GET | Employee, Manager, Admin |
| POST | Manager, Admin |
| DELETE | Admin |
## Phase 4: Verification
### Cross-Reference Check
```bash
# Verify all commands are documented
for cmd in $(grep -r "class.*Command" --include="*.cs" -l); do
name=$(grep -o "class [A-Za-z]*Command" "$cmd" | head -1)
if ! grep -q "$name" docs/specifications/*.md; then
echo "Missing in spec: $name"
fi
done
# Specification Verification Report
## Date: [Date]
## Verified By: AI
## Summary
- Total Specs: 15
- Up to Date: 12
- Needs Update: 3
- Missing: 0
## Issues Found
### Outdated Specifications
1. **Employee.spec.md**
- Missing: PhoneNumber property
- Missing: BulkUpdate command
2. **API-Reference.md**
- Missing: /export endpoint
- Outdated: Error codes
## Recommendations
1. Update Employee.spec.md with new properties
2. Add BulkUpdateEmployeeCommand specification
3. Regenerate API reference from OpenAPI