789 件 ・ 関連度順
概要と使いどころ
Use this agent when you need to review UniProt annotation rules (ARBA, UniRule) for quality, biological accuracy, and GO annotation appropriateness. This agent performs comprehensive analysis of rule condition sets, evaluates literature support, assesses taxonomic scope, and recommends curation actions.
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 agent when you need to systematically review existing GO annotations for a gene and make curation decisions based on literature evidence and functional analysis. This agent should be called after seeding the SPECIES/GENE/GENE-ai-review.yaml file, which seeds each annotation with `action: PENDING`; these should all be manually reviewed.
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。
Consult this skill BEFORE proposing a fix to any CLI gap or schema gap that touches evidence, trust magnitude, evidence types, evidence grades, the TM formula, or star-level promotion gates. Also read it whenever an issue mentions citations, stars, commits, contributors, views, reviewers, percentile, arxiv, github-stars-own, repo-own, social-signal, benchmark-result, peer-review, self-attestation, fusion-recipe, verifier-attestation, or proxy-containment — those are the 10 canonical evidence types and the raw inputs that feed their formulas. Also read it when asked whether a skill qualifies for a given star level (0★–6★): the Star Bar and promotion gates live in `META.md`, not in the TM methodology page. Reading both prevents proposing a calibration that satisfies the TM grade threshold but violates a Star Bar installability or link requirement.
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。
Phase 5 of the feature-pipeline suite. Use this after /fp-iterate prints the M4 stop hook confirming CI is green. Fetches origin/main, runs gaia dev diff to surface any skill-registry changes the PR introduced that are unrelated to its stated purpose (accidental drift), then prints the final pipeline summary including a CI churn report (via /ci-churn). Also invoke standalone whenever you want to audit whether a branch has unexpected registry drift — e.g. before merging any review/meta or cli/ branch, or when a reviewer asks "did this PR touch anything it shouldn't?". Triggers: "check for drift", "drift check", "final summary", "pipeline done", "wrap up the pipeline", "fp-drift", "Phase 5".
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。
Produce the rendered evidence a human-gated frontend PR owes its reviewer: capture each changed surface (plus the before state for anything modified, plus mobile width), then generate one self-contained local HTML page the founder can open and review without checking anything out. Use when a PR is gated by the "Frontend changes are HUMAN-GATED" section of CLAUDE.md, or when the user says "/design-gate", "screenshot evidence for this PR", "prep this for founder review", "build the design evidence page", "what does this look like before and after". The page comes from a template script, not hand-written markup. Output is session-local and never committed. Do NOT use for non-gated changes: typo/grammar/factual fixes in an unchanged block, dead link targets, alt/ARIA fixes with no visual change, cache-bust bumps, or refactors with no rendered diff.
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。
Walks a user through connecting the judge models this plugin can use — Codex, OpenCode, OpenRouter (or any compatible endpoint: 9router, z.ai, Moonshot), Gemini — and through picking models, including "research current models for me". Use for "multi setup", "set up multi", "configure judges/reviewers/ backends", "connect 9router", "change/pick models", "onboarding", or whenever a probe shows missing backends and the user needs to know what to do about it.
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 review by several models at once — Claude sub-agents, OpenAI Codex, and a cheap third reviewer via OpenCode — reconciled into one report. Reviews whatever is named: a diff, a branch, specific files, one function, a legacy module, a whole repo. Use for any review request, a second or third opinion, a cross-check before a PR, or "code-review", "multi", "consensus 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。
Revise an already accepted article, essay, paper, statement, or manuscript under strict minimal-change constraints while still satisfying reviewer comments, supervisor feedback, or requested edits. Use when the user asks for minimal edits, smallest necessary changes, preserve the current voice, keep the existing style, avoid broad rewriting, or implement requested revisions without unnecessary polishing.
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。
Prepare or open a GitHub or Gitea pull request with an explicit AI-authorship disclosure, change classification, reproducible reviewer verification steps, and optional Mermaid diagram. Use whenever the user asks to prepare, write, open, create, push, ship, or get changes ready for a PR or review. Unless the user explicitly asks for a draft-only result, create or reuse a dedicated branch, verify the change, commit scoped files, push the branch, and then create the PR with gh or tea.
