2,694 件 ・ 関連度順
概要と使いどころ
Bring Mycelium into a project that already has code. Detects that the repo predates the framework, asks before touching anything, then reads the codebase to draft what it CAN establish (delivery, solution shape) and — the actual point — names what it cannot (purpose, strategy, real user evidence). The output is a discovery backlog with a head start, never a filled canvas.
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 CircleCI failures for a branch, PR, and scheduled nightly builds. Use when asked to check CI, a build, or nightly; report evidence and suggested fixes without opening a PR.
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。
Executes diagnostic investigation tasks to test debugging hypotheses. Runs tests, traces execution, checks git history, and reports evidence. (converted from 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。
Independent LLM judge evaluates task completion separately from the executing agent, catching false success claims by reviewing task goal, actions taken, final state, and evidence. Produces PASS/FAIL with confidence score and reasoning.
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。
Compress large context before reasoning to reduce token usage while preserving evidence. Use this whenever the user mentions huge files, long prompts, RAG payloads, prompt caching, expensive sessions, codebase context, chat history compaction, or wants the same answer quality with fewer 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。
LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations
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。
Two-step self-review at every task lifecycle phase. Step 1 (this skill) runs in-context to gather session signals — files read vs grepped, user pushback, build evidence, degradation signs. Step 2 launches a forked subagent for unbiased code/plan review with fresh eyes. Combined report classifies findings as hard blocks or soft warnings.
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。
Executes a QA specification (specs/qa/QA-<N>-<slug>.md) written by /plan-qa: drives every step with the plan's drivers, verifies each Expected line mechanically ([assert]) or by evidence-backed judgment against the plan's written criterion ([judge]), pauses at named operator handoffs, and writes the results artifact QA-RESULTS-<N>-<slug>.md. Use only when the user asks to run or execute a QA plan — never trigger automatically.
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 the open-pr e2e fixture through a real review in a fresh subagent, grade it against e2e/checklist.md with a second independent subagent, diagnose each failure to the prompt file that owns it, fix, and repeat until clean or the round budget runs out. Use when changing anything under src/ and you want evidence the review still behaves, not just green unit tests.
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。
Find the most valuable commercial insight and the monetization point closest to lawful revenue for a project, product, service, website, community, content account, open-source tool, or business idea. Use when a user asks how to monetize, who pays, why people do not buy, what to charge, whether to keep building, what to stop, what to do next, or asks to continue or deepen an earlier business analysis. Answer the user's actual question before asking for more information and carry the analysis forward without repeating it. When the buyer, purchased result, or delivery ability is unknown, do not select them from industry stereotypes; use explicit conditional candidates and an evidence-gathering next step. Not for investment advice, income forecasts, get-rich-quick schemes, or guaranteed results.
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。
Execute a frozen workflow contract and collect evidence by implementing only approved scope/files and checks. Use when PLAN_FROZEN=true and Execution Contract is complete, then hand off to 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。
Review execution against the frozen Execution Contract, produce Evidence/Gaps, and decide pass or unfreeze. Use after ac-execute or at milestone acceptance gates.
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。
Assess source material against the ASDLC Knowledge Base and produce an evidence-calibrated Content Review Report.
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 before EZ_math_model declares quality_audit, packaging, or final delivery complete, especially when pass/fail claims must be backed by files, commands, counts, or concrete 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。
Filter and summarise the cross-library KB audit log. Reports confidentiality events (attribution drops, synthesis aborts, dispatcher failures, no-evidence markers, cross-library promotions) over a date range, by event type, and by source handle.
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。
Query the project knowledge base. Wraps the research-librarian agent. The librarian reads the shelf-index, identifies the 2-4 most relevant library files for the question, deep-reads only those, and returns structured evidence with citations. Stateless — reads the index fresh on every query.
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。
This skill should be used to spawn specialized OpenAI Codex CLI subagents for code review, debugging, architecture analysis, security audits, refactoring, documentation, comparative evidence adjudication, and autonomous /goal runs. It adds each persona through process-local developer instructions while preserving the project's AGENTS.md chain, including during parallel launches. Supports GPT-6-Astra across low, medium, high, xhigh, max, and ultra reasoning with default or priority service tiers, plus GPT-5.6 and GPT-5.5 models. Triggers on 'delegate to Codex', 'Codex Astra', 'Astra subagent', 'Codex subagent', 'code review agent', 'security audit', 'refactor with Codex', 'goal run', 'autonomous goal', 'have Codex weigh this'.
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 credential-free public website monitoring evidence from server access logs, HTTP fetches, robots/llms/sitemap checks, and exported summaries while protecting raw IP and private query data. Use this skill when the user asks whether crawlers or AI bots reached a site, whether public SEO/LLM discovery files respond, or how to separate observed facts from unknown Search Console, rank, analytics, or citation claims.
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。
Validate proposed or existing backlinks for relevance, editorial legitimacy, link attributes, spam/toxicity risk, platform compliance, anchor quality, target-page fit, and monitoring evidence. Use this skill when the user asks whether an external link opportunity or placed backlink is safe and useful, and reject toxic, irrelevant, paid-undisclosed, fake, or spam placements.
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。
Coordinate SEO, LLM-readable site architecture, UX, content, monitoring, security, and external authority work as a task-plan-driven sequence. Use this skill when the user asks to plan, execute, validate, or route multi-skill website growth work; asks what to do next across semantic core, URL structure, internal linking, schema, llms.txt, UX journeys, analytics, citation monitoring, or white-hat link placement; or wants a central architect that preserves evidence, alarms, handoffs, and tests.
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。
Validate SEO and LLM-readability claims against live HTML, local fixtures, and generated artifacts. Use this skill when the user asks to prove whether title, meta description, canonical, hreflang, JSON-LD, NewsArticle.image, OpenGraph, Twitter cards, RSS autodiscovery, robots.txt, llms.txt, sitemap, news-sitemap, crawler access, or performance evidence is actually present, and when subjective audits must become timestamped pass/fail reports.
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。
Agent Brain /brain-research: the decision depends on external evidence or unfamiliar domain context.
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 sources need to be converted into a claim ledger with confidence levels.
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 behavior needs concrete proof before review, merge, or shipment.
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。