「graded」の検索結果

Peer review checklist and quality standards for intelligence products, plus schema validation for graded evidence items and claim tables from /quality-of-information-check and /claim-extraction. Rejects outputs that break the evidence schema or the grading caps. Loaded by the quality-reviewer agent.

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。

Use when evidence needs grading before anyone reasons from it — the user asks "how reliable is this?", "grade this source", "check this report", "can I trust this article?", "is this corroborated?", or hands over a URL, a pasted report or a Liberty91 event ahead of an ACH or assessment. The Quality of Information Check from the CIA Tradecraft Primer, adapted for vendor and press CTI reporting. Resolves each document to its originating source, splits it into claims, and grades every claim on two written elements, access level (how the source knows) and claim support (what backs the statement), with a stated rationale, using a fixed rubric with hard caps. The grade is not an Admiralty rating. Five outlets citing one vendor report count as one source; anything that cannot be traced to a primary is capped, not guessed. Returns a graded claim table, gaps, a deception screen and JSON. /ach, /threat-assessment and /writing-assessments run it first by default.

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。

Use when a report or article needs to be split into individual claims before it is graded, cited or used as evidence — the user asks "what does this report actually claim?", "split this into claims", "separate the facts from the judgements", or another skill needs a claim list. Turns one document into five to twelve atomic claims, each typed (observation, attribution, assessment, actor claim, victim disclosure) and anchored to the verbatim sentence it rests on, so every extraction can be checked against the source. Preserves the source's own hedging. Does not grade. Invoked by /quality-of-information-check; its output feeds /ach, /key-assumptions-check, /intelligence-writing, /writing-assessments and /threat-actor-profiling.

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。

Testing and evaluation framework for LLM prompts and applications -- promptfooconfig.yaml, assertions, model-graded evals, red teaming, CI/CD integration, custom providers, and comparative evaluation

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。

Use when a task needs the judgment of a Diagnostic Medical Sonographer — deciding whether a duplex, compression, or graded-compression ultrasound study is diagnostic versus technically limited, choosing when to interrupt a scanning protocol to escalate a real-time critical finding, setting scan technique and ALARA (TI/MI) parameters for a given exam type, or drafting the technical worksheet and preliminary findings a physician will interpret and sign.

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。

Use when a task needs the judgment of an Agricultural Grader/Sorter — calling a defect grade on a moving packing line, deciding whether a lot with a marginal QC sample gets accepted, hand re-sorted, downgraded, or held, choosing where to station a human grader relative to an optical sorter, or diagnosing why a lot's cull rate or customer chargebacks spiked.

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。

Run a structured incident response. Use when the user says "we have an incident", "production is down", "service is degraded", "on-call response", "p0 incident", "something is broken in prod", "help me manage this incident", "incident commander", or there is an active production issue requiring coordinated response - even if they don't explicitly say "incident response".

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。

Use when creating or managing picklist fields: choosing between Global Value Sets and object-local picklists, configuring controlling and dependent field relationships, managing picklist values, and replacing values in existing data records. NOT for why the API or an integration ignores a dependency matrix - use admin/field-dependency-and-controlling. NOT for cleaning up degraded, unrestricted or orphaned picklist values - use admin/picklist-field-integrity-issues. NOT for record type picklist filtering - use admin/record-types-and-page-layouts. Keywords: GlobalValueSet, StandardValueSet, __gvs suffix, customValue, valueSetName, valueSetDefinition, restricted picklist, GlobalValueSetTranslation, OpportunityStage, CaseStatus.

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。

Use when picklist data quality has degraded: unrestricted picklists accepting garbage API values, dependent picklist relationships bypassed by integrations, record type picklist value mappings drifting out of sync, or orphaned values appearing in reports. NOT for the value-deactivation runbook or the API-name-vs-label trap — use admin/picklist-data-integrity. NOT for initial picklist creation or Global Value Set design — use admin/picklist-and-value-sets. NOT for record type configuration itself — use admin/record-types-and-page-layouts.

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。

Qualitative quality review of game design documents — answers "is this design good, and does it follow best practices?" — across all three GDD axes: systems, flows, and content types. Fans out adversarial lenses (completeness, clarity, pillar alignment, systems-math, fantasy-delivery, feasibility, scope) plus domain lenses that check it against the game-design rules, each prompted to find problems rather than validate; produces a severity-graded verdict and a two-bucket report (apply-ready fixes vs research), handed to /unikit-gd-apply or /unikit-gd-explore in one move. Scope is inferred: a named system, flow, or content type reviews that document; "all" runs a cross-document review. Use when the user wants a critique, quality judgment, or rules check of the design, e.g. "review the combat GDD", "review the onboarding flow". This is the subjective quality pass — for a mechanical consistency check (numbers, terms, IDs, references matching the registry) use /unikit-gd-verify.

