「verified」の検索結果

Resolve the currently-unresolved review threads on the current branch's PR in one sweep — assess each, fix it (test-first, verified) or reply-only, then reply and resolve — and return a summary. Use standalone to address PR review feedback, or as the thread-handling step invoked by /watch-pr. Repo is adamayoung/TMDb.

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。

GitHub issue creation skill. Analyzes the entire codebase impact based on user request, then creates a structured issue with AI-verified/human-judgment-needed/caution sections. /issue "issue description" Trigger: "/issue", "이슈 만들어", "issue 만들자", "깃헙 이슈"

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。

Iterative task completion loop with Definition of Done verification. Combines the Ralph Wiggum technique (prompt re-injection via Stop hook) with DoD-based independent verification. Claude proposes DoD criteria, user confirms, then Claude works autonomously. Stop hook re-injects the original prompt and blocks exit until all DoD items are independently verified. "/ralph", "ralph loop", "ralph 루프", "반복 작업", "DoD 루프", "완료 검증 루프", "task loop", "keep going until done"

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。

Makes working code easier to read and change without altering what it does, and proves the behaviour stayed the same. Use when someone says "simplify this", "clean up this function", "this file is a mess", "reduce the complexity", "refactor for readability", "tidy my diff before the PR", or when a linter reports high cyclomatic complexity or deep nesting. Covers pinning current behaviour with characterization tests, measuring complexity, choosing a named refactoring, applying it in small verified steps, and reporting suspected bugs found on the way instead of fixing them silently.

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 experiment integrity against the evidence ledger. At L2 (repo + result files present) a fresh cross-model reviewer reads the eval code line-by-line for fake/derived ground truth, score self-normalization, phantom results (a paper number with no backing file/key), dead/uncalled metric code, verified-scope inflation, method-described ≠ method-evaluated drift, synthesized-looking results, placeholder/fake data still wired into a released result, code-output ≠ reported-number mismatch, and missing reproducibility artifacts (an empirical/agent/LLM paper shipping neither code nor the prompts/configs its results need) — every finding span-anchored to a ledger claim_id. At L0/L1 (PDF / source only) the same patterns are surfaced as info-level 'could-not-verify' signals where the ledger gives an anchor (observability_level_required:2) — NEVER a fraud verdict from a PDF. The reviewer PROPOSES findings; tools/adjudicate_findings.py computes the verdict. Detect-only. Triggers: "experiment forensics", "audit the results", "check the eval code", "实验诚实度".

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。

Axiom — First-Principles Assumption Auditor / 第一性原理拆解器 workflow skill. Use this skill when the user needs First-principles assumption auditor. Classifies each hidden assumption (fact / convention / belief / interest-driven), ranks by fragility × impact, and rebuilds conclusions from verified premises. Bilingual: auto-detects Chinese or English 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。

Axiom — First-Principles Assumption Auditor / 第一性原理拆解器 workflow skill. Use this skill when the user needs First-principles assumption auditor. Classifies each hidden assumption (fact / convention / belief / interest-driven), ranks by fragility × impact, and rebuilds conclusions from verified premises. Bilingual: auto-detects Chinese or English 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。

Finds, evaluates, fills, submits, and tracks a candidate's own job applications using a verified resume, evidence-based targeting, secure local profile storage, and browser automation. Use for onboarding or migrating a job-search profile, searching active roles, assessing a posting, applying to an authorized URL or batch, recording outcomes, or reviewing application effectiveness.

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 building a feature, refactoring, fixing a complex bug, changing architecture, or starting any non-trivial coding task. 12-stage verified dev workflow from research to deploy.

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。

Decide which model, effort level, and cascade shape each subagent gets, and how to keep improvement loops safe (evaluator-as-selector, stop on regression). Routes on measured cost-per-completed-task rather than per-token price, because a tier's token count varies more by task shape than price varies across tiers. Covers per-model effort semantics, the concision lever, cascade preconditions, context handoff, and watching a subagent fan-out live. Use when choosing a subagent's model or effort, when choosing how to escalate a failed attempt, or when asked which model or effort a task should get. Grounded in a 2026-07 calibration, a 2026-08 coding-cost study, a 2026-09 seeded-bug repair battery, a 2026-10 Haiku 5.5 ladder priced per spawn, and a 2026-10 retry-versus-escalation ladder on 295 SWE-bench Verified tasks; Managed Agents API specifics are operational, not calibrated.

