「ds」の検索結果

Designs and audits native-unit capacity reservation, serial admission, ambiguity holds, stop reserves, effect closure, and control-disjoint settlement handoff for consequential agent attempts. Use when scarce capacity must be conserved across retry, rework, resurrection, or compensation. NOT for scheduling work, choosing models, pricing unlike resources into one scalar, authorizing effects, grading work, paying workers, or asserting runtime containment.

日本語の概要は準備中です。原文の説明を表示しています。

Strategic analyst that maps competitive landscapes, identifies white space opportunities, and provides positioning recommendations. Use when users need competitive analysis, market positioning strategy, differentiation tactics, or "how do I stand out?" guidance across any domain (portfolios, products, services). NOT for market size estimation or financial forecasting.

日本語の概要は準備中です。原文の説明を表示しています。

Implement AI chatbot analytics and conversation monitoring. Use when adding conversation metrics, tracking AI usage, measuring user engagement with chat, or building conversation dashboards. Activates for AI analytics, token tracking, conversation categorization, and chat performance.

日本語の概要は準備中です。原文の説明を表示しています。

license: Apache-2.0 NOT for unrelated tasks outside this domain.

日本語の概要は準備中です。原文の説明を表示しています。

Verifies build output integrity after code changes. Runs builds, validates artifact structure, checks for regressions in bundle size, asset references, and static export completeness. The last line of defense before a bad deploy ships.

日本語の概要は準備中です。原文の説明を表示しています。

Produces a narrow-interval quality signal for a WinDAGs skill that a third party can verify without inspecting model weights or method internals. The mechanism is attribution-kNN over a tamper-evident outcome log (task→skills→accept/reject store), combined with a conformal-prediction calibration certificate that provides a formal coverage guarantee. Thompson/Beta sampling is explicitly rejected as a category error: it produces a selection signal for stationary i.i.d. rewards, not an attestation signal for context-dependent LLM output quality. The resulting bundle — outcome-log Merkle root + conformal threshold + optional TEE guardrail signature — constitutes a "narrow-interval trust" credential: verifiable, bounded, and internals-opaque.

日本語の概要は準備中です。原文の説明を表示しています。

Track the full Toulmin epistemic ancestry of every claim produced by a multi-agent swarm. Each agent output is tagged with an argument chain (claim / data / warrant / relationship) derived from SwarmTracer spans and LineageEdge records, so operators can zoom into any sub-claim and see precisely which agents asserted it, what triggered each assertion, and how contradictions propagated or were synthesised away. The SwarmTracer pattern — wrapping the SwarmAgentExecutor to capture spans, record messages, and build a lineage graph — is the concrete runtime substrate. Argumentative lineage lifts that graph into the Toulmin vocabulary so reasoning provenance is both machine-queryable and human-interpretable.

日本語の概要は準備中です。原文の説明を表示しています。

Design polished terminal UX for CLIs and TUIs. Use for setup flows, dashboards, tables, and actionable errors. NOT for web UIs, desktop windows, API schemas, or shell automation.

日本語の概要は準備中です。原文の説明を表示しています。

Design and build mathematically rigorous, high-density, interactive data graphics and streaming telemetry visualizations following Mike Bostock's D3.js and Observable methodologies. Use when crafting custom SVG/Canvas charts, reactive streaming time-series, multi-dimensional brush-and-link coordinates, small multiples, or topological swarm graphs. NOT for generic dashboard template clones, basic spreadsheet charts, or off-the-shelf low-effort wrapper libraries.

日本語の概要は準備中です。原文の説明を表示しています。

Discipline an AI agent needs to work an issue/task tracker (Jira, Linear, GitHub Issues) as the shared source of truth: pull the right next item instead of inventing work, search before creating to avoid duplicates, write actionable items with checkable acceptance criteria, keep status transitions honest, and link work to items via branches/PRs/commits so progress is legible. Use when an agent picks up tracker work, files a new issue, updates status, or closes an item. NOT for authoring the PR itself (use agent-pr-authoring), roadmap-level planning and prioritization (use legible-roadmap-with-sidequests), or the mechanics of multiple agents coordinating on the same codebase (use multi-agent-coordination).

日本語の概要は準備中です。原文の説明を表示しています。

Apply cognitive task analysis to expert work that depends on perceptual cues, branching judgment, and recurring monitoring loops. Use when decomposing expert capability into agent structure, simulation design, or validation interviews. NOT for ordinary step-by-step SOP capture or simple pipelines with no tacit cue layer.

日本語の概要は準備中です。原文の説明を表示しています。

Time-blind friendly planning, executive function support, and daily structure for ADHD brains. Specializes in realistic time estimation, dopamine-aware task design, and building systems that actually work for neurodivergent minds.

日本語の概要は準備中です。原文の説明を表示しています。

Frame multi-agent designs through explicit environment, autonomy, information, coordination, commitment, incentive, and verification assumptions. NOT for endorsing multi-agent architecture without need or claiming runtime correctness from conceptual methods.

日本語の概要は準備中です。原文の説明を表示しています。

Designs and audits closed, ordered, replay-safe message protocols between already admitted agent bodies. Use when a multi-agent exchange needs explicit epochs, audiences, per-sender sequencing, gathers, terminal fences, acknowledgements, and deterministic replay. NOT for selecting or spawning agents, granting identity or authority, choosing a runtime topology, general human facilitation, wire transport implementation, or deciding whether evidence is true.

