411 件 ・ 関連度順
概要と使いどころ
Review open PRs two ways - default is a per-PR deep review with severity-tagged findings, inline comments, and a verdict; --survey runs a risk-tiered triage digest of what's safe to merge first
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。
First-touch triage for external pull requests - verdict, label, and a welcoming comment within minutes of open
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。
First-touch review of newly opened PRs on [REPLACE: WATCHED_REPO] — verdict + welcoming comment + label
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。
Crypto market scanner and single-token analyst - movers scans top winners/losers/trending or on-chain runners with pump-risk flags; single-token produces a verdict-first deep report for one token.
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。
One-pass crypto read - tracked-protocol positions and health plus macro context, with regime take, DeFi verdict, biggest movers, yields, fees, breadth, Fear & Greed, and prediction markets.
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。
One-shot Base-token investigation - runs any subset of six onchain-security checks (rug-scan, contract-audit, deployer-trace, holder-concentration, honeypot, lp-lock) into one verdict. Keyless core.
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。
Three recap modes - default synthesizes agent health, community growth, and economic activity into a was-it-worth-it verdict; ops recaps what shipped and failed; push ranks push impact.
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。
Decides which named technologies a company actually runs on its website, verified against the live site. Triggers on "find companies using Shopify", "they're on HubSpot", "tech stack targeting", "technographics", "who uses Klaviyo", "companies running WordPress". Outputs a per-domain verdict (tech_confirmed plus the verified stack and its evidence); the copy-ready clause is OFF by default and runs only when the operator asks for one.
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。
Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable `npm install @metaharness/kernel@X.Y.Z` next step. Exits 2 if no .harness/manifest.json at path.
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。
MCP threat-model artifact for a scaffolded harness. Reports allowed/denied tools, dangerous permissions count, secrets reachability, network/shell/file-write grants, default-deny posture. Verdict: clean (exit 0) / medium (exit 1) / high (exit 2). The 'enterprise gold' artifact for PR + compliance 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。
Critique dimensions, severity framework, verdict decision matrix, and review output format for documentation assessment reviews
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。
Canonical AT completeness gate — research-anchored 7-category taxonomy (C1-C7) + 15-item mechanical checklist. Paradigm-neutral. Drives acceptance-designer reviewer verdict deterministically.
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。
Dung khi da co THIET KE va can duyet truoc khi dang — cham diem 4 nhom brand consistency, hierarchy va do doc, yeu to chuyen doi, phu hop nen tang, moi nhom 10 diem, kem feedback theo dang van de - tai sao - cach sua va verdict duyet / sua nhe / lam lai. Kich hoat khi user nhac 'review design', 'duyet thiet ke', 'feedback thiet ke', 'cham diem design', 'anh nay ok chua', 'nhin sao sao ma khong biet sai cho nao', 'check brand', 'approve creative'. Dung ca khi user chi gui anh va hoi 'xem giup'. Khong dung cho — duyet CHU nhu content brief va ads copy thi dung skill 62-marketing-review; do xem trang co ra don khong thi dung skill 68-cro-audit-trang.
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。
Dung khi leader phai DUYET output CHU cua team truoc khi trien khai — content brief co dung insight va dung pillar khong, CTA co ro khong; ads copy va creative co proof cho claim khong, dung tone khong, hook co nam trong 125 ky tu dau khong; verdict Approve / Revise / Redo kem feedback cu the. Kich hoat khi user nhac 'duyet brief', 'review ads copy', 'duyet content', 'check truoc khi chay', 'bai nay dang duoc chua', 'em viet the nay sep xem giup', 'duyet output team'. Khong dung cho — cham diem THIET KE va hinh anh thi dung skill 47-design-review; danh gia nang luc nguoi lam thi dung skill 65-team-performance-review; can nhieu goc nhin phan bien cho mot huong chien luoc thi dung skill 72-hoi-dong-marketing.
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 leader must review or approve TEXT-based team output before it ships — content briefs checked for angle, pillar, and CTA, ad copy and creative checked for substantiated claims, on-brand tone, a hook inside the first 125 characters, and platform policy, ending in an Approve, Revise, or Redo verdict with point-by-point feedback. Trigger on 'review this brief', 'approve the ad copy', 'check ads before launch', 'review team output', 'is this good enough to publish', 'my team keeps sending me drafts'. Not for — reviewing a visual design, see `47-design-review-global`; evaluating a person over a period, see `65-team-performance-review-global`; writing the copy yourself, see `05-ad-copy-global`.
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 finished DESIGN needs scoring and feedback — brand consistency, hierarchy plus readability plus accessibility, conversion elements, and platform fit, 10 points each, with per-issue feedback in issue, why, and how-to-fix form and a verdict of approve, minor fix, or redo. Trigger on 'design review', 'review this design', 'score this creative', 'is this design good', 'brand check on this banner', 'can we ship this or not'. Also use when the user just sends an image and asks for thoughts. Not for — reviewing copy and briefs, see `62-marketing-review-global`; writing the brief before production, see `42-image-brief-global`; the brand rules being checked against, see `46-brand-guideline-global`.
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。
Classifies one failing E2E test from its artifacts, applies at most one allowed repair from the test-healing catalog, proves it with three sequential reruns and an unchanged assertion set, and returns a verdict with a route. Use per failure inside test-loop; never for production code 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。
Measures whether an automation suite builds release confidence via feedback-loop length, suite reliability, release cadence, and production escape rate, and emits a release_confidence verdict. Use when judging suite value, ROI, or pre-release trust; not for writing or healing 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。
Review changed Elixir/Phoenix code read-only. Check requirements, cite evidence, deduplicate, and return a verdict.
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 changed Elixir/Phoenix code read-only. Check requirements, cite evidence, deduplicate findings, and return a severity-based verdict.
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 an A/B codex review experiment — holistic codex review vs 3 focused dimension passes (security, ecto, liveview) on the branch diff, classify findings, report a panel-value verdict. Use when the branch is fresh, before any codex review runs.
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 verifies suspected security bugs to eliminate false positives. Produces TRUE POSITIVE or FALSE POSITIVE verdicts with documented evidence for each bug.
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 arasi iletisim sablonlari. Standard handoff, QA verdict (PASS/FAIL), escalation, bug report, security finding ve status update formatlari.
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。
Final arbiter for Bug Hunter. Receives Hunter findings and Skeptic challenges, independently re-reads code, and delivers authoritative verdicts with CVSS scoring and proof-of-concept generation for security findings.
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。