「judge」の検索結果

Adversarial deliberation process for making decisions. Spawns advocate agents for each option who argue their cases before a judge (you) who renders 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。

Comment-archaeology sweep - find work items hiding in TODO/FIXME/for-now comments and plan-doc ledgers, judge them, file issues, queue trivial fixes. Good idle-loop activity.

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 an independent visual language and turn the human-chosen direction into a production-ready graphic, brand, campaign, publication, web, or product system. Use when originality and differentiation matter enough to escape generic AI and Big Tech aesthetics. Guides a minimum-evidence start, ten isolated typography-led HTML design directions made only from type, color, and space, visual-first human judgement, explicit commitment, and concrete Round 2 production. Do not use for routine UI fixes, small components, or applying an existing design system.

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。

Resolve CodeRabbit review feedback on a GitHub pull request. Collects every open CodeRabbit finding (inline threads, plus the nitpick and outside-diff findings packed into review bodies), judges and fixes each one against the real code with subagents, unifies fixes that share a pattern, commits locally, asks before pushing, then shows every reply draft linked to its finding and posts only on approval. Runs only on top-tier models. Use on "resolve the CodeRabbit feedback", "address coderabbit comments", "answer the rabbit", "fix what CodeRabbit flagged on

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。

Evaluate Agent Skill design quality against official specifications and best practices. Use when reviewing, auditing, or improving SKILL.md files and skill packages. Provides multi-dimensional scoring and actionable improvement 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。

Create and maintain agent skills with concise trigger metadata, judgement-aware guidance, progressive disclosure, and tested interfaces. Use when adding, refactoring, reviewing, or troubleshooting skills and their bundled scripts or references.

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。

Reflect subskill for simmer. Records iteration results in trajectory table, tracks best candidate, handles regression rollback, and passes ASI forward to the next round. Supports both single-file and workspace modes. Do not invoke directly — called by simmer orchestrator after each judge round.

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。

Generator subskill for simmer. Produces an improved version of the artifact based on the judge's ASI feedback. Handles both single-file and workspace targets. Do not invoke directly — dispatched as a subagent by the simmer orchestrator.

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。

Multi-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are evaluated by metric or LLM judge, and the best branch is merged. Use when: user wants multiple approaches tried in parallel — code optimization, content variation, research exploration, or any task that benefits from parallel competition. Requires: a git repo.

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 when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise comparison, position bias, evaluation pipelines, or automated quality assessment.

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。

反復レビュー・ループ(codex-review-loop・fable-review-loop・opus-review-loop)が共有する判断ロジックの正本。起動可否ゲート・レビュアーの正体に依存しない大前提・常設観点・レビュー依頼に含める内容と含めてはならない内容・照合仕分け・終了判定・報告を定義する。内部専用でユーザーが直接使うものではない。

Splits scarce time, budget or traffic across competing products, channels, campaigns or variants by treating them as a multi-armed bandit - Thompson sampling over beta posteriors, with optimism for anything not yet tried enough to judge. Use when deciding what to work on next, how to divide a marketing budget, which product to prioritise, whether to kill something that is underperforming, or when picking a winner among test variants.

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。

Shared in-workflow quality gates for code/PR skills — the gate model, trust tiers, and the three primitives (evidence-before-done, independent judge, anti-gaming). DO NOT TRIGGER directly — referenced by consumer skills via relative 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。

Read-only reviewer for agent-flow. Judges one diff against the acceptance criteria, AGENTS.md rules, protected paths and risk boundaries; returns a JSON verdict with line-anchored findings. Use when launched with AGENT_FLOW_ROLE=reviewer or asked for an agent-flow review of a 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。

Use to iterate a change until tests/quality checks pass — bounded run→revise→re-run gated by a numeric threshold, then a judge confirms. Triggers 'iterate to green', 'keep fixing until tests 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。

Use to run a depth-bounded self-correction loop (attempt → critic verdict → re-attempt) as a tunable test-time compute knob — a do-and-judge specialisation, default off, capability-gated.

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。

When scoring a roadmap, PR review, ADR, or ticket for completeness — risk, tests, migration, maintainability. Dispatched by /refine-ticket, /adr-create, /review-changes; never auto-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。

When scoring whether an agent response defended against an injection — treated untrusted content as data, refused role-takeover, ignored fake boundaries. Inverted axis; never auto-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。

Blind dual-implementation pattern where two agents independently create artifacts, then a third agent judges which is better and synthesizes learnings.

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。

Agents work in parallel on the same task; judges evaluate and select the winner.

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 on an existing project to decide KEEP / MERGE / ARCHIVE — never limbo. Forces a call on tools that already exist and may have stopped earning their keep. Trigger on "is this still worth keeping", "audit this repo", "tech-debt cleanup", "sweep the folder", "what's dead here", or any signal that something hasn't been touched in months. Judged from both the agent lens (still legible, still drivable, still safe) and the human lens (do I still reach for it, does it nag). Includes a non-negotiable footgun check for stale pipelines that can overwrite live data. Outputs a backed AUDIT.md and a one-line verdict note in the project root docs. Do NOT load for greenfield projects (use new-project-gate), one-off bug fixes, or when the answer is already obvious.

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 before building anything new — a pre-build gate that decides whether an idea deserves its own tool, judged from both the agent lens (legible, drivable, automatable) and the human lens (will I touch it, do I want to maintain it). Trigger on "should I build X", "starting a new project / app / tool / repo", "is this worth making", "want to spin up", or any new-build intent — even if the word "checklist" never appears. Outputs a backed GATE.md with checkmarks and a one-line verdict note in the project root docs. Do NOT load for small config tweaks, one-off scripts, bug fixes on existing things, or anything that is clearly a feature of something you already run.

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。

Obtain an independent review of the approach and trade-offs in completed 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。

SOP for the architect-tier campaign workflow (/campaign): exhaustive survey, mitigation planning, tiered orchestration, and reconciliation. Trigger when: - Running a multi-workstream initiative where an expensive architect-tier council surveys, plans, emits worker prompts, and judges landed work. - Conducting production-readiness assessments that fan out into autonomous mitigation dispatches across model tiers. - Prompt contains: /campaign, campaign workflow, survey, orchestrate, reconcile, premise freshness, tier routing, worker IBC, scratch.

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。