日本語の概要は準備中です。原文の説明を表示しています。

Data structures and serialization formats for agent-to-agent communication. Covers message envelopes, structured output schemas, capability declarations, task handoff payloads, error/retry signaling, and context windows as data structures. Compares the version-pinned A2A, MCP, and JSON-RPC role boundaries covered by this bundle; OpenAI and LangChain-specific APIs require their own current sources. Teaches when to use rigid schemas versus free-form content with validation, typed versus untyped boundaries, and streaming versus batch. Activate on: "agent message format", "agent communication schema", "agent-to-agent protocol", "A2A protocol", "MCP message format", "structured output for agents", "agent interop", "interchange format", "agent serialization", "task handoff format", "capability declaration". NOT for: what agents say to each other (use agent-conversation-protocols), orchestration topology (use multi-agent-coordination), building agent infrastructure (use agentic-infrastructure-2026).

日本語の概要は準備中です。原文の説明を表示しています。

Safety-case design for always-on agents with episodic memory. Covers data hygiene, privacy and security risk surfaces, cost controls, scope, user dependency concerns, retention, incident containment, and responsible deployment evidence. It identifies hazards and asks for named controls, tests, owners, and residual uncertainty; it does not provide legal, clinical, youth-safety, or jurisdictional determinations. Activate on: "agent safety", "always-on agent privacy", "agent cost control", "persistent agent risks", "AI companion safety", "agent data hygiene", "runaway agent costs", "parasocial AI risk", "/always-on-agent-safety". NOT for: architecture design (use always-on-agent-architecture), input design (use always-on-agent-inputs), application brainstorming (use always-on-agent-applications), healthcare compliance specifically (use hipaa-compliance).

日本語の概要は準備中です。原文の説明を表示しています。

Design or review a declared control-command profile and its verb/backend lifecycle matrix. Distinguish policy denial, unsupported capability, delivery acknowledgement, independently observed effect, and unknown outcome; bind authorization to principal, target, scope, current policy, expiry, and fencing epoch. NOT for claiming runtime correctness, proving an adapter from declarations, or approving a control-panel button without independent runtime evidence.

日本語の概要は準備中です。原文の説明を表示しています。

Expert-level idiomatic Rust API design — the patterns that make illegal states unrepresentable and abstractions zero-cost. Type-state programming (PhantomData state machines), newtype + sealed + extension traits, typestate builders, RAII guards & Drop ordering, the interior-mutability decision tree (Cell/RefCell/Mutex/RwLock/Atomic/OnceLock), enum-driven state machines, error architecture (thiserror vs anyhow), dyn vs generic dispatch & object safety, the impl Trait / GAT / RPITIT toolbox, and Deref-for-smart-pointers (and its abuse). Use when designing a Rust library's public API, encoding invariants in the type system, choosing a dispatch or error strategy, or reviewing Rust for idiom. NOT for borrow-checker firefighting / toolchain / test-runner workflow (use rust-development-workflow), NOT for pd-console GPUI rendering/layout/panes (use gpui-rust-console), NOT for app packaging/notarization (use rust-app-distribution).

日本語の概要は準備中です。原文の説明を表示しています。

Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl configuration, and 2026 legal landscape.

日本語の概要は準備中です。原文の説明を表示しています。

Delegate a read-only Coval evaluation, simulation, monitoring, product-how-to, or troubleshooting subtask to Sofia through the official Coval MCP consult_sofia tool. Use when the user needs Coval-specific FDE judgment, analysis of organization data, metric or test-set recommendations, or a diagnosis grounded in Coval runs and conversations.

日本語の概要は準備中です。原文の説明を表示しています。

End-to-end Coval accent testing workflow. Creates one persona per accent (each using a distinct accent voice and mirroring your Standard Customer behavior), launches one run per accent against the same voice agent + test set + metrics, polls for completion, builds a per-persona comparison table from the results, and creates the saved multi-run report (grouped by Persona) via the public API. Use when a user wants to follow the Testing Across Accents cookbook (https://docs.coval.dev/guides/testing-across-accents) without doing each step by hand.

日本語の概要は準備中です。原文の説明を表示しています。

Turn a large dataset (an existing oversized Coval test set, an export of past conversations, or a CSV/JSON of cases) into a small, high-signal Coval test set by removing duplicates, identifying unique scenarios, and selecting a representative, failure-weighted subset — then bulk-loading it with no row cap. Use when the user says "I have thousands of cases", "dedupe my test set", "my test set is too big", "turn this dataset into a test set", "pick representative scenarios", or "my CSV import only kept 10 / uploaded everything".

日本語の概要は準備中です。原文の説明を表示しています。

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

日本語の概要は準備中です。原文の説明を表示しています。

Analyze a Coval audio-quality testing report from runs across different voice, speaking-style, volume, interruption, and background-noise scenarios. Use when a user provides a Coval report URL, report export, run IDs, screenshots, or metric summary and wants evidence-backed next steps such as prompt changes, tool handling fixes, STT/TTS adjustments, trace setup, or expanded audio-scenario coverage.

日本語の概要は準備中です。原文の説明を表示しています。