Skill Router

Use the narrowest useful specialist contract. Clear bounded edits, ordinary explanations, factual lookups and routine verification often need no skill beyond AGENTS.md. This router is optional, not a startup checklist.

Need	Route
Material unresolved direction	brainstorming
Durable plan/dependencies	planning
Tracked multi-step implementation	execution
Substantive review or incoming feedback	code-review
Explicit interview	grilling; documented interview only when requested
Multi-session decision graph	manual wayfinder
Architecture improvement survey	manual improve-codebase-architecture
Describe a codebase or mechanism	direct source explanation, or manual codebase-research for a report
Intake-state decisions	manual triage; routine tracking uses AGENTS.md/runtime context
Inline visual	manual show-me when requested; ordinary tables need no additional workflow

Legacy receiving-code-review, idea-refine, grill-me, grill-with-docs and teach-session are thin entrypoints to shared owners. Verification-before-completion and cost-estimate retain only manual migration guidance; do not recommend their retired workflows as automatic steps.

The catalog below is generated by the repository skill-catalog script. It lists canonical skills, not proof that every harness exposes them. Inspect actual runtime discovery when needed; root-only harness utilities and show-me may be absent from Codex links. Manual invocation syntax depends on the installed harness. An explicit user-supplied skill path can be read without changing integration files.

<!-- generated:skill-catalog --> <!-- Generated by the harness's skill-catalog.py --write (source harness only; plugin copies are regenerated at publish) — edit above the marker only. -->

Model-invocable skills

authoring-for-agents, beads, brainstorming, code-review, codebase-design, design-evolve, document-review, domain-modeling, execution, first-principles-thinking, grilling, html-artifact, model-council, performance-optimization, perspective-council, planning, prototype, research, resolving-merge-conflicts, security, skill-router, systematic-debugging, test-driven-development

Slash-only workflows

Surface	Use
/check-invariants	Run mechanically checkable invariants from the project overlay and report pass or fail.
/codebase-research	Graduated research on an external or unfamiliar codebase — survey its capabilities, map its architecture, or trace one mechanism — into durable reports under docs/research/codebases/.
/cost-estimate	Legacy entrypoint; the uncalibrated code-volume and commit-based estimation method is retired.
/grill-me	Start a decision interview using the shared grilling workflow.
/grill-with-docs	Start a grilling interview and record authorized domain terminology and architectural decisions.
/i-have-adhd	Apply explicitly requested concise, easy-to-act-on communication preferences.
/idea-refine	Explore a raw idea through brainstorming using the legacy idea-refine entrypoint.
/improve-codebase-architecture	Find evidence-backed architecture improvements within a named area or requested codebase survey.
/phase-execution	Execute one phase of a workstream roadmap.
/receiving-code-review	Use when explicitly invoking the legacy receiving-code-review entrypoint; incoming feedback is owned by code-review.
/run-phases	Run every remaining phase of a workstream unattended.
/show-me	Show the current topic visually, inline in the conversation.
/teach	Teach a concept, walk through a session, or conduct an explicitly requested ongoing course.
/teach-session	Walk through the current session using the shared teach workflow.
/triage	Evaluate unevaluated beads issues and move each to an intake state — ready-for-agent, human, needs-info, backlog, or a wontfix close.
/verification-before-completion	Use only when explicitly invoking this legacy entrypoint; verification policy is owned by AGENTS.md.
/wayfinder	Map and resolve material decision dependencies across a multi-session effort.