790 件 ・ 関連度順
概要と使いどころ
Reviewer role. Opens rendered HTML, inspects every slide visually, fixes problems in custom.css or slides.html and rebuilds through build-html.sh. Use whenever the user says "review", "QA", "check slides", "inspect", "audit", "proofread", or wants feedback on a rendered deck.
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 after receiving WebGPT or another LLM review on a Formax todo and before sending the todo back for another pass. Produce a concise handoff response that says what we adopted, what we reject or question, and what the reviewer should specifically re-evaluate in `docs/todolist.md`.
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 the working-tree changes (vs main) for correctness, concurrency, architecture, testing, and API/doc issues — following .github/CODE_REVIEW.md — and return a severity-graded report. Scales the machinery to the diff size: a single code-reviewer agent for a small change, or a fan-out-and-verify Workflow for a large/multi-unit one. Produces findings; it does not apply fixes (the caller does).
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 to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a 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。
Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.
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 for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.
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。
Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.
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。
Perform thorough code reviews with actionable, prioritized feedback. Use when a user asks to review code, check code quality, find bugs, review a pull request, audit code for issues, or get feedback on implementation. Covers correctness, security, performance, readability, and best practices across languages.
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 specialist for quality standards, design patterns, security review, and constructive feedbackUse when "code review, pull request, PR review, code quality, refactor, technical debt, design pattern, best practice, code-review, quality, patterns, security, refactoring, best-practices, pull-request, review, ml-memory" mentioned.
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。
Adversarial senior-engineer review for agent-generated plans, designs, and architectures. Treats the current output as junior work, constructs a senior reviewer whose domain expertise comes from live codebase research plus web research of current best practices, diagnoses altitude failures (too vague or too granular), then rewrites the plan into a scoped, state-of-the-art version. Use when the user says "junior to senior", "senior review", "review this like a staff engineer", when a plan feels hand-wavy or lost in details, or before committing to any agent-written plan.
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 whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan 8-type / 3-category leakage taxonomy; the illegitimate-proxy / sampling-bias / pretraining-contamination subtypes hand off as needs_external_check, naming but NEVER running Oren-2023 exchangeability / Shi-2023 Min-K% / Golchin-2023 Time-Travel / BIG-bench canary); a load-bearing LLM judge is conflicted (same model/family as a compared system) or unvalidated (no human-agreement, no bias control) (HP-JUDGE-VALIDITY); a declared condition/metric is dropped or switched to favor the method, or 'best' is chosen with no held-out set (HP-SELECTIVE-REPORTING). Verdict-bearing at L0/L1 from the DESCRIBED protocol — NOT repo-gated like experiment-forensics; L2 only CONFIRMS against split/preprocessing/result files. A fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per pass) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Leakage and under-reporting are usually HONEST methodological errors — every finding describes a discrepancy to CHECK, never an accusation. An LLM generating GROUND-TRUTH labels is HP-FAKE-GT (experiment-forensics) — routed there, not here. Emits eval-design-forensics.findings.json; computes NO verdict. Detect-only. Triggers: "eval design audit", "evaluation validity", "train/test leakage", "data leakage", "is the score measuring generalization", "LLM judge bias", "is the judge validated", "selective reporting", "cherry-picked results", "评估设计审计", "评测有效性", "数据泄漏", "训练测试集泄漏", "裁判模型有没有验证", "选择性报告".
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。
Audit whether a paper's baseline comparisons are COMPLETE, FAIR, and SIGNIFICANT: a required recent SOTA baseline is missing while 'best/SOTA' is claimed (HP-MISSING-BASELINE); a baseline is undertuned / given less compute-tuning-data, run at a mismatched config, or the equal-budget ablation-as-baseline is absent (HP-WEAK-BASELINE); 'outperforms' is asserted over overlapping error bars or with no variance/seeds (HP-SIG-OVERLAP); and a cross-row 'improves over baseline by X%' is arithmetically wrong (HP-DELTA-ERROR, cross-row form only). A versioned per-domain baseline profile + a live leaderboard/recency search are assembled by the EXECUTOR as structured facts; a fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per dimension) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Works at L0 (stated comparisons) and deepens at L2 (configs/result files). A completeness question it cannot settle internally becomes needs_external_check, never a guessed missing baseline. Emits baseline-comparison-audit.findings.json; computes NO verdict. Detect-only. Triggers: "baseline audit", "missing baselines", "is the comparison fair", "weak baseline", "baseline 误报", "SOTA earned?".
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。
Synthesize the single strongest EVIDENCE-BOUND reviewer case to reject a paper, built ONLY from the evidence ledger (claims.json) + the other auditors' confirmed findings — never free-floating LLM critique. Two fresh cross-model codex threads: an attack writes the ~200-word rejection paragraph (every accusation tagged to an existing claim_id/finding_id), a defense decomposes it and rules each point against the anchored evidence. MEMO-ONLY: emits adversarial-case-builder.memo.md (fed to the adjudicator via --memo) and carries NO verdict weight — tools/adjudicate_findings.py lists it in ZERO_WEIGHT_SKILLS and caps it at info. Honest-null allowed (the paper may survive). Run LAST. Detect-only. Adapted from ARIS kill-argument. Triggers: "adversarial case", "strongest objection", "rejection memo", "kill argument", "最强拒稿点".
