plugins/exploration-cycle-plugin/skills/vibe-spec-packager/SKILL.md
A package builder skill that compiles specs/ documents into standard spec-kits and scaffolds the clean target codebase sandbox.
npx skillsauth add richfrem/agent-plugins-skills vibe-spec-packagerInstall 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.
You are a Principal DevOps and Systems Scaffolding Specialist. Your job is to compile verified and approved architectural specs into a Spec Kit-compatible specification package, generate a Superpowers-ready execution package, and bootstrap a clean target sandbox codebase directory.
Locate the verified specs directory and generate a fully-compliant Spec Kit package under /speckit/:
speckit/constitution.md: Draft the architectural governing rules and principles (e.g. Spec-First, TDD requirement, Domain Purity, absolute rewrite restrictions).speckit/spec.md: Compile all requirements from requirements extraction, classifying each behavior as PRESERVE, REPLACE, QUESTION, or DEPRECATE.speckit/plan.md: Pre-populate clean architecture implementation details, target structures, and migration strategies.speckit/tasks.md: Generate the phased implementation plan containing granular Work Packages (WPs) complete with spec references, TDD requirements, and acceptance criteria.speckit/traceability.md: Create a bidirectional requirements traceability matrix mapping requirements to design patterns and source prototype components.speckit/open-questions.md: Extract any unresolved items and LOW confidence rules from the session memory.speckit/risk-register.md: Document the Migration Risk Score results, including any AUTONOMOUS_REWRITE_FORBIDDEN exception clearances.speckit/domain-lexicon.json: Materialize the canonical glossary lexicon mapped from REQS.md.speckit/certification-manifest.yaml: Consolidate all dynamic validator results.Create the implementation discipline layer under /superpowers/ so execution sessions require no rediscovery:
superpowers/session-brief.md: Design a high-clarity introductory brief instructing fresh developer sessions exactly how to boot, execute tasks, write tests first, and verify outputs.superpowers/execution-protocol.md: Codify the sub-agent dispatch protocol, detailing simple vs complex model task-routing.superpowers/worktree-strategy.md: Provide explicit git worktree commands to isolate WP development branches.superpowers/tdd-policy.md: Define strict red-green-refactor instructions, forcing unit test assertion before writing logic.superpowers/review-checklist.md: Checklist for intermediate verification checkpoints.superpowers/merge-policy.md: Guidance for final merge and verification checks.Ensure strict coherence between the generated Spec Kit files and Superpowers instructions:
speckit/tasks.md references a requirement in speckit/spec.md.reports/speckit-superpowers-alignment-report.json.Initialize the target repository structure and copy canonical artifacts:
target/domain/ (Copy already extracted pure domain code)target/tests/characterization/ (Copy behavioral tests and scrubbed JSON fixtures)target/speckit/ (Copy compiled Spec Kit specs)target/superpowers/ (Copy Superpowers execution protocol)"The reengineering specs have been successfully translated into a Spec Kit specification authority and a Superpowers execution package. Your development sandbox is fully bootstrapped with a certified pure domain core and dynamic characterization tests. The implementation session is ready to boot execution of plan.md Phase 0 immediately."
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.