「claim」の検索結果

Enforces tiered test coverage standards with three dimensions — line coverage by tier, spec-to-test traceability, and spec-to-code implementation mapping. Use before claiming code is complete.

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 the Implement→Review→Test→Fix cycle until the work is actually clean, with evidence. Use after any non-trivial implementation and before claiming it is 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。

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。

Checkable-ish surface presentation signals a reviewer notices first — duplicate/near-identical tables, leftover pipeline/template strings, too-few or LLM-looking figures, and page-padding. AUXILIARY ONLY and weak by design: a deterministic pass (tools/check_presentation.py — dup-table + pipeline-artifact) plus a fresh cross-model GROSS-cases-only semantic pass (thin-float, LLM-figure, page-padding), every above-info finding span-anchored to the evidence ledger (claims.json). The adjudicator CAPS everything at minor (SURFACE_ONLY_SKILLS + SURFACE_PATTERNS) — these contribute at most SOFT_FLAGS, never a HARD verdict — default false_positive_risk:high. NOTE: the pure AI writing-STYLE impressions (AI-flavor prose, defensive 'not-X-but-Y' hedging, narrative-arc, jargon-stuffing, invented codenames) MOVED to the zero-verdict-weight AIS track — for those use skills/ai-style-impressions, NOT this. Emits presentation-signals.findings.json; NEVER computes the verdict. Triggers: "presentation signals", "surface check", "duplicate tables", "排版信号".

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。

Flagship intra-paper self-consistency forensics: does the paper contradict ITSELF across abstract/intro/tables/body/appendix, and does the method DESCRIBED match the method EVALUATED? Needs no external ground truth — works PDF-only (L0). Runs a deterministic arithmetic pass + a fresh cross-model semantic pass, every finding span-anchored to the evidence ledger (claims.json), reviewer≠adjudicator. Emits consistency-audit.findings.json; NEVER computes the verdict. Triggers: "consistency audit", "check the paper against itself", "self-consistency", "内部自洽".

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。

End-to-end substantive-integrity forensic sweep of a research paper (especially autoresearch / AI-Scientist-style output). Orchestrates the whole pipeline: ingest (arxiv-id | pdf | dir → working dir + pdftotext for L0) → /evidence-ledger (artifact manifest + observability level L0/L1/L2 + span-anchored claims.json) → fan out the integrity auditor skills (consistency, citation, baseline, experiment, presentation, proof-derivation, eval-design — each reads the ledger, emits span-anchored findings) + the zero-verdict-weight AIS writing-style track → advisory memos (/adversarial-case-builder + /novelty-duplication-advisory, no verdict weight) → deterministic tools/adjudicate_findings.py (--ledger REQUIRED) → reviewer-ready Integrity Forensics Report. Cross-model (fresh codex per dimension) and reviewer≠adjudicator: the model proposes findings, the deterministic adjudicator decides the verdict. Observability-aware, detect-only, never an opaque AI-text classifier (a separate zero-weight AIS section lists AI writing-style impressions, never moving the verdict). Triggers: "anti-autoresearch", "integrity audit this paper", "forensic review", "audit a submission", "审一篇投稿的诚信".

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。

MEMO-ONLY prior-work overlap advisory: surfaces the two ADVISORY taxonomy signals neither a tool nor a model can decide from the paper alone — ADV-TRIVIAL-COMBINATION (standard A+B+C / 缝合 stapling) and ADV-DUPLICATE-PUBLICATION (repackaged / duplicate submission). The executor RETRIEVES candidate prior work (DBLP fuzzy-title + boolean · WebSearch · WebFetch) from the paper's own title + contribution spans in the evidence ledger; TWO fresh cross-model codex reviewers (one per axis) LAY OUT the overlap side-by-side against each anchored contribution claim. It NEVER rules 'trivial' or 'duplicate' (that is a human judgment) and absence of a match is NOT evidence of originality. Emits novelty-duplication-advisory.memo.md + an info-only findings mirror; carries NO verdict weight — tools/adjudicate_findings.py lists it in ZERO_WEIGHT_SKILLS and caps it at info. Detect-only. Adapted from ARIS novelty-check, reframed from 'is MY idea novel' to 'here is the overlap a reviewer should weigh'. Triggers: "novelty advisory", "duplication check", "prior-work overlap", "is this stapling", "缝合", "查重", "重复发表", "duplicate submission".

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。

Use when deterministic runtime code needs to execute CommonGround worker lifecycle steps through the local `cg worker` command namespace, including claim acquisition, renewal, progress append, terminal finish, child dispatch, and suspend flows.

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。

Generates WAFFLES Declarations for social media posts — preemptive lists of what a post does NOT say. Use when users mention WAFFLES, ask for clarifications on their post, want to prevent misinterpretation, or request disclaimers for controversial/nuanced takes.

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。

Load at the start of any task whose deliverable is prose another person will read — a PR description, commit message, README, doc, postmortem, blog post, issue or review comment, report, release note or essay — before drafting it, whether the result is pushed, posted, published or saved to a file, without being asked. Draft, then run this pass on the draft before handing it over. Also use when someone says "de-claude", "de-slop", "humanize this", "this reads like AI", "make it sound human", or asks for a voice, tone or register edit. Rewrites the constructions that mark prose as model-written (staged reveals, verdict headers, aphoristic closers, "it's not X, it's Y", em-dash drama, forced triads, flat-certainty adverbs) into plain technical prose and checks the rewrite kept every claim. Not for fiction, poetry, code, or quoted text; for a full adversarial review of a deliverable use challenging.

