Jeffallan/claude-skills / skills/spec-miner
spec-miner
VerifiedReverse-engineering specialist that extracts specifications from existing codebases. Use when working with legacy or undocumented systems, inherited projects, or old codebases with no documentation. Invoke to map code dependencies, generate API documentation from source, identify undocumented business logic, figure out what code does, or create architecture documentation from implementation. Trigger phrases: reverse engineer, old codebase, no docs, no documentation, figure out how this works, inherited project, legacy analysis, code archaeology, undocumented features.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.7 KB |
| references/analysis-checklist.md | markdown | 2.0 KB |
| references/analysis-process.md | markdown | 1.3 KB |
| references/ears-format.md | markdown | 1.8 KB |
| references/specification-template.md | markdown | 2.4 KB |
references/specification-template.md
View on GitHub# Specification Template
## Full Template
```markdown
# Reverse-Engineered Specification: [System/Feature Name]
## Overview
[High-level description based on analysis]
## Architecture Summary
### Technology Stack
- **Language**: TypeScript 5.x
- **Framework**: NestJS 10.x
- **Database**: PostgreSQL 15
- **ORM**: Prisma 5.x
### Module Structure
```
src/
├── auth/ # Authentication (JWT, guards)
├── users/ # User CRUD operations
├── orders/ # Order processing
└── common/ # Shared utilities
```
### Data Flow
```
Request → Guard → Controller → Service → Repository → Database
↓
External APIs
```
## Observed Functional Requirements
### [Module Name]
**OBS-XXX-001**: [Feature Name]
[EARS format requirement]
**OBS-XXX-002**: [Feature Name]
[EARS format requirement]
## Observed Non-Functional Requirements
### Security
- JWT tokens signed with RS256
- Passwords hashed with bcrypt (12 rounds)
- Rate limiting: 100 req/min per IP
### Performance
- Database connection pool: 10 connections
- Response timeout: 30 seconds
- Pagination: default 20, max 100
### Error Handling
| Code | Condition | Response |
|------|-----------|----------|
| 400 | Validation failure | `{ error: string, details: object }` |
| 401 | Invalid/missing token | `{ error: "Unauthorized" }` |
| 404 | Resource not found | `{ error: "Not found" }` |
| 500 | Unhandled error | `{ error: "Internal server error" }` |
## Inferred Acceptance Criteria
### AC-001: [Feature]
Given [precondition]
When [action]
Then [expected result]
## Uncertainties and Questions
- [ ] What triggers order status transitions?
- [ ] Is soft delete implemented for users?
- [ ] What external APIs are called?
- [ ] Are there background jobs?
## Recommendations
1. Add OpenAPI documentation to controllers
2. Missing input validation on PATCH endpoints
3. Consider adding request tracing
```
## Output Location
Save specification as: `specs/{project_name}_reverse_spec.md`
## Required Sections
| Section | Purpose |
|---------|---------|
| Overview | High-level summary |
| Architecture | Tech stack, structure, data flow |
| Functional Requirements | EARS format observations |
| Non-Functional | Security, performance, errors |
| Acceptance Criteria | Given/When/Then format |
| Uncertainties | Questions for clarification |
| Recommendations | Improvements identified |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |