「human review」の検索結果

Use this skill when an agent needs Google Cloud Vision API for still-image understanding: labels, object localization, OCR, document text, SafeSearch, image properties, crop hints, web detection, batch annotation, Cloud Storage based pipelines, confidence evaluation, privacy, quotas, cost, and QA. Do not use it for Gemini multimodal reasoning, video analysis, image generation, custom model training, product catalog search design, or human reference/authenticity 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。

Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions via show-me-your-work. Use for /figure-it-out, 'figure it out', a large migration, or when no narrower playbook applies.

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。

Keeps private and unapproved material out of a public build. Scans the built output (HTML, serialized component payloads, client JS and CSS chunks, static data routes, public files) against a private tier that always applies and a draft tier that applies in production. Gates work-in-progress so it shows in preview and is absent from production, and keeps sign-off in a ledger only the human writes. Use when a site or app publishes content that agents drafted or that came from private sources.

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。

Acceptance Orchestrator workflow skill. Use this skill when the user needs a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

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。

Acceptance Orchestrator workflow skill. Use this skill when the user needs a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

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-encounter orientation on a repository nobody here has worked in yet. Runs a fixed five-step workflow — venv setup, tarball fetch, tree-sitting structural scan, featuring synthesis, then reasoning over the two — and yields an account of what the repo contains and how it is arranged, optionally written out as _FEATURES.md. Use for "I just cloned this", "what is this repo", "what does this do", "explore this repo", "give me an orientation", "what are the main features", "review what's new in this repo", or before starting work in a codebase you have not seen. This is the divergent what's-here skill. Route elsewhere for: a named symbol, a file's structure or a line range (tree-sitting); all callers of a Python symbol (searching-codebases); teaching a human the codebase through exercises (orienting-codebases); fetching or cloning a repo without analysing it (accessing-github-repos, cloning-project).

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。

The checkpoint coordinator for /feature. Routed to by /feature once a writing-plans plan exists. Uses authored HTML checkpoints or bounded legacy batches, delegates each scope to subagent-driven-development (fresh author agent per task, full review chain, fresh verification), then stops for a human checkpoint before the next batch. The checkpointed counterpart to /sprint's autonomous 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。

Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells and produce more human-like 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。

Use when you write or revise the analiz deliverable - the ONE self-contained HTML report (spec and plan as sections) a human reviews passage by passage

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。

Guide a human review of a commit, PR, file, or directory. Use when invoked by name

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。

SEO-friendly article writing, audit, and humanization workflow for Markdown content. Use when creating, outlining, editing, auditing, rewriting, or quality-checking blog posts, tutorials, comparisons, listicles, explainers, FAQ sections, excerpts, SEO titles, meta descriptions, tags, or Google-friendly content briefs that need clear topics, natural keyword use, on-page SEO review, reader-friendly prose, and iterative optimization.

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 designing, reviewing, or refactoring a CLI that must serve AI agents alongside humans, or when converting an API or SDK into an agent-usable CLI interface.

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。

Make AI coding-agent messages to humans clear and easy to follow. Use for every user-facing update, explanation, review, question, and handoff in this repository, or when the user asks to simplify or rewrite an agent message.

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 at write time to vector/embedding memory — Grove content-addressed insertion, chroma/pgvector upserts, memory-consolidation promoting session traces to MEMORY.md, or embedding externally-ingested content. Scores each candidate record against a fixed panel of sentinel queries and quarantines any record that would become the nearest neighbor of too many unrelated queries — a hub — whether from adversarial poisoning or accidental over-generality. This is the memory-record-side sibling of skill-injection-guardian (file-side) and the write-side complement of memory-use-warrant (read-side). Quarantine, never silently drop; a human reviews. Backed by the admission-time hubness gate (arxiv 2606.19692v1). Triggers on inserting into vector memory, consolidating memory, and embedding stranger content.

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 Verify for snapshot testing in .NET. Approve API surfaces, HTTP responses, rendered emails, and serialized outputs. Detect unintended changes through human-reviewed baseline files.

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。

Advises on setting up and validating LLM text classification: codebook, learning regime and model choice, prompts, validation against human coding (kappa, F1), hybrid review, measurement error, and reporting, plus a short resumable batch pattern with a rule-based baseline. Use to classify, code, or label text at scale; category discovery goes to topic-modeling.

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。

Write clear, plain-spoken code comments and documentation that lives alongside the code. Use when writing or reviewing code that needs inline documentation like file headers, function docs, architectural decisions, or explanatory comments. Works well for both human readers and AI coding assistants who see one file at a time.

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。

Investigate an alert, page, or production symptom in an incident channel or a team's oncall / monitoring channel, and report findings a human can verify. Ordinary conversation and chatter are not alerts; leave those alone. Use when an alert or page lands, when error rate, latency or saturation is up, when someone asks "why is X broken", "investigate", "what changed", "root cause this", pastes a monitor, dashboard, trace or error-tracker link, or reports production trouble; also by default when an alert lands in a covered channel unasked. Feed-level asks land here too ("which alerts matter", "triage today's alerts"), plus the scheduled alert-review routine and the ticket path ("customer X can't check out"). Runs a fast first pass posted as a short interim update with a TL;DR, every finding carrying the query or link to verify it, then proposes the fix and — with connector access and confirmation — carries it out, never unattended. Afterwards `incident-postmortem` writes it up.

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。

Line-editor pass on any content draft against a client voice guide. Flags cadence issues, signature-move overuse, voice-guide violations, receipt gaps — things a rule-based gate can't catch. Use after /content-gate and before human 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。

Use AgentClick when an agent should pause before risky commands, plans, drafts, or code changes so a human can inspect, edit, approve, or reject them in a purpose-built browser UI.

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。

Generate structured software specifications for features, bug fixes, and products. Use when the user wants to create a spec, PRD, feature brief, requirements document, or when starting any new implementation that needs a specification first. Invoke via /spec-writer or when the user says "write a spec", "spec this out", "create a spec", "I need a spec for...", or describes a feature they want to build. Produces adaptive-complexity specs with Job Stories, Gherkin acceptance criteria, and three-tier boundaries. Output is a markdown file ready for agent execution or human 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。

6-phase multi-agent pipeline with approval gates. Orchestrates Plan→Design→Implement→Review→Test→Deploy phases with explicit entry/exit criteria, phase-level agent assignment, and human-in-the-loop approval checkpoints.

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。

Post-implementation QA planning — independent of /review (the developer chooses whether to run them sequentially or in parallel), only when the change has a running surface worth driving. Interviews the developer to turn the specs and the diff into an executable QA specification (specs/qa/QA-<N>-<slug>.md) that /execute-qa runs. The agent drives browser and shell; the human steps in only at named handoff points. Use only when the user asks to plan manual QA — never trigger automatically.

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。