Bi-directional translator between verbose descriptions and established terminology (semantic anchors). Use when (1) user describes a concept verbosely and you want to identify the precise term, or (2) user asks for methodology/approach and you want to suggest relevant anchors. Covers 120+ terms across testing, architecture, design principles, problem-solving, requirements, documentation, communication, development workflow, statistical methods, strategic planning, and creative writing.
Install Semantic Contracts (and, as a sub-mode, individual semantic anchors) into a coding agent's persistent context for Claude Code, Codex, Gemini CLI, Cursor, GitHub Copilot, and similar agents. Use when setting up project-level or user-level onboarding, generating or updating AGENTS.md / CLAUDE.md / GEMINI.md / Copilot instruction files, or choosing which contracts a project should run. A contract is the part the LLM cannot guess — a named composition of anchors plus the project's own rendered template — so installing contracts is the high-value path; installing a bare anchor list is the lightweight fallback.
DEPRECATED alias of semantic-contracts-installer. Renamed because the skill's high-value job is installing Semantic Contracts (compositions the LLM cannot guess), not bare anchor lists. Use semantic-contracts-installer instead; this alias forwards to it and will be removed after one release.
Author an arc42 architecture document with the project's cross-section traceability rules. Use when producing or extending an arc42 document — it carries the procedure the "Architecture Documentation" contract deliberately leaves out: scaffolding the with-help template, the five traceability rules arc42 does not enforce, the Chapter 11 Risks-vs-Technical-Debt structure, the ADR-to-risk-ID wiring, the Chapter 1.2-vs-10 quality-goal marking, and the six-part Quality Attribute Scenario form. The contract pins the vocabulary (arc42, C4/PlantUML, Nygard ADRs, Pugh); this skill is the how-to.
Recover the "theory" (Naur 1985) of an existing codebase through recursive question refinement before writing documentation. Use on brownfield projects where the spec is missing — produces a Question Tree separating what is answerable from code (with evidence) from what must be asked of the team (routed by role). Phase 1 builds the tree; team answers the OPEN leaves; Phase 2 synthesizes PRD, Cockburn use cases, arc42 architecture, and Nygard ADRs from the answered tree.
Empirically test whether a candidate term qualifies as a semantic anchor by probing how densely it sits in LLM training data — across several model tiers in a clean room — before proposing it. Use when triaging an anchor proposal, deciding anchor vs contract, or vetting a rename. Produces a verdict against the four criteria (Precise, Rich, Consistent, Attributable), a tier rating, and a ready-to-paste proposal or rejection.