「evidence」の検索結果

QA a change by driving the running dev app like a real QA engineer - start the server and a real browser session, write a checklist from the agreed requirements and the diff, execute every item with evidence, then go looking for anything that looks off even where the diff did not touch. Reports findings by severity and separates regressions from pre-existing problems. Use after a change is implemented and the gates pass, when the user asks to "QA this", "test it in the app", or "check it actually works".

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 about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

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。

Complete MCP engineering work on the live path: build or repair servers and Apps, debug stdio or Streamable HTTP, migrate protocol/SDK/transport versions, reconcile source with package and activated runtime, inspect capability/effect authorization, and verify named-host claims without promoting weaker evidence. Use for real Model Context Protocol implementation, review, migration, runtime, or host-integration tasks. Do not use for ordinary non-MCP APIs, generic frontend work, or incidental product copy.

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 reviewing active Loop Factory specs against the working tree, checking verification evidence, deciding ACCEPTED or CHANGES_REQUESTED, and archiving accepted specs.

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。

Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per theme, APA 7th citations, evidence hierarchy, and 3 user checkpoints. Self-contained using native OpenClaw tools (web_search, web_fetch, sessions_spawn). Use for literature reviews, competitive intelligence, or any research requiring academic rigor and reproducibility.

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。

Code auditor that grades software projects and the agents/developers who built them. Produces structured JSON + Markdown reports with a standardized rubric. Evaluates architecture, correctness, testing, authorship cohesiveness, ghost code, and more. Optionally ingests tmux session logs for process evidence and interrogates agents about specific problems found. Use when asked to "audit", "grade", "evaluate", "review code quality", "rate this project", "score the agents", or "assess the codebase". Especially useful after Marcus multi-agent experiments to grade agent output and track quality over time.

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。

Diagnose a dygo Business App that does not validate, boot, route, render, authorize, migrate, or execute background work correctly. Use for evidence-first investigation rather than feature implementation.

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。

Diagnose Azure application and infrastructure issues with a structured, evidence-based workflow. Use this skill when users ask to troubleshoot outages, latency, failures, configuration drift, or anomalies. Root cause analysis using logs, metrics, traces, and dependency mapping.

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。

Product Research / 产品研究编译器：当用户要围绕一个产品问题做系统调研、竞品证据、替代方案、行业信号、 用户与市场研究、最佳实践提炼、产品候选池、本地 HTML 研究看板、可视化研究报告或跨职能 Dashboard 时使用。 当用户只有大白话、模糊方向、业务愿望或 Roadmap/PRD 前置材料想法，需要先转成清晰研究目标、研究问题和输出要求时也使用。 适合把研究转成 Research Project、学习报告、证据矩阵、PM 决策看板、候选池、模板、实践任务、业务判断、商业化输入或高门槛应用研究前置。适合“系统研究一个主题” “整理到 Obsidian”“做深度专题”“研究行业最佳实践”“概念解读”“概念源流”“PM 技术评审提问脚本” “行业演进看板”“这个主题对我的产品决策有什么用”“让我系统学会并输出 learning report HTML”。不适合创建 Skill、评审 SKILL.md、普通即时搜索或一次性摘要。 当用户已经要在明确候选项中选一个、需要最终推荐和排除理由时，应使用 decision-research。 当 decision-research 或 grill-me 返回一个可研究、可关闭的精确证据 gap 时，也使用本 Skill 只补 Evidence Delta。

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。

Prove — or honestly fail to prove — a specific technical claim: "the fix works", "it's deployed", "the service is running", "the site is done", "there are no vulnerabilities". Atomizes the claim, picks the shortest decisive signal on the evidence ladder, and returns a verdict from a fixed vocabulary (pass / partial / fail / skip) with an explicit coverage boundary. NOT code review, NOT a fix, NOT orchestration — only "what is proven, and what we merely hope". Triggers — "prove it works", "is it really done?", "are you sure?", "we deployed — is it live?", "verify that", "did we actually check?".

