기타 스킬

Performs claim-evidence verification for agent outputs, recording supported, contradicted, or insufficient-evidence results alongside source accessibility. Activate on 'detect hallucination', 'fact check', 'verify claims', 'check accuracy', 'find fabrications'. NOT for validation (use dag-output-validator) or confidence scoring (use dag-confidence-scorer).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Profiles DAG execution performance including latency, token usage, cost, and resource consumption. Identifies bottlenecks and optimization opportunities. Activate on 'performance profile', 'execution metrics', 'latency analysis', 'token usage', 'cost analysis'. NOT for execution tracing (use dag-execution-tracer) or failure analysis (use dag-failure-analyzer).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Review of Cognitive Systems Engineering applications and current practice in safety-critical domains

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Validates agent outputs against schemas and quality criteria, scores confidence, detects hallucinations, monitors convergence, decides when to iterate, and synthesizes actionable feedback. Use when checking if a node's output is acceptable, scoring confidence, detecting fabricated content, deciding whether to re-execute, or generating improvement feedback. Activate on "validate output", "check quality", "confidence score", "hallucination check", "should we iterate", "improvement feedback". NOT for executing DAGs (use dag-runtime), planning DAGs (use dag-planner), or matching skills (use dag-skills-matcher).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Validates agent outputs against expected schemas and quality criteria. Reports structural and content checks within the declared evidence scope. Activate on 'validate output', 'output validation', 'schema validation', 'check output', 'output quality'. NOT for confidence scoring (use dag-confidence-scorer) or hallucination detection (use dag-hallucination-detector).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Records and evaluates event-specific probability forecasts for agent outputs. NOT for validation or automatic acceptance.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Builds scoped, provenance-preserving context packets between DAG nodes. NOT for execution or aggregation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Investigates DAG incidents with a precise top event, timeline, competing hypotheses, barriers, propagation, and bounded recovery. NOT for automated root-cause classification, trace collection, or performance profiling.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Ranks eligible skill candidates with explicit retrieval evidence, capability coverage, and uncertainty. NOT for discovery, authorization, or execution planning.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Propose and safely admit immutable DAG revisions after failures, requirements, resource changes, or unresolved effects. NOT for mutating an executing graph in place or retrying an effect with unknown commit state.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

AI-powered career biographer that conducts empathetic interviews, extracts structured career narratives, and transforms professional stories into portfolios, CVs, and personal brand assets. This skill should be used when users want to document their career journey, create professional portfolios, generate CVs, or craft compelling career narratives.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert causal reasoning and mental model construction for diagnosis and prediction in complex domains

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Naturalistic causal reasoning for failures and disputed attribution. Use when postmortems or root-cause debates need reframing. NOT for causal inference, fault trees, or fully observed failures.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Foundational concurrent computation model where actors communicate exclusively through asynchronous message passing

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Construct a finite oriented simplicial or cellular cochain model and compute its stated linear invariants when coefficient spaces, maps, metrics, and observations are explicit. Use for scoped Hodge, rank, or residual calculations; not for attributing agent intent or authorizing effects. NOT for attributing intent, identifying a liar, or authorizing external effects.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Compare before/after Coval runs using matched cases, stable metric versions and inspected conversation evidence. Use to assess a regression or proposed improvement; does not automatically launch or tune anything.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Launch a specific Coval evaluation with explicit cases and execution bounds. Use when resources are already selected; for result analysis use quick-eval.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Connect a customer agent to Coval and complete a small first evaluation with inspected voice or chat results. Use when no usable evaluation exists yet; reuse existing recordings and resources when available.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Monitor a Coval run's progress with live updates. Use when user wants to check run status or wait for completion.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

WindowPanel (@ai-matrx/summon/window) and its window manager. Use when a window won't drag, resize, minimize or pop out, the tray or restore is wrong, rendering <WindowPanel> on a page, or editing features/window-panels/**. NOT for opening or registering overlays (use overlay-system).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when adding/changing a CMS surface manifest, the site_structure/html_pages_structure framing XML, a CMS context menu/extraSections wiring, or the cms-authoring platform skill. Also use when a new CMS route/tab needs an agent entry point.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Collapsing every copy of one kind of thing (tables, UIs, hooks, APIs, renderers) into a single canonical one. Use when asked to unify, merge, converge, or 'make one X used everywhere', before migrating callers onto a new canonical piece, or removing a duplicate component. NOT for docs (use docs).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Redux Toolkit selector rules against re-renders, recalculation warnings, and render loops. Use when writing useSelector/useAppSelector or createSelector, deriving state in a connected component, or seeing 'Selector returned a different result when called with the same parameters'.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.