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。

Loads, lists, composes, or validates graded evaluation rubrics: PASS/WARN/FAIL grading with weighted criteria and balanced anchor examples for evaluator-style review.

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。

Use when a repo has its own generators, scripts or turbo tasks and an agent reaches for a generic skill instead — derive a Playbook context (ADR-244) from the real config, graded by the tree.

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。

Author or expand browser-agent benchmark tasks in data/real_world_bench.json (Odysseys schema, per-rubric graded). Use when creating, adding, or expanding real-world browser tasks, writing rubrics, or picking bot-friendly sites — every task MUST be verified runnable through ego-browser before it is written.

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。

Knowledge base from NASA System Safety Handbook Volume 2 (NASA/SP-2014-612). Use for risk-informed safety cases (RISC), integrated safety analysis (ISA), adequate safety concepts, safety objectives and requirements, acquirer/provider roles, graded safety analysis, claims-evidence-argument structure, SSMP development, and RISC evaluation. Does not cover nuclear or chemical safety domains, occupational health regulations, or NASA-specific programmatic requirements beyond system safety.

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。

不安症に対する段階的曝露療法（エクスポージャー）：恐怖階層表、SUDs尺度、曝露計画とガイダンス。心理教育のみ、実施は不可。

Exposición graduada para trastornos de ansiedad: Jerarquía de miedo, escala SUDs, planificación y orientación de la exposición. Solo psicoeducación, no ejecución.

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。

针对焦虑症的阶梯式暴露疗法：恐惧阶梯、SUDs 主观痛苦评分、暴露计划与辅导。仅限心理教育，不予自行实施。

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。

Градуированная экспозиция при тревожных расстройствах: Иерархия страхов, шкала SUDs, планирование и сопровождение экспозиции. Только психообразование, без самостоятельного проведения.

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。

Synthesises retrospective notes, closing reports and post-implementation reviews into a DRAFT lessons-learned document: themed lessons with source counts, anonymised quoted evidence graded by strength, repeats against a prior register, contradictions, and a recommended owner with a stated basis for each follow-up. Names no individual or vendor and assigns no blame. Use when the user asks to "compile the lessons learned", "write up the retrospective", "theme the close-out notes", "what did we learn across these projects" or "refresh the lessons register". Do not use for a single sprint's review, use sprint-review-summary instead; for an incident investigation, use incident-postmortem-drafter; for customer feedback themes, use customer-feedback-theme-synthesis. Drafts for human review; never approves, authorises or signs off.

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。

Builds one DRAFT message house for a product, service, programme or initiative from the source material the user provides: an umbrella statement, two to four pillars and graded proof points under each, with every proof point that lacks a source flagged, a claim sensitivity table, an audience coverage check and open questions. Use when the user asks to "build a message house", "write our messaging framework", "what are the key messages for this launch", "turn this research into messaging pillars" or "test our current messaging against the evidence". Do not use for a campaign one-pager, use campaign-brief-builder instead; to check whether a written document's claims are substantiated, use claims-evidence-map. Drafts for human review; never approves, authorises or signs off.

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。

Triages a batch of customer support tickets (helpdesk export, shared mailbox, chat transcripts, web forms) into one row per ticket with category, urgency graded on the evidence in the ticket, suggested next action and owner, plus a DRAFT customer reply for every ticket that needs one, returned as one Markdown pack. Use when the user asks to "triage these tickets", "sort the support queue", "what needs an answer first", "categorise this backlog", "draft replies for these tickets" or "build today's queue review". Do not use for internal requests from colleagues, use request-intake-triage instead; for one long thread that needs handing over, use escalation-summary; for a personal mailbox, use inbox-triage. Drafts for human review; never approves, authorises or signs off.

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。

Use this skill whenever the user asks to inspect, audit, review, assess, or evaluate a codebase/project for maintainability, extensibility, architecture, reliability, security, testing, engineering quality, or AI-agent/prompt/tooling risks. Also use this when invoked by `/inspect`. It performs a read-only, evidence-backed, multi-agent project inspection with complete file coverage, per-dimension scoring, blunt technical findings, and explicit degraded-mode disclosure.

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 graded `trial_result` JSONL outputs from the eval pipeline, including reliability and custom slicing.

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。

Build AI-focused SRE incident response practices for LLM outages, degraded quality, runaway cost events, and safety regressions.

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。