plugins/spec-kitty-plugin/skills/spec-kitty-constitution/SKILL.md
A standard Spec-Kitty workflow routine.
npx skillsauth add richfrem/agent-plugins-skills spec-kitty-constitutionInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
<!-- spec-kitty-command-version: 3.0.3 -->Source: This skill augments the baseline workflow located at
./workflows/spec-kitty.constitution.md. It acts as an intelligent wrapper that is continuously improved with each execution.
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
In repos with multiple features, always pass --feature <slug> to every spec-kitty command.
This command delegates constitution work to the CLI constitution workflow. Do not hand-author long governance content in chat unless the user explicitly asks for manual drafting.
.kittify/constitution/constitution.md.kittify/constitution/interview/answers.yaml.kittify/constitution/references.yaml.kittify/constitution/library/*.mdUse when user wants speed, defaults, or bootstrap:
spec-kitty constitution interview --defaults --profile minimal --json
spec-kitty constitution generate --from-interview --json
Use when the user wants project-specific policy capture:
spec-kitty constitution interview --profile comprehensive
spec-kitty constitution generate --from-interview
constitution interview (or edit answers.yaml) and regenerate.--force with generate if the constitution already exists and must be replaced.references.yaml.After generation, verify status:
spec-kitty constitution status --json
After constitution generation, first-run lifecycle actions should load context explicitly:
spec-kitty constitution context --action specify --json
spec-kitty constitution context --action plan --json
spec-kitty constitution context --action implement --json
spec-kitty constitution context --action review --json
Use JSON text as governance context. If mode=bootstrap, follow referenced docs as needed.
tools
Ingests repository files into the ChromaDB vector store. Builds or updates the vector index from a manifest or directory scan using ingest.py. Use when new files need to be indexed or the vector store is out of date. <example> user: "Index these new plugin files into the vector database" assistant: "I'll use vector-db-ingest to add them to the vector store." </example> <example> user: "The vector store is missing recent files -- update it" assistant: "I'll use vector-db-ingest to re-index the changes." </example>
data-ai
Removes stale and orphaned chunks from the ChromaDB vector store for files that have been deleted or renamed. Use after files are removed or moved to keep the vector index in sync with the filesystem. <example> user: "Clean up the vector store after I deleted some files" assistant: "I'll use vector-db-cleanup to remove orphaned chunks." </example> <example> user: "The vector database has chunks for files that no longer exist" assistant: "I'll run vector-db-cleanup to prune them." </example>
testing
Audit Vector DB coverage -- compares the live filesystem manifest against the ChromaDB index to identify coverage gaps.
development
3-Phase Knowledge Search strategy for the RLM Factory ecosystem. Auto-invoked when tasks involve finding code, documentation, or architecture context in the repository. Enforces the optimal search order: RLM Summary Scan (O(1)) -> Vector DB Semantic Search -> Grep/Exact Match. Never skip phases.