「drift」の検索結果

Diagnose and fix a failing scheduled (or standalone) TMDb Integration workflow run — re-run transients, or fix real drift on a branch off main, then PR and (optionally) merge. Use for the weekly Sunday Integration cron failure, or any red Integration run not tied to an open 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。

One-shot perspective reset that surfaces blind spots mid-work. Scans what the user has been doing, generates one abstract reframing question, and runs 3 quick checks (scope drift, side effects, better approach) in under 10 lines. No dialogue, no code. Trigger phrases: "/stepback", "step back", "한발 물러서", "넓은 관점", "놓치는 거 없나", "방향 맞나", "zoom out", "큰 그림", "방향이 맞는 거야", "잠깐 멈춰", "지금 뭘 하고 있는 거야", "blind spot", "재확인"

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。

Validate data quality in CSV, JSON, and database exports by checking for missing values, type mismatches, duplicates, outliers, and schema violations. Use when building ETL pipelines, auditing data imports, checking data freshness, or ensuring data contracts between teams. Trigger words: data quality, validation, null values, duplicates, schema check, data contract, ETL, pipeline, data 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。

I am a veteran print production specialist with 15+ years in tabletop game manufacturing. I've shepherded hundreds of games from digital files to retail-ready products, working with manufacturers from The Game Crafter to Panda GM to Cartamundi. My expertise spans the entire production pipeline: color management, dieline creation, paper selection, finishing techniques, component nesting, insert design, and the critical art of the unboxing experience. I've learned the hard way about RGB-to-CMYK disasters, registration drift, humidity warp, and minimum font sizes that become illegible smudges. I know the difference between 280gsm blue-core and 320gsm black-core card stock by feel. I can tell you why your rich black needs to be C60-M40-Y40-K100, not just K100. I understand why your box needs 15mm clearance on each dimension, and why that gorgeous neon green in your design will become a muddy olive in print. Use when "print my game, packaging design, prepare files for print, dieline, print specifications, board game manufacturing, card game printing, box design, bleed and safe area, CMYK conversion, paper stock, card finish, foil stamping, embossing, unboxing experience, thermoform insert, punchboard design, component manufacturing, Panda GM, Game Crafter, Cartamundi, print-production, packaging, manufacturing, board-games, card-games, cmyk, dieline, die-cutting, offset-printing, tabletop" mentioned.

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。

World-class infrastructure automation - Terraform, Pulumi, CloudFormation, and the battle scars from managing infrastructure that handles production trafficUse when "terraform, pulumi, cloudformation, infrastructure, iac, state file, remote backend, s3 backend, dynamodb lock, terraform plan, terraform apply, terraform destroy, module, workspace, provider, resource, state drift, import, aws, gcp, azure, infrastructure, terraform, pulumi, cloudformation, iac, devops, aws, gcp, azure, cloud" mentioned.

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。

Manage public/private repository pairs. Verify parity, detect drift, run sync scripts, and validate no sensitive data leaks to the public repo. Use for projects that maintain separate dev and public repositories.

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。

Install a per-turn canary signal (e.g. starting every reply with the user's name and a turn counter) so silent context degradation becomes visible the moment it happens, and run a recovery protocol when the canary trips. Use when the user mentions a "canary", "context canary", or "canary check", asks to detect context rot / compaction / drift, says "you stopped using my name" or "did you lose context", asks "how degraded is your context", or wants an early-warning system for long agent sessions.

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。

Citation-integrity forensics: is every reference real, correctly attributed, and used in a context the cited work actually supports? Catches hallucinated references (no paper at the claimed arXiv id/DOI/venue, fabricated authors/year), metadata drift (wrong year/venue/version), and wrong-context citations (a real paper cited for a claim it never makes — or argues against). A hot zone for machine-generated papers. Decidable at L0 (text + canonical sources). Span-anchored to the evidence ledger (claims.json); the executor gathers canonical facts (DBLP / arXiv / DOI), then one FRESH cross-model thread per cited key proposes findings; reviewer != adjudicator. Emits citation-forensics.findings.json; NEVER computes the verdict. Triggers: "citation forensics", "check the references", "hallucinated citations", "wrong-context citation", "verify references", "引用核对".

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。

Transparent, itemized impressions of AI-generated WRITING STYLE — the repo's ONLY non-integrity track. Two passes: a deterministic defensive-hedge density screen (tools/check_ai_style.py, AIS-DEFENSIVE-HEDGE) plus a fresh cross-model GROSS-cases-only semantic pass over the 13 AIS-* style tells (broken narrative arc, LLM phrase tics, jargon-stuffing, invented codenames, clause/formula walls, gratuitous pseudocode, bullet overuse, bold-module spam, restatement loops, focus drift, single-style figures, appendix dumping). Every finding is named, LOCATED, span-anchored to the evidence ledger (claims.json), carries not_integrity_finding:true + false_positive_risk:high + an fp_case, and gets ZERO verdict weight: the adjudicator forces it to info, excludes it from overall_verdict, and renders it in a SEPARATE report section. NOT an AI-text classifier — no scores, no "this is AI-written", no authorship probability; a paper can be CLEAN_GIVEN_EVIDENCE and still list many. Emits ai-style-impressions.findings.json; computes NO verdict; if a tell is actually substantive it routes to the integrity auditor. Triggers: "AI style", "vibe check", "writing fingerprint", "AI 文风", "vibe paper".