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 a verified local Git commit when committing changes is requested. Not for explaining commit history, drafting a message only, or postponing a commit. Applies every commit gate and never implies a push or 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。

Create a verified local Git commit when committing changes is requested. Not for explaining commit history, drafting a message only, or postponing a commit. Applies every commit gate and never implies a push or 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。

Verify statistics and claims in blog posts by fetching cited source URLs and checking if the claimed data actually appears on the page. Extracts all statistical claims (numbers, percentages, named sources), fetches each cited URL via WebFetch, and scores match confidence (exact match 1.0, paraphrase 0.7-0.9, not found 0.0). Flags uncited claims as UNVERIFIED. Use when user says "fact check", "verify statistics", "check sources", "validate claims", "factcheck", "source verification".

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 options, a recommendation, or an already-chosen approach are on the table and the reasoning under them has not been independently checked — especially when the case rests on cited documentation, remembered behavior, or premises nobody verified. Not for generating alternatives, and not for critiquing a spec, which is /pushback.

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 options, a recommendation, or an already-chosen approach are on the table and the reasoning under them has not been independently checked — especially when the case rests on cited documentation, remembered behavior, or premises nobody verified. Not for generating alternatives, and not for critiquing a spec, which is the pushback 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。

Publish or update a static site (gh-pages) on GitHub Pages via GitHub Actions in any repo: text or pre-built HTML in, workflow set up, live URL verified. Don't use for CI test pipelines, framework/SSG builds, or Netlify/Vercel hosting.

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。

Prepare verified ownership and delivery notes.

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。

Suede-owned referral and affiliate program discipline. Use when designing refer-a-friend mechanics, ambassador or partner incentives, fraud controls, attribution, payout logic, or viral-loop measurement. NOT FOR: executing payouts or changing billing, launch-wide packaging (use suede-launch-packaging), lifecycle messaging (use suede-emails), or reporting unverified referral lift.

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。

Suede-owned comparison-page discipline for accurate, evidence-backed alternative, versus, and competitor-comparison content that wins evaluators and search intent. Use when planning or writing a public page that positions products against named alternatives from verified evidence. NOT FOR: gathering the underlying competitor evidence (use suede-competitor-profiling), internal battle cards (use suede-sales-enablement), or scaled page generation (use suede-programmatic-seo).

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 documentation needs creating, checking, or maintaining — docs may have drifted from code, pre-release doc verification, updating docs after finishing code work, adding or enforcing project terminology, deciding where a new doc should live, or a routine re-audit of previously verified docs.

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 definition of done. Run before calling any change done, fixed, verified, ready or shippable, for features and bug fixes alike. Checks the pre-mortem was answered, proves the tests fail on the old code, gets a fresh breaker review, runs CI's own checks in a clean checkout, checks the user-facing words, and writes the evidence report. Also use when asked "is it done", "is it ready", "did you verify it" or "can we merge".

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。

Coordinates an active production incident by establishing command, reducing blast radius, preserving evidence, communicating verified impact, restoring service, validating recovery, and creating owned follow-up actions. Use for outages, severe degradation, security or data-integrity events, failed releases, and urgent operational triage. Not for a normal local bug, routine alert tuning, or a postmortem after the incident is already closed.

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。

Produce a professional, send-ready deliverable on the user's behalf — in the correct file format (never raw markdown), in the user's voice, structured to lead with the strongest material, and free of document-level AI tells. Runs a gated pipeline with a fresh-context verification policeman and a Stop-hook that won't let the session finish without a verified PASS. Use when producing a job take-home, client report, executive one-pager, slide deck, proposal, or anything going out under the user's 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。

Designs and audits native iOS interfaces. Use when reviewing or refining SwiftUI layout, typography, Liquid Glass, navigation, or dashboards on a freshly verified build.

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。