spec-discovery
Parse specs to extract IDs, titles, and traceability metadata (repo, path, hash).
Best use case
spec-discovery is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Parse specs to extract IDs, titles, and traceability metadata (repo, path, hash).
Teams using spec-discovery should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/spec-discovery/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How spec-discovery Compares
| Feature / Agent | spec-discovery | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Parse specs to extract IDs, titles, and traceability metadata (repo, path, hash).
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Spec Discovery Skill
Locate specs and external request headers, extract IDs (e.g., `REQ-NOTIFY-001`), and return traceable metadata for downstream agents.
## Variables
| Variable | Default | Description |
|----------|---------|-------------|
| ROOT | . | Primary repository root |
| EXTRA_REPOS | [] | Additional repo roots containing `specs/` |
| INCLUDE_EXTERNAL_REQUESTS | true | Scan `specs/external-requests/` |
| OUTPUT_FORMAT | json | json or toon manifest output |
## Workflow (Mandatory)
1. **Load repositories**: ROOT + EXTRA_REPOS
2. **Walk specs**: `specs/`, `specs/external-requests/`, skip `specs/templates/`
3. **Parse headings**: match `^#+\s*(REQ-[A-Za-z0-9_-]+)\s*:?\s*(.*)$`
4. **Normalize**: path relative to repo root, anchor from ID + title
5. **Traceability**: compute SHA-256 of file content; record `source_repo`, `path`, `hash`
6. **Emit manifest**: sorted by repo → path → ID in JSON/TOON (see Output Schema)
## Red Flags (Stop & Verify)
- No IDs detected in a spec file → confirm heading format before skipping
- Duplicate spec IDs across repos → flag in the manifest `notes` field
- Missing `specs/` directory → report empty result rather than failing
## Output Schema
```json
{
"format": "spec-manifest/v1",
"generated_at": "<ISO-8601 UTC>",
"sources": [
{"repository": "<repo-name>", "root": "<abs-path>"}
],
"specs": [
{
"id": "REQ-NOTIFY-001",
"title": "Email Sending Endpoint",
"source_repo": "ai-dev-kit",
"path": "specs/external-requests/notify.md",
"link": "specs/external-requests/notify.md#req-notify-001-email-sending-endpoint",
"hash": "<sha256-of-file>"
}
]
}
```
## Provider Notes
- Use this skill when other commands request `/ai-dev-kit:specs-find` or spec traceability.
- Prefer JSON for machine workflows; use TOON for compact prompt embedding.
- Preserve ID/title casing; anchors should be lowercase + hyphenated.Related Skills
vertex-engine-inspector
Inspect and validate Vertex AI Agent Engine deployments including Code Execution Sandbox, Memory Bank, A2A protocol compliance, and security posture. Generates production readiness scores. Use when asked to inspect, validate, or audit an Agent Engine deployment. Trigger with "inspect agent engine", "validate agent engine deployment", "check agent engine config", "audit agent engine security", "agent engine readiness check", "vertex engine health", or "reasoning engine status".
spec-writing
Execute this skill should be used when the user asks about "writing specs", "specs.md format", "how to write specifications", "sprint requirements", "testing configuration", "scope definition", or needs guidance on creating effective sprint specifications for agentic development. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
openapi-spec-generator
Openapi Spec Generator - Auto-activating skill for API Development. Triggers on: openapi spec generator, openapi spec generator Part of the API Development skill category.
consul-service-discovery
Consul Service Discovery - Auto-activating skill for DevOps Advanced. Triggers on: consul service discovery, consul service discovery Part of the DevOps Advanced skill category.
adk-deployment-specialist
Deploy and orchestrate Vertex AI ADK agents using A2A protocol. Manages AgentCard discovery, task submission, Code Execution Sandbox, and Memory Bank. Use when asked to "deploy ADK agent" or "orchestrate agents". Trigger with phrases like 'deploy', 'infrastructure', or 'CI/CD'.
update-specification
Update an existing specification file for the solution, optimized for Generative AI consumption based on new requirements or updates to any existing code.
typespec-create-api-plugin
Generate a TypeSpec API plugin with REST operations, authentication, and Adaptive Cards for Microsoft 365 Copilot
typespec-create-agent
Generate a complete TypeSpec declarative agent with instructions, capabilities, and conversation starters for Microsoft 365 Copilot
typespec-api-operations
Add GET, POST, PATCH, and DELETE operations to a TypeSpec API plugin with proper routing, parameters, and adaptive cards
gen-specs-as-issues
This workflow guides you through a systematic approach to identify missing features, prioritize them, and create detailed specifications for implementation.
create-specification
Create a new specification file for the solution, optimized for Generative AI consumption.
create-github-pull-request-from-specification
Create GitHub Pull Request for feature request from specification file using pull_request_template.md template.