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。

Family-G proof & derivation integrity forensics: does a THIRD PARTY's written proof/derivation actually establish its theorem, or does it skip an obligation, assume its own conclusion, take an invalid step, drift a symbol's meaning, or smuggle an unstated assumption? Decides from the WRITTEN proof/derivation — verdict-bearing at L1 (the LaTeX source; PDF-extracted math is unreliable, so an L0 PDF-only run surfaces info only) — never asserts 'fabricated', only that the step shown does not hold. A fresh cross-model reviewer reads the theorem/proof + an extraction-only obligation scaffold and proposes per-obligation findings, each span-anchored to the evidence ledger (claims.json); reviewer≠adjudicator. Emits proof-derivation-forensics.findings.json; NEVER computes the verdict. dimension=proof, can be critical. Triggers: "proof forensics", "check this proof", "derivation integrity", "audit the math", "证明审计", "推导有没有漏洞".

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。

/aegisops-ai — Autonomous Governance Orchestrator workflow skill. Use this skill when the user needs Autonomous DevSecOps & FinOps Guardrails. Orchestrates Gemini 3 Flash to audit Linux Kernel patches, Terraform cost drifts, and K8s compliance 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。

/aegisops-ai — Autonomous Governance Orchestrator workflow skill. Use this skill when the user needs Autonomous DevSecOps & FinOps Guardrails. Orchestrates Gemini 3 Flash to audit Linux Kernel patches, Terraform cost drifts, and K8s compliance 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。

Open a GitHub PR via API as a flowing graph — branch + push + create_pr + mergeable poll, with structural protection against pushing to main/master/etc. Use when a Claude Code or Claude.ai container needs to land changes on GitHub via the API (no git CLI required) and the prose "create branch, push, open PR, wait for mergeable" workflow keeps drifting under context pressure.

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。

Check that a document's claims about code are actually true by reading the prose, the code, and the tests and reporting (or fixing) where they disagree. Use whenever the user wants to verify a README, guide, spec, or docstring still matches the code; whenever they mention documentation drift, doc-code sync, "is this still accurate", stale docs, or keeping docs/tests/code consistent; before publishing or merging a docs change; or as a periodic doc-accuracy sweep. The agent reads the prose's meaning directly — there is no claim-comment DSL to maintain. Pairs with TDD — the test suite is the deterministic behavioral gate, this skill is the semantic prose-vs-reality 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。

Disciplined, validation-gated revision of an EXISTING skill so each edit is a measured improvement rather than a guess. Use when editing, revising, or tuning a skill that already exists and there is evidence it underperforms (observed failures, drift, complaints) — invoke by name, or have versioning-skills / creating-skill defer to it before applying edits. Not for authoring a brand-new skill from scratch (use creating-skill) or one-off prose.

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。

Exploratory data analysis. Use when users upload .csv/.xlsx/.json/.parquet files or request "explore data", "analyze dataset", "EDA", "profile data". Small files get ydata-profiling HTML/JSON reports; large files (over 200MB or 5M rows) get fixed-memory DuckDB/sketch profiling. Also covers near-duplicate row detection, cross-file key overlap ("can these join?"), dataset drift vs a stored baseline, and time-series profiling.

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 implementation engine. Routed to by /sprint (full plan, autonomous) and by executing-plans (scoped batch, checkpoint-gated). One fresh subagent per task — test-first via tdd — followed by spec-compliance review, quality review, and fresh-run verification. No single context accumulates drift, and nothing is accepted on a subagent's word.

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 verifying that requirements/specs/PRDs and their implementation plans match — before starting work, after a spec or plan update, or when suspecting coverage gaps, scope creep, or design drift between intent and action documents. Needs both documents; not for checking code against a spec.

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。

Set up or tune any dev machine, fresh or drifted, on macOS, Linux, or Windows: report what's missing, install only that, then fix PATH, duplicate runtimes, and shell config. Don't use for Dockerfiles, CI images, or single package installs.

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 the user asks to audit what's wrong with a project, "make it right", "看看项目出了什么问题", "为什么用户的需求还没上线", "为什么没提交App Store", "为什么没新build", or wants a holistic state-of-the-project check covering unmerged branches, stalled PRs, failed GitHub Actions, stale builds, plan drift (TODOS.md / ROADMAP), unreleased commits, and log errors. Runs read-only investigation, presents a grouped checklist, fixes only after explicit user confirmation. Aware of the Cathier iOS app workflow (Xcode + fastlane + auto-merge @claude PRs from in-app feedback).

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 the user has 2+ video / audio recordings of the same event captured by different devices (cameras, phones, separate audio recorders) and wants them aligned to a single common timeline. Outputs only a lightweight `.sync.json` sidecar per input — original files are never re-encoded. Triggers — "多机位同步", "对齐这几个机位", "match camera timelines", "sync these angles", "audio drift between cameras", "separate audio recorder", "Riverside / Zoom recording that needs to line 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。

Suede Labs cross-surface canon discipline: hold one canonical answer across every surface that states it (web, iOS, Android, docs, a second service) by generating a contract from the reference surface and making the others assert against it, so a divergence fails a test instead of reaching a user or an answer engine. Consistent canon is what makes a product citable: generative search quotes sources that do not contradict themselves, and a number that differs between your site and your app is a contradiction a model can see. Use when the same rule, threshold, ladder, or stated fact lives on two or more surfaces; when values are copied by hand out of a handoff; when two surfaces already disagree; or when auditing where they drifted. NOT FOR: deciding which surface is correct (a product call this skill records rather than makes); reviewing a diff (use suede-code-review); wiring merge gates (use suede-ci-gate); a generative-search audit of a page (use suede-seo-audit).

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 for regenerating Axone contract schemas and rendered Markdown docs. Use when contract APIs or metadata change, when checking generated-doc drift, or when preparing documentation commits.

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。