Agent skill · data analytics · aiskillstore
spec-discovery
Parse specs to extract IDs, titles, and traceability metadata (repo, path, hash).
Why this skill is useful
Adds a specialized workflow for parsing specs and extracting traceability metadata that the AI wouldn't reliably generate on its own.
What it needs
About 1k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.
What this skill does
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 EXTRAREPOS [] Additional repo roots containing specs/ INCLUDEEXTERNALREQUESTS true Scan specs/external-requests/ OUTPUTFORMAT json json or toon manifest output Workflow (Mandatory) 1. Load repositories: ROOT + EXTRAREPOS 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 sourcerepo, 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 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.
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aiskillstore/spec-discovery