Pre-spec steering layer for AI coding agents — capture product intent, invariants, and decision criteria before implementation, hand off to spec-driven workflows, observe intent drift (warn-only), and write learnings back to keep intent and code aligned.
Skill Claude CodeCodex
From the Intent Tree, build the decision criteria for this change (North Star / Anti-direction / Invariants / Decision Rules). Prevents Claude from escaping into local optimizations. Does not implement.
Skill Claude CodeCodex
Projection skill that, for a packet responsible for designing a persistent data model, reads, read-only, the three layers — the intent (packet), the invariants (compass), and the existing schema/migration — and projects table definitions/constraints/indexes/naming into derived output under .intent/db-design/, tracing…
Skill Claude CodeCodex
The entry point of Intent Planning. From the repository's pain points, README, and an overview of existing code, build an Intent Tree (L0-L4) and recommend/confirm the mode for working out the Intent. Does not implement.
Skill Claude CodeCodex
Convert one chosen packet into a condensed draft that can be handed to cc-sdd without wasting tokens. Does not intrude on cc-sdd's main generation. Can invoke /kiro-spec-init when instructed to proceed.
Skill Claude CodeCodex
Convert one chosen packet into a proposal draft + delta spec hints that can be handed to OpenSpec without wasting tokens. Does not intrude on OpenSpec's main generation. Can invoke /opsx:propose when instructed to proceed.
Skill Claude CodeCodex
Convert one chosen packet into a specify input + spec hints that can be handed to GitHub Spec Kit without wasting tokens. Does not intrude on Spec Kit's main generation. Can invoke /speckit.specify when instructed to proceed.
Skill Claude CodeCodex
Brownfield entry skill that reads an existing codebase with no remaining docs / spec read-only, extracts intent candidates (roughly L0–L3), invariant candidates, and gaps of silence — every item marked inferred with its recovery basis — and ingests them into .intent/code-ingest/.
Skill Claude CodeCodex
Inward skill that reads user-provided natural-language text (specs such as PRD / issue / user story, plus fragmentary notes, scribbles, and voice transcripts) read-only and ingests unstated intent candidates and gaps of silence into .intent/spec-ingest/. Fragmentary input is bundled by topic and sorted into decided /…
Skill Claude CodeCodex
After implementation, cross-check the .intent/ deliverables against the implementation reality on the three axes of completeness / correctness / coherence, classify the drift, and propose corrections. Reflects changes only after user approval. Guides missed write-backs to /intent-writeback.
Skill Claude CodeCodex
Read-only aggregation skill that reads the scattered .intent/ artifacts and generates a formatted read-through/overview view under .intent/overview/ as a derived view. Never modifies any canonical artifact.
Skill Claude CodeCodex
From the Intent Tree and Intent Compass, build the Packet Plan before proceeding to specification or direct implementation. Each packet has a parent intent and is behavior-preserving / testable / rollbackable. Does not implement.
Skill Claude CodeCodex
Continues a whole Intent Planning request, including replies after a human confirmation pause, through discover, compass, packets, and the selected export. Does not take over explicit specific-stage requests.
Skill Claude CodeCodex
Outward projection skill that reads git commit history read-only, matches each commit against intent to thicken "why it changed," and derives a release note under .intent/release-note/.
Skill Claude CodeCodex
Read-only guidance skill that reads the current state of .intent/ and recommends a summary of where you are plus exactly one "next move". Never creates, modifies, or deletes any file.
Skill Claude CodeCodex
Outward generation skill that reads Intent, steering, and packets within a given scope read-only and maps them into a single readable natural-language Spec under .intent/nl-spec/ in the given format.
Skill Claude CodeCodex
Read-only verification that cross-checks intent-tree, intent-compass, and packets (+ the export draft) and reports contradictions, coverage gaps, boundary inconsistencies, and normative violations with severity. Fixes remain proposals.
Skill Claude CodeCodex
After implementing an exported packet, record the learnings gained from the implementation into deltas.md as a delta, and promote only the approved items into the canonical deliverables (intent-tree / intent-compass / packets). Never edits the canonical deliverables directly.