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 implementation to Codex, grok, or cursor-agent, then review the diff, send it back to iterate, gate on the full test suite, and ship it as a PR. Use this whenever the user wants Codex, the grok 后端, or cursor-agent to write code, mentions handing off / delegating implementation to one of those backends, asks to work through a plan or spec unit-by-unit with an implementation backend doing the coding, or wants a review-and-merge loop wrapped around delegated output — and also when resuming such a loop ("keep going", "next unit", "继续下一个"). It encodes constraints that are expensive to rediscover: the implementer runs in the real environment behind backend-specific git and publication boundaries, must not be pointed at a full test suite by default, and its self-report is a claim rather than evidence. This loop expects an approved plan or an equivalently precise spec; settle an unsolved high-level goal into a plan first, using the engineering-mode skill when it is installed.

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 implementation work to a dedicated implementer subagent, then review its diff, send it back to iterate, gate on the full test suite, and ship it as a PR. Use this whenever the user wants a separate model to write code, mentions handing off / delegating implementation, asks to work through a plan or spec unit-by-unit with a subagent doing the coding, or wants a review-and-merge loop wrapped around delegated output — and also when resuming such a loop ("keep going", "next unit", "继续下一个"). It encodes constraints that are expensive to rediscover: the implementer self-reports success, must not run the full test suite by default, must not touch git, and its report is a claim rather than evidence. Cursor port of implementation-loop. This loop expects an approved plan or an equivalently precise spec; settle an unsolved high-level goal into a plan first, using the cursor-engineering-mode skill (it ships in this same plugin).

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。

Diagnose and repair a failed GEODE smoke workflow within the requested acceptance criteria. Preserve failed evidence, verify the shared root cause, and apply merge, rebuild, or live rerun stages only when authorized.

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。

GEODE evidence-first development workflow. Use for feature work, provider/model changes, GUI/computer-use work, PDF/document ingestion, observability/schema/event/state changes, verification planning, GitFlow merge prep, and requests to "follow the workflow" or "scaffold the process".

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。

Evidence-first multi-step research with bounded parallel collection, contradiction checks, and cited synthesis.

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。

Add or update a GEODE model or provider from current primary documentation and repository call-site evidence. Use for model IDs, context limits, pricing, reasoning controls, provider routes, capability gates, or fallback changes.

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。

Discover and run tests that provide meaningful evidence for a code change. Use after implementation, before handoff or commit, or when the user asks to validate behavior.

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。

Establish concise, cross-agent project instructions from repository evidence. Use when initializing or repairing AGENTS.md, CLAUDE.md, related discovery links, or project-specific agent guidance.

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。

案卷阅卷与证据分析 Skill。支持两种输入模式：(a) 仅证据材料 — OCR 后快速给出结论，逐条标注源头，自动标记矛盾点；(b) 起诉状 + 证据材料 — 根据起诉状确定的法律关系分析证据充分性，逐条溯源，标注证据间矛盾。自动提取时间轴并生成 HTML 可视化，最终输出结构化阅卷报告。

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。

Transforms police body camera transcripts into structured 10-section legal summaries with timestamp-cited verbatim statements, constitutional issue spotting, evidence inventory, and probable cause articulation. Maintains strict neutrality for all parties. Use when analyzing BWC footage for discovery, pre-trial prep, or trial. Trigger: body camera, BWC, body worn camera, officer footage, use of force review, incident summary.

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。

Drafts appellee response briefs for federal and state appellate courts, exploiting standards of review and record evidence to defend trial court decisions. Trigger when the user needs to respond to an appellant's opening brief or defend a favorable lower court ruling on appeal.

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。

China legal triage assistant. Input a contract, labor dispute facts, lawsuit-cost question, or draft legal document need; output risk checklist, cost estimate, evidence outline, or editable document skeleton. Boundary: preliminary legal information only, not a lawyer and not formal legal advice.

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。

Systematically QA-tests a web app and fixes bugs: test, then iteratively fix, re-verify, commit each fix. Tiers: Quick, Standard, Exhaustive. Produces before/after health scores and fix 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。

Read-first Figma gateway via Figma MCP: analyze designs, implement 1-3 screens, extract tokens, produce Evidence Packet. Advanced ops gated on explicit intent. Use for 'figma', 'design tokens'.

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。