「evidence」の検索結果

Writes and rewrites the words on marketing pages: homepage, landing page, pricing, feature, product and about pages, including headlines, button text, section copy, title tag and meta description. Starts from the reader's own language and the proof the business can show, edits copy where it lives in the repository, and flags every claim that needs evidence. Use when someone says "write copy for this page", "rewrite our homepage", "this page sounds generic", "headline ideas", "better CTA", "landing page copy for this ad" or "pricing page wording". Email copy belongs to email-sequence, popups to popup-cro, and line-editing a finished draft to copy-editing.

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。

Edits existing marketing copy in ordered passes (structure, claims, sentences, consistency, proof) and returns the edited text with a change log and a list of questions for the author. Flags claims that need evidence instead of inventing proof, and keeps the writer's voice. Use when someone says "edit this copy", "proofread this page", "tighten this", "polish this email", "review my landing page copy", "make this clearer", "check this before we publish", or asks for copy feedback on a page, ad, email or product description.

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。

Builds a content strategy a small team can execute: audience needs backed by counted evidence, an audit of what is already published, a topic map with one page per search intent, a scored backlog, a 90-day calendar sized to real capacity, and the numbers that will show whether it worked. Use when someone asks "what should we write about", "plan our blog", "content strategy", "content plan for next quarter", "topic clusters", "content audit", "our blog traffic is falling", or wants a pile of content ideas turned into a prioritised plan.

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。

Guides a founder from real decisions to a short set of written company values that people can act on: collects incidents, tests each candidate value, writes it as a trade-off with behaviors and a story, and wires it into hiring, feedback and promotion. Use when someone asks to "define our company values", "write a values document", "our values are generic, fix them", "turn our values into interview questions", "what should our culture be before we hire", or wants to check whether the team lives the values it has. Produces VALUES.md, an evidence log and an interview kit.

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 the cause of a hard bug by running several read-only subagents in parallel, each attacking it from a different angle (change history, code path, data and state, environment, reproduction), then checking their evidence, ranking the hypotheses and naming the one experiment that would confirm the leader. It diagnoses and does not fix. Use when someone says "hunt this bug with multiple agents", "swarm on this regression", "investigate in parallel", "find the root cause", or when a failure is intermittent, crosses components, or has resisted a first look.

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。

Reconstructs the workflow behind a past artifact by querying local ax session, recall, and commit history data. Use when a user asks "what made X work", "how was Y shipped/built", "extract workflow from <date|sha>", "workflow around <topic>", "recipe for this feature", or similar. It finds the anchor session or commit, inspects ax sessions, ax recall, and ax sessions show, and returns an ordered read-only narrative with decisions and evidence.

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 implementing policy-as-code, continuous compliance monitoring, automated evidence collection, or audit-ready systems requiring SOC2/ISO/PCI/HIPAA complianceUse when ", " 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。

Challenges a recommendation, design, large change, or any artifact submitted for hard review (spec, proposal, policy, plan) across 5 dimensions (consistency, completeness, actionability, alignment, risk), from the standards of a named senior expert in the artifact's domain and ideally from a fresh context or a different model. Searches assuming defects exist and reports only those that survive evidence. Panel mode runs several independent lenses in parallel on a release candidate, verifies every finding against the current head, and routes confirmed ones to file owners. Use before shipping a significant recommendation, design, large branch, or multi-agent release, or when asked to tear something apart, be brutally honest, or poke holes in it.

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。

Refuses "flaky" as a diagnosis. Turns an intermittent failure into a reproduction by isolating it from the environment, naming the variable that controls it, forcing that variable, and measuring before and after with enough runs to count. Separates real defects from environment contention with evidence, and never retries to green or widens a threshold. Use when a test, performance check, or deploy step fails intermittently or passes on rerun.

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。

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。

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。

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。

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。

Create a minimal, repeatable reproduction plan for a bug. Use when a junior developer needs clear steps to reproduce and capture evidence.

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。

Evaluate proposed repository harness changes with pinned Darwin tools and explicit evidence limits.

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。

Use when the user explicitly asks to use the informed-patient skill to prepare for a medical appointment, organize symptoms before seeing a doctor, or evaluate the evidence behind a diagnosis or treatment. Do not trigger automatically from health questions or symptom mentions alone — requires an explicit request 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。

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。

Investigate an unexplained defect or unexpected behavior without changing application code. Use for root-cause diagnosis and an evidence-backed handoff, including a bounded unresolved result. Not for implementing a known fix, new features, or explanation-only questions.

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。

Record user-decided ADRs or inspect their health read-only. Preserve attribution and acceptance evidence.

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。