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。

Find tests that enumerate a domain by copying it, and declare the invariants a codebase depends on. Reports where a parametrize list, for-loop, or it.each iterates a hand-written subset of a dict/set/tuple/Enum that exists in the source, and names the members nothing covers. Use when reviewing tests, when a module gains a name-to-thing table, registry, enum, or dispatch map, before trusting a green suite as evidence a domain is covered, or when asked "is this test actually total", "does anything cover X", "what does this repo guarantee", "which invariants do we declare". Also for vacuous tests that pass over an empty collection, for a domain that has silently NARROWED (an enumeration cannot see that), and for recording the refutation that proves a claim can fail.

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 git worktrees across any repository with the `gwm` Rust binary (CLI + ratatui TUI). Use when the user asks to create / list / remove / bootstrap / switch / link worktrees, run a command across worktrees (`gwm exec`) or reclaim build artifacts (`gwm clean`), materialise a PR into a worktree (`gwm review`), drive a multi-repo workspace (`--workspace`), run the JSON daemon / statusline (`gwm daemon`, `gwm statusline`), list or pin AI-agent sessions per worktree (`gwm agents`, Claude Code / Codex / opencode / Mistral Vibe detection), seed config from a preset (`gwm init --preset`), diagnose with `gwm doctor`, drive tmux/zellij, or wire `gcd` via `gwm shell-init`. Also covers multi-forge (#419): GitHub via `gh` **or** GitLab via `glab`, the `forge` / `[forge_hosts]` keys, and `gwm trust add`. Triggers on `gwm`, `gwq`, `git worktree`, `.gwm.toml`, `forge`, `forge_hosts`, `glab`, `gwm trust add`, GitLab MR, `gwm create`, `gwm list`, `gwm exec`, `gwm clean`, `gwm review`, `gwm daemon`, `gwm statusline`, `gwm agents`, `gwm note`, `gwm bootstrap`, `gwm doctor`, `gwm switch`, `gwm tmux`, `gwm zellij`, `gwm link`, `gwm status`, `gwm shell-init`, `gcd`, `feat/#`, `fix/#`, GitHub issue/PR linking on a worktree.

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 or update docs to match the code, citing each claim to path:line and asking on ambiguity; runbook docs also get a check-only validation script. Don't use for API-reference autogen (JSDoc/Sphinx), landing pages, or CLAUDE.md/AGENTS.md.

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。

Analyze liquid markets with a strict ICT/SMC framework that combines multi-timeframe bias, liquidity sweeps, displacement, close-confirmed MSS/BOS, FVG/OB/Breaker/OTE retracements, premium-discount location, session timing, invalidation, targets, and risk-to-reward. Use for ICT chart reviews, live-market analysis, OHLCV scans, or validating a user's trade thesis. Return an auditable setup status and conditional plan; do not use for generic indicator analysis, order execution, or claims of proven institutional intent.

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。

Applies the existentialist and feminist philosophy of Simone de Beauvoir, French philosopher and author of The Second Sex. Reach for this skill whenever the user is grappling with existential dilemmas, moral ambiguity, gender dynamics, societal expectations, or relationship ethics. Trigger this skill for questions about freedom versus responsibility, bodily autonomy, marginalization, or when the user feels trapped by external labels or "immanence." Use this to help the user reclaim their agency, recognize the social construction of their situation, and make authentic choices that expand their transcendence while respecting the interconnected freedom of others.

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。

Applies the empiricist, skeptical, and practical reasoning of David Hume, 18th-century Scottish philosopher. Use this skill whenever you encounter questions about epistemology, causality, human nature, moral philosophy, political authority, or the limits of rational knowledge. Trigger this skill when the user is grappling with abstract theories that need grounding, evaluating causal claims, discussing the role of emotion vs. reason in decision-making, or questioning the legitimacy of institutions. Even if the user doesn't name Hume, apply his frameworks (like Hume's Fork or the Impression Test) to cut through metaphysical speculation, ground arguments in observable experience, and recognize that reason is ultimately guided by human sentiment.

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。

Judge claims through evidence and alternatives.

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 product-marketing context discipline. Use when a project needs a shared record of product, audience, ICP, positioning, objections, customer language, proof, and goals, or when that record needs updating. NOT FOR: writing a campaign (use suede-campaign-in-a-box), conducting new customer interviews (use suede-customer-research), or publishing brand claims.

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 skill that prepares a song for sync pitching: scene and emotional angles, a supervisor-facing one-sheet, an exists/missing/unknown asset checklist covering master, instrumental, clean, and stems, screened lyric flags, mood tags, and the open clearance questions kept in their own labeled pile. Use when a track is headed for film, TV, ads, games, trailers, or creator campaigns; when a music supervisor, sync agent, or brand asks what a song is and whether it can be used; or when someone asks for a one-sheet, pitch email, or sync package for a release. Prepares review-ready materials only: never claims clearance, promises placement, or sends outreach. NOT FOR: finding and organizing the rights gaps behind an open clearance question (use suede-rights-audit); building the rights transfer package (use suede-rights-passport); linting the release folder itself (use suede-release-linter); a full rollout campaign (use suede-campaign-in-a-box).

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-affiliated marketing deliberation that applies documented public frameworks through clearly labeled simulated advisors, surfaces disagreements, and synthesizes a decision. Use when the user wants multiple expert lenses on one bounded marketing question. NOT FOR: factual claims about a living person's private views, primary research (use suede-customer-research), or executing the selected tactic (route to the relevant public Suede 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。

Use when reviewing iOS (Swift), Android (Kotlin) or Flutter changes - token storage, ATS and cleartext config, TLS trust, exported components, deep links, WebView JavaScript bridges, certificate pinning claims, secrets bundled in the app, Firebase rules

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 or analysing an A/B test, computing power or sample size, testing whether a difference is real, or writing any statistical claim — effect sizes with intervals, SRM checks, multiple comparisons and causal caveats

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。