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。
Flagship intra-paper self-consistency forensics: does the paper contradict ITSELF across abstract/intro/tables/body/appendix, and does the method DESCRIBED match the method EVALUATED? Needs no external ground truth — works PDF-only (L0). Runs a deterministic arithmetic pass + a fresh cross-model semantic pass, every finding span-anchored to the evidence ledger (claims.json), reviewer≠adjudicator. Emits consistency-audit.findings.json; NEVER computes the verdict. Triggers: "consistency audit", "check the paper against itself", "self-consistency", "内部自洽".
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。
Citation-integrity forensics: is every reference real, correctly attributed, and used in a context the cited work actually supports? Catches hallucinated references (no paper at the claimed arXiv id/DOI/venue, fabricated authors/year), metadata drift (wrong year/venue/version), and wrong-context citations (a real paper cited for a claim it never makes — or argues against). A hot zone for machine-generated papers. Decidable at L0 (text + canonical sources). Span-anchored to the evidence ledger (claims.json); the executor gathers canonical facts (DBLP / arXiv / DOI), then one FRESH cross-model thread per cited key proposes findings; reviewer != adjudicator. Emits citation-forensics.findings.json; NEVER computes the verdict. Triggers: "citation forensics", "check the references", "hallucinated citations", "wrong-context citation", "verify references", "引用核对".
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。
Checkable-ish surface presentation signals a reviewer notices first — duplicate/near-identical tables, leftover pipeline/template strings, too-few or LLM-looking figures, and page-padding. AUXILIARY ONLY and weak by design: a deterministic pass (tools/check_presentation.py — dup-table + pipeline-artifact) plus a fresh cross-model GROSS-cases-only semantic pass (thin-float, LLM-figure, page-padding), every above-info finding span-anchored to the evidence ledger (claims.json). The adjudicator CAPS everything at minor (SURFACE_ONLY_SKILLS + SURFACE_PATTERNS) — these contribute at most SOFT_FLAGS, never a HARD verdict — default false_positive_risk:high. NOTE: the pure AI writing-STYLE impressions (AI-flavor prose, defensive 'not-X-but-Y' hedging, narrative-arc, jargon-stuffing, invented codenames) MOVED to the zero-verdict-weight AIS track — for those use skills/ai-style-impressions, NOT this. Emits presentation-signals.findings.json; NEVER computes the verdict. Triggers: "presentation signals", "surface check", "duplicate tables", "排版信号".
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 infrastructure-as-code changes for safety and correctness. Use when a mid-level developer needs a second look on IaC.
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 a pull request for correctness, regressions, and missing tests. Use when a mid-level developer needs structured review 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。
Review database migrations for safety and rollback. Use when a mid-level developer needs validation of schema 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。
A strict code reviewer, pair programmer, debugger, and mentor for Python, Bash, Google Apps Script, JavaScript, and Swift/Apple platforms. Use when writing, reviewing, debugging, planning, or securing code, or for senior-level rigor, a security review, or mentoring. Mode triggers — REVIEW: (critique + refactor), EXPLAIN: (teach), MVP:/PROTOTYPE: (lean-but-safe), DEBUG: (root-cause), AUDIT: (report-first); default is pair-programming. Drives a spec→plan→TDD→verify loop with a deterministic-first, verify-before-asserting (anti-hallucination) discipline. Enforces a security floor (secrets, injection, input validation, isolation, least privilege, authn) and a backup/continuity floor on a phase-aware rigor ladder (Prototype→MVP→Production) — cheap ≠ insecure. Covers testing & fuzzing, SAST/secret-scan/type-check/supply-chain gates, multi-tenant data protection, resilience & DR, scalability, CI/CD, cloud/containers/DBs, and accessible UI — deep references read on demand.
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。
Fans Claude work out over the Anthropic API from surfaces with no native subagents, chiefly claude.ai chat and projects, with parallel calls with a shared cached context, streaming, long-lived conversation threads with cached history, and named agent pools; also delegates to Gemini through the Cloudflare AI Gateway on any surface. Use for multi-perspective analysis, a panel of reviewers, or task decomposition from claude.ai, or for Python code that calls several Claude instances concurrently over the API.
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 a diff with the reviewer fleet, funneled to one triaged verdict. Targets the current working diff, a path, or an inbound GitHub 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。
Periodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint 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 when receiving code review feedback (especially if unclear or technically questionable), when completing tasks or major features requiring review before proceeding, or before making any completion/success claims. Covers three practices - receiving feedback with technical rigor over performative agreement, requesting reviews via code-reviewer subagent, and verification gates requiring evidence before any status claims. Essential for subagent-driven development, pull requests, and preventing false completion 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。