dmlguq456
UserHearting — the agent setting for Claude Code, Codex, and OpenCode. One portable contract projected onto all three, with routed capabilities, sealed cross-harness dispatch, per-node model tiers, and a live Fleet view. Formerly agent_setting.
Categories
Indexed Skills (27)
code-execute
Use only when autopilot-code dispatches the implementation stage for an approved plan. Not for top-level user requests or primary capability routing.
code-plan
Use only when autopilot-code dispatches the planning and plan-check stage. Not for top-level user requests or primary capability routing.
code-refine
Use only when autopilot-code dispatches plan revision after user notes, plan-check feedback, or verification failure. Not for top-level user requests or primary capability routing.
code-report
Use only when autopilot-code dispatches the final code-cycle reporting stage. Not for top-level user requests or primary capability routing.
code-test
Use only when autopilot-code dispatches implementation verification and evidence recording. Not for top-level user requests or primary capability routing.
design-components
Use only when autopilot-design dispatches component, mockup, or preview construction. Not for top-level user requests or primary capability routing.
design-handoff
Use only when autopilot-design dispatches the development-handoff packaging stage. Not for top-level user requests or primary capability routing.
design-init
Use only when autopilot-design dispatches design environment and state initialization. Not for top-level user requests or primary capability routing.
design-refs
Use only when autopilot-design dispatches visual-reference collection and brief creation. Not for top-level user requests or primary capability routing.
design-review
Use only when autopilot-design dispatches design quality, token-contract, and breakage review. Not for top-level user requests or primary capability routing.
design-tokens
Use only when autopilot-design dispatches design-token definition or revision. Not for top-level user requests or primary capability routing.
draft-refine
Use only when autopilot-draft or autopilot-refine dispatches an internal strategy or draft refinement stage. Not for top-level user requests or primary capability routing.
draft-strategy
Use only when autopilot-draft dispatches document strategy and evidence-plan creation. Not for top-level user requests or primary capability routing.
post-it
Use when the acting agent needs to store, retrieve, resolve, hand off, or promote a scoped working-memory item in support of current work. Not for primary task routing, broad artifact triage, or replacing the capability that owns the current work.
artifact-projection-read
Use when an agent or operator needs to browse or query an existing Cairn artifact projection without changing artifacts or runtime state. Not for primary task routing, ingest, mutation, activation, deactivation, apply, migration, namespace switching, or flat-browse fallback ownership.
analyze-project
Use when the user asks to analyze existing code, a paper, or a document and no usable persistent analysis exists, or to refresh stale analysis; default initial analysis to persistent output. Not for conversational, read-only, or no-file analysis; orientation, context recovery, status, experiments, external research, source changes, or completed-work audits.
analyze-user
Use when durable cross-project user preferences must be inferred from coding, writing, or analysis evidence and stored as a profile. Not for one-project context recovery, casual preference acknowledgment, or ordinary task execution.
audit
Use when completed work or artifacts need a read-oriented inspection for drift, inconsistency, omissions, or unsupported claims. Not for implementing fixes, producing the primary artifact, or replacing execution-stage verification.
autopilot-apply
Use when an approved cheatsheet or patching guide must be applied to the real source artifact and the applied result verified. Not for drafting or refining the cheatsheet, or for unrelated source implementation.
autopilot-code
Use when source code must be implemented, debugged, refactored, or code-audited through a plan, execution, test, and report loop. Not for requirements-only changes, new empirical experiments, or document-only editing.
autopilot-design
Use when a visual product surface needs references, design tokens, components or mockups, review, and development handoff. Not for implementing an already-approved design in code or for document prose work.
autopilot-draft
Use when a new paper, presentation, report, proposal, or other user-facing document must be produced from evidence. Not for correcting only an existing document or for source-code implementation.
autopilot-lab
Use when training setup, checkpoint evaluation, ablation, metric computation, or other new empirical output is required. Not for ordinary production-code changes that create no new experiment or evaluation result.
autopilot-refine
Use when an existing document or research artifact needs factual, structural, stylistic, or review-driven correction with history preserved. Not for drafting a new artifact or performing new empirical work required before the document can change.
autopilot-research
Use when a task needs a durable survey of new academic, technology, or market evidence before downstream specification or production. Not for repository-only project analysis, a simple factual lookup, or work already grounded by sufficient current evidence.
autopilot-ship
Use when an application needs deployment or release configuration, readiness verification, and a ship checklist. Not for ordinary feature implementation or an unauthorized production deployment.
autopilot-spec
Use when product requirements, architecture, evaluation policy, or another blueprint must be created or materially updated before implementation. Not for implementing an already-approved specification or for editing unrelated documents.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.