403 件 ・ 関連度順
概要と使いどころ
Review an LLM agent design and find where it will be unreliable, expensive, or unsafe. Use when asked to review an agent architecture, critique a multi-step/tool-using agent, debug an agent that loops or goes off-task, or harden an agent before launch. Produces a structured review — task fit, control flow, tools, memory/context, failure handling, cost, and safety — with prioritised findings and fixes.
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。
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments. Identical to greploop, but triggers reviews by tagging @greptile-apps, which bypasses Greptile's file-count limit on huge PRs that the plain @greptile mention refuses to review. Use when the user wants to fully optimize a large PR/MR/CL against Greptile's code review standards.
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 Scenario output must be checked and improved rather than accepted first roll: iterating a generation until it matches the brief, fixing a batch that came back off-brief, retrying failed shots methodically, wiring an automated generate, review, revise loop, or deciding whether to re-prompt, swap references, inpaint, post-process, or change model. Keywords: refine, iterate, critique, review loop, QA, self-correction, verify, acceptance criteria, retry, drift.
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 automated codex⇄Claude debate to consensus — no round cap, no deadlock exit. Two explicit subcommands. `review` (also the bare/back-compat default) — codex (reviewer) critiques the current diff and a Claude subagent (author) fixes/disputes, looping until they agree. `answer` — Claude and codex each answer a freeform prompt in parallel, then cross-check until they agree, and a unified answer is returned. Use when the user types `/codex-debate`, asks to "have codex review this", "run the codex debate", "review this PR with codex", "argue this with codex until you agree", or passes a question to "have Claude and codex debate/answer until they agree".
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 writing Agent Relay or Ricky workflows that must loop review, fix, and validation with fresh agent context until independent signoff agents, typically Claude and Codex, both agree the work is comprehensively complete. Covers fresh-context iterations, repairable gates, dual reviewer verdict contracts, iteration-count reporting, PR signoff comments, and blocked-state handling.
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。
Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.
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。
Use when asked to take over, adopt, or babysit a GitHub pull request until it merges — read review feedback, fix it, resolve threads, dismiss unreasonable change requests, and merge once approved and green. Picks between driving the PR live in this session or handing it to the Looper daemon for unattended background runs, confirming with the user when unclear. Triggers on "take over this PR", "接管这个 PR", "持续修复 review 直到合并", or a Looper takeover bot comment. Works in any coding agent (Claude Code, Codex, opencode, Gemini, …) using gh + git.
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。
Build, modify, audit, repair, optimize, debug, and deploy agents with Agentforce Agent Script. TRIGGER when: user creates, reviews, or changes .agent files or aiAuthoringBundle metadata; asks to fix AgentScript, audit an existing agent, run an AgentScript health check, common-pitfall review, or baseline-versus-candidate repair loop; changes a response, action, subagent, route, state flow, or Agent Spec; previews, debugs, deploys, publishes, or tests agents; uses sf agent generate/preview/publish/test; or manages Agentforce MCP servers, tools, assets, or authentication. DO NOT TRIGGER when: Apex, Flow, Prompt Template, Experience Cloud, or general Salesforce CLI work is unrelated to Agent Script; or the primary input is a production session or trace ID rather than an agent artifact.
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 skill when a human needs to review a Deepline Play result and hand feedback, labels, or approval back to the agent for revision, evaluation, comparison, or bounded iteration. Triggers on “put this run in a Sheet,” “review these results,” “read my feedback,” “make this a standing rule,” “never regress on this case,” “compare these runs,” “keep improving,” or “add the revised run to the same spreadsheet.” Skip ordinary Play authoring or execution with no human review loop, generic spreadsheet work, and one-off CSV export.
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 a weekly operating review (Friday wrap or Monday plan) — review progress against the 90-day priorities, surface stalled open loops, and set next week's focus. This is the PERSONAL operating review; distinct from /audit (checks the kit's connections/freshness) and /level-up (finds one automation to build). Trigger on "/weekly", "weekly review", "weekly planning", "how did this week go", "plan my week".
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。
Assemble a finished piece from human-written fragments via an orchestrated two-loop pipeline - an assembly loop (assembler + cold reviewer) that sequences the fragments into a draft, then a polish loop (polisher + cold reviewer), then frequency analysis and a catalog-deslop pass with a regression gate. Two modes with opposite fidelity contracts - stitch mode preserves the author's exact wording, narrative mode preserves every idea but may rewrite freely. Use when the user says "mosaic", "assemble my fragments", "stitch these notes into a post", or provides a fragments file to turn into a finished piece. For writing from a topic with research, use article-factory; for prose from scratch, use the prose skill.