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。
Before designing, training, or auditing ANY model that replicates human-annotated labels, audit the annotation protocol's INPUT — the exact document/evidence the human labelers consulted — and give the model that same input. Use when: (1) designing a classifier/LLM extractor whose target is a hand-coded label set, (2) a label-replication model shows low recall concentrated in a label subset and the diagnosis on offer is "the label's information is not in the features", (3) reviewers propose construct splits (e.g. "designation vs record-evident"), adjudication sittings, or per-domain stop rules to explain residual disagreement with gold, (4) validating an extraction pipeline against labels transcribed from a source document. Symptom of the underlying failure: elaborate theory accumulates to explain why gold is "partially unpredictable" when the model was simply never shown the document the annotators read.
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。
N-round adversarial review pipeline for empirical research output — the chain from data to LaTeX tables to a manuscript that cites them. A Claude drafter proposes minimal diffs, a deterministic mechanical battery gates every diff from a clean state with a regression gate, a Codex reviewer files check-backed critiques, and a blind judge panel decides residual disputes. Manual-invoke ONLY: trigger when the user explicitly runs /adversarial-empirical-review or names 'adversarial-empirical-review' / 'adversarial empirical review'. Do NOT auto-trigger on generic 'review my results', 'check my tables', or manuscript-editing requests. For prose-style refinement use style-emulation instead; this skill AUDITS WHETHER THE TABLES ARE CORRECT — that each number in the tables is what the analysis code computes, reproduces from the data, and is internally consistent. It is an empirical + code review: the manuscript is read only to resolve table numbering, and prose is not examined.
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。
Cybersecurity partner skill for acting as a practical security collaborator across architecture review, threat modeling, secure design, risk prioritization, defensive planning, vulnerability remediation, incident readiness, security roadmaps, and technical decision support. Use when the user wants an ongoing security advisor, reviewer, or second set of eyes.
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 source-aware mechanical-engineering judgment to research, analysis, coding, writing, teaching, research identity, and release work. Use for thermal-fluid systems, heat transfer, fluid mechanics, thermodynamics, HVAC, energy systems, turbomachinery, piping, multiphase flow, experiments, correlations, CFD, reduced-order models, AI/ML, uncertainty, engineering datasets, literature reviews, citations, manuscripts, reviewer revisions, Overleaf packages, figures, proposals, research software, reproducibility, public releases, engineering teaching materials, or a research-project logo and visual identity.
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。
Develop research proposals with solicitation alignment, reviewer-focused logic, evidence-bounded preliminary results, milestones, risks, and compelling figures. Use for federal, foundation, equipment, partnership, or internal research proposals.
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。
Invoke a Rubber Duck Reviewer subagent to independently critique plans and implementations before proceeding. Use when the agent is about to implement a non-trivial plan (multi-file changes, architectural decisions, security-sensitive logic, database schema changes), after completing a self-contained unit of work (module, endpoint, feature), when stuck or facing repeated failures (same test fails 2+ times, unexpected results), or when the agent wants independent validation of assumptions and design decisions. Triggers on any non-trivial implementation task where independent critique would catch blind spots before they become costly mistakes.
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。
Drive a failing GitHub Actions run to green in as few CI runs as possible, with a bounded fix-critique-commit-push-recheck loop that batches every evidenced fix into each push. Use when the user supplies a GitHub Actions run URL or run ID and wants the failure fixed, or asks to "make CI green", "fix the failing workflow/build/tests", "fix the red build", or to keep iterating on a branch or pull request until its checks pass. Pulls run results and failed-job logs through the gh CLI, and sends every fix plan to the rubber-duck reviewer before any code is touched.
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。
Systematic contract review assistance — clause extraction, risk flagging, and comparison — use when analyzing agreements.
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。
Structured code review discipline: correctness, design, readability, and security checks with actionable feedback. Use when reviewing diffs, PRs, or code snippets before merge or after writing.
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。
Professional code review craft: review strategy, feedback that lands, reviewer efficiency, and team review culture. Use when reviewing code or improving a team's review 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。
Building defensible grant budgets — personnel, equipment, indirect costs, and justifications reviewers believe.
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。
Writing biosketches that build reviewer confidence — personal statement, contributions, and honest positioning.
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。
Audit academic peer review operations -- reviewer matching algorithms, conflict of interest detection, turnaround time optimization, review quality scoring, and editorial workflow management..
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 a concrete technical proposal with evidence and tradeoffs when a decision needs design. No implementation or automatic reviewer.
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。
Quality gate for product specifications before stakeholder review. Use this skill when: - A spec draft is ready and you want to validate it before sending to Engineering, Design, and QA - You want to check a spec against your template's completeness rules - You need to catch vague language, missing sections, or gaps before review - You want a pass/fail scorecard with specific fix suggestions
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。