测试与安全技能

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".

中文简介正在准备中。当前显示原文说明。

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".

中文简介正在准备中。当前显示原文说明。

Audit whether a paper's baseline comparisons are COMPLETE, FAIR, and SIGNIFICANT: a required recent SOTA baseline is missing while 'best/SOTA' is claimed (HP-MISSING-BASELINE); a baseline is undertuned / given less compute-tuning-data, run at a mismatched config, or the equal-budget ablation-as-baseline is absent (HP-WEAK-BASELINE); 'outperforms' is asserted over overlapping error bars or with no variance/seeds (HP-SIG-OVERLAP); and a cross-row 'improves over baseline by X%' is arithmetically wrong (HP-DELTA-ERROR, cross-row form only). A versioned per-domain baseline profile + a live leaderboard/recency search are assembled by the EXECUTOR as structured facts; a fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per dimension) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Works at L0 (stated comparisons) and deepens at L2 (configs/result files). A completeness question it cannot settle internally becomes needs_external_check, never a guessed missing baseline. Emits baseline-comparison-audit.findings.json; computes NO verdict. Detect-only. Triggers: "baseline audit", "missing baselines", "is the comparison fair", "weak baseline", "baseline 误报", "SOTA earned?".

中文简介正在准备中。当前显示原文说明。

Synthesize the single strongest EVIDENCE-BOUND reviewer case to reject a paper, built ONLY from the evidence ledger (claims.json) + the other auditors' confirmed findings — never free-floating LLM critique. Two fresh cross-model codex threads: an attack writes the ~200-word rejection paragraph (every accusation tagged to an existing claim_id/finding_id), a defense decomposes it and rules each point against the anchored evidence. MEMO-ONLY: emits adversarial-case-builder.memo.md (fed to the adjudicator via --memo) and carries NO verdict weight — tools/adjudicate_findings.py lists it in ZERO_WEIGHT_SKILLS and caps it at info. Honest-null allowed (the paper may survive). Run LAST. Detect-only. Adapted from ARIS kill-argument. Triggers: "adversarial case", "strongest objection", "rejection memo", "kill argument", "最强拒稿点".

中文简介正在准备中。当前显示原文说明。

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".

中文简介正在准备中。当前显示原文说明。

Nielsen's 10 usability heuristics. Use when auditing an interface, designing interaction flows, writing error messages or reviewing usability.

中文简介正在准备中。当前显示原文说明。

Lighthouse audits and Core Web Vitals — LCP, CLS, INP. Use when optimising page load, layout shift, input delay, images, fonts or render-blocking resources.

中文简介正在准备中。当前显示原文说明。

Orchestrator that routes a UI/UX task through brand, tokens, layout, components, polish and accessibility. Use for multi-concern work such as a design review, UI build or interface audit.

中文简介正在准备中。当前显示原文说明。

Use when the user wants a Xiaohongshu posting calendar, weekly review board, first-10-post launch plan, 10-20-post positioning test, or data-based next-step plan. Trigger phrases: "排期", "复盘", "30 天计划", "前10条", "10-20条测试", "发了没数据", "weekly review", "content calendar", "XHS schedule". Do not use for first-draft editing or initial account positioning.

中文简介正在准备中。当前显示原文说明。

Calibrated grilling session for stress-testing a plan, design, idea, or decision. First assesses the user's topic knowledge, confidence, and desired pressure level, then asks one question at a time with recommended answers. Use when user says "grill me", "stress-test this", "challenge my plan", "interview me", or wants a plan probed without being overwhelmed.

中文简介正在准备中。当前显示原文说明。

Black-box QA audit of slop-guard across MCP, CLI, fit, docs, agent workflows, and writing-effectiveness. Files GitHub issues for real problems found.

中文简介正在准备中。当前显示原文说明。

Audits font loading, type scales, measure, spacing, OpenType, and rendered punctuation with 78 scoped rules. Use when asked to "audit typography", "fix the fonts", or "review my type system". For a new visual direction use ui-design Direction; for general UI defects use ui-design Audit.

中文简介正在准备中。当前显示原文说明。

Reviews a local diff, branch diff, or PR with file:line findings in confirmed and plausible tiers, gates any test the diff adds or changes, and in apply mode lands the fixes and diff-scoped simplifications. Use when asked to "review my changes", "code review", "tidy this", "simplify my diff", "deslop this", "structural review", "security audit", or "audit these tests in my PR". For the PR itself use pr-creator; for CI and review threads use pr-babysitter; for UI defects use ui-design; for repo architecture use codebase-architecture; for pruning the whole suite to a target use test-audit.

中文简介正在准备中。当前显示原文说明。

Prunes low-value tests across a whole suite to a measured target while holding coverage. Use when asked to "remove useless tests", "prune the test suite", "we have too many tests", "agents keep writing pointless tests", or "cut 20% of tests without losing coverage".

中文简介正在准备中。当前显示原文说明。

Creates and reviews executable implementation plans grounded in repository evidence, with vertical slices, explicit decisions, and verification criteria. Use when asked to "plan this feature", "stress-test this plan", "grill me", or "split this into tickets". For architecture use codebase-architecture; for code review use tidy.

中文简介正在准备中。当前显示原文说明。

Audits libraries, CLIs, and SDKs using 38 rules for public contracts, package exports, piped output, errors, and configuration. Use when asked to "audit my CLI", "review my SDK", or diagnose package type resolution.

中文简介正在准备中。当前显示原文说明。

Audits agentic products for tool parity, authority, approval payloads, recovery, and trust using 24 rules and a ship verdict. Use when asked for an "AX audit", to review an agent approval flow, or whether an agent can operate the product.

中文简介正在准备中。当前显示原文说明。

Speeds up CI and the merge path: finds where changes wait between push and deploy, then fixes the critical path, check placement, merge queue or post-merge checks with auto-revert, flaky tests, and deploy rate. Use when "CI is slow", "speed up CI", "do we need a merge queue", "main keeps going red", "flaky tests block merges", agents open PRs faster than they merge, or building a self-healing merge loop.

中文简介正在准备中。当前显示原文说明。

Audits and edits agent instruction files, verifies repository commands, and migrates repositories to AGENTS.md as the single shared source. Use when asked to "improve my AGENTS.md", "migrate CLAUDE.md to AGENTS.md", or make instructions work across agents.

中文简介正在准备中。当前显示原文说明。

Creates and improves portable Agent Skills with a validator, routing scenarios, and evidence-based keep, cut, merge, or retire decisions. Use when asked to "write a skill", "update all skills", "audit my SKILL.md", "remove redundant instructions", or fix skill triggering.

中文简介正在准备中。当前显示原文说明。

Implements snapshot/golden file tests with temporal normalization so tests don't break daily. Use when implementing tests that compare output against expected snapshots.

中文简介正在准备中。当前显示原文说明。

Assesses production readiness or audits a codebase against its specs. Supports quick static mode, deep 17-dimension audit, or single-dimension focus. Use before a production launch, after a major refactor, when inheriting a codebase, or when someone asks how done the project is.

中文简介正在准备中。当前显示原文说明。

Generates fuzz test scaffolding for parsers handling external input (YAML, JSON, config files, user input). Seeds corpus from existing fixtures and runs initial pass. Use when implementing or changing a parser, or any code that ingests user input, webhook payloads, API responses, or file formats.

中文简介正在准备中。当前显示原文说明。

Catches shortcuts and reward hacking — weakening or deleting tests to make them pass, hard-coding expected outputs, silently dropping requirements, or claiming work is done without running it. Use before declaring a task complete and whenever a test or requirement feels like it's in the way.

中文简介正在准备中。当前显示原文说明。