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。
[Workflow] Use when you need to run /workflow-review-changes repeatedly in an outer convergence loop until a complete whole-workflow run applies zero fixes — recursive re-review of a fixed scope (branch-diff + current changes) until a clean no-op pass.
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。
Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.
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 the card's Review Hero loop by hand — trigger a review, address its comments, rerun until clean, then merge. Use in an external tool (Claude Code, Cursor) where Workhorse's automated loop isn't running.
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。
Jevを使い、日本語中心・英語対応で文書、メール、メッセージ、提案書、技術資料、スライドの抽出テキストを多角的にレビューする。AIっぽさ、定型的な文体、冗長さ、直訳調、過剰敬語などを評価し、根拠引用と具体的な改善案を作成担当者へ返して改善ループを回すときに使う。Japanese-first bilingual editorial style review with Jev scores, source-grounded feedback and bounded revision loops; not an AI-authorship detector.
XP-style plan review that identifies gaps, hidden assumptions, and critical misses. Triggers on 'review the plan', 'check the plan', 'audit the plan'. Reviews plans for YAGNI violations, missing feedback loops, and over-engineering.
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。
Detects deeply nested loops with duplicated inline logic and recommends extracting into small, named functions. Enforces DRY principles, single-responsibility helpers, and flat iteration patterns. Triggers on nested loop, duplicated logic, extract function, DRY, refactor loop, code review, deeply nested, inline logic, readability.
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。
Operational guide for WordPress.org submission readiness of NV oOS standalone plugins (nvoos-docs-hub live at 0.5.3; nvoos-content-graph live at 1.0.10 in the re-submission loop; nvoos-design-system next in the pipeline — issue #6811). Covers the 18 wp.org guidelines, the Plugin Check (PCP) gate in CI and Docker, PCP finding triage, the reviewer-reply loop (findings taxonomy from the real 0.4.3 review, related-issue sweep checklist, reply-email template), packaging exclusion tri-sync, readme.txt standards, .wordpress-org listing assets, and the NV oOS Complete checkout-flow disclosure discipline (docs-hub 0.5.3, content-graph). Use when preparing a wp.org submission, responding to a reviewer email, fixing the plugin-check CI job, triaging PCP findings, or capturing listing screenshots.
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。
Build and run multi-agent content production teams on OpenClaw with single-repo architecture, symlink-based file sharing, role-specialized AGENTS.md, and automated review-fix-score loops. Use when: (1) Setting up a team of 3+ agents with writer/reviewer/scorer/fixer roles for content creation, (2) Creating a quality-controlled publishing pipeline, (3) Bootstrapping agent workspaces with symlinks and tool configs from scratch, (4) Running multi-round review→fix→score cycles until a quality threshold is met, (5) Debugging agent spawn permissions, tool-call loops, or symlink issues. Based on real production experience building a 6-agent content team (2026-03-30).
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。
Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable metrics, and scope constraints, then runs an autonomous loop of code changes, testing, measuring, and keeping/discarding results. Inspired by Karpathy's autoresearch. USE FOR: autonomous improvement, iterative optimization, experiment loop, auto research, performance tuning, automated experimentation, hill climbing, try things automatically, optimize code, run experiments, autonomous coding loop. DO NOT USE FOR: one-shot tasks, simple bug fixes, code review, or tasks without a measurable metric.
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。
機能追加やコード整理の後に、ビルド・型・lint・テスト・秘密情報の検索・差分を6段階で確認するスキル。合否と修正事項をまとめ、PRを作成できる状態か報告します。
Kubernetesの設定ファイル作成・レビューと障害調査を支援します。稼働確認、権限、リソース制限、自動スケールの設定例と調査コマンドを参照できます。
Full PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA → reviewer-readable English PR → verification loop (CI + Cubic, where Cubic is skipped only when its quota is exhausted) → merge by default → worktree cleanup. Decomposes one task into the smallest atomic, independently-mergeable PRs and builds the independent ones concurrently via one worktree per PR driven by parallel subagents or a team. Unbounded loop: any failing gate sends you back to fix-and-re-QA inside that PR's worktree. Use whenever implementation work needs to land as a PR. Triggers: 'create a PR', 'implement and PR', 'work on this and make a PR', 'implement issue', 'land this as a PR', 'split into atomic PRs', 'parallel PRs', 'work-with-pr', 'PR workflow', 'implement end to end', even when user just says 'implement X' if the context implies PR delivery.
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。