Skip to content

Explore skills

Search every indexed skill by name, description, repository or instructions, then narrow the results.

Showing 12121–12150 of 14526 skills

zhang-yiming-perspectivealchaincyf/zhang-yiming-skill张一鸣(字节跳动/TikTok创始人)的思维框架与表达方式。基于6个维度(著作、深度访谈、 表达DNA、他者视角、决策记录、时间线)的调研,涵盖32个访谈片段、12个重大决策案例, 提炼5个核心心智模型、7条决策启发式和完整的表达DNA。 用途:作为思维顾问,用张一鸣的视角分析产品、组织、全球化、人才和个人成长问题。 当用户提到「用张一鸣的视角」「张一鸣会怎么看」「一鸣的思路」「zhang yiming perspective」时使用。 即使用户只是说「帮我用张一鸣的角度想想」「如果是字节会怎么做」「切换到张一鸣」也应触发。 即使用户说「字节怎么看」「头条的逻辑」「一鸣怎么选择」「一鸣」也应触发。Stars: 182Updated Claude CodeCodexUnverifiedInstall
adversarial-case-builderwanshuiyin/Anti-AutoresearchSynthesize 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".Stars: 180Updated Claude CodeCodexUnverifiedInstall
ai-style-impressionswanshuiyin/Anti-AutoresearchTransparent, 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".Stars: 180Updated Claude CodeCodexUnverifiedInstall
baseline-comparison-auditwanshuiyin/Anti-AutoresearchAudit 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?".Stars: 180Updated Claude CodeCodexUnverifiedInstall
citation-forensicswanshuiyin/Anti-AutoresearchCitation-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".Stars: 180Updated Claude CodeCodexUnverifiedInstall
consistency-auditwanshuiyin/Anti-AutoresearchFlagship 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".Stars: 180Updated Claude CodeCodexUnverifiedInstall
eval-design-forensicswanshuiyin/Anti-AutoresearchAudit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan 8-type / 3-category leakage taxonomy; the illegitimate-proxy / sampling-bias / pretraining-contamination subtypes hand off as needs_external_check, naming but NEVER running Oren-2023 exchangeability / Shi-2023 Min-K% / Golchin-2023 Time-Travel / BIG-bench canary); a load-bearing LLM judge is conflicted (same model/family as a compared system) or unvalidated (no human-agreement, no bias control) (HP-JUDGE-VALIDITY); a declared condition/metric is dropped or switched to favor the method, or 'best' is chosen with no held-out set (HP-SELECTIVE-REPORTING). Verdict-bearing at L0/L1 from the DESCRIBED protocol — NOT repo-gated like experiment-forensics; L2 only CONFIRMS against split/preprocessing/result files. A fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per pass) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Leakage and under-reporting are usually HONEST methodological errors — every finding describes a discrepancy to CHECK, never an accusation. An LLM generating GROUND-TRUTH labels is HP-FAKE-GT (experiment-forensics) — routed there, not here. Emits eval-design-forensics.findings.json; computes NO verdict. Detect-only. Triggers: "eval design audit", "evaluation validity", "train/test leakage", "data leakage", "is the score measuring generalization", "LLM judge bias", "is the judge validated", "selective reporting", "cherry-picked results", "评估设计审计", "评测有效性", "数据泄漏", "训练测试集泄漏", "裁判模型有没有验证", "选择性报告".Stars: 180Updated Claude CodeCodexUnverifiedInstall
evidence-ledgerwanshuiyin/Anti-AutoresearchBuild the deterministic evidence ledger (artifact_manifest.json + claims.json) that every other Anti-Autoresearch auditor reads. One pass inventories artifacts, derives the observability level (L0 PDF-only / L1 +LaTeX / L2 +repo+results) by fixed rule, and extracts span-anchored, hashed, checkable claims (numbers, comparisons, scope, method, baselines, citations, captions, table cells) into claims.json. An OPTIONAL additive cross-model pass ADDS span-anchored semantic claims — method, theorem statements with their assumptions, definitions, proof/derivation steps and equations, scope, baselines, conclusions, the motivation span, and reproducibility-artifact references (the proof, derivation, and structure anchors the family B/D/G auditors need) — it never invents a number, emits a finding, or computes a verdict. Run FIRST, before any audit skill. Triggers: "build the ledger", "extract claims", "prep for integrity audit", "evidence ledger", "建证据账本".Stars: 180Updated Claude CodeCodexUnverifiedInstall
experiment-forensicswanshuiyin/Anti-AutoresearchAudit 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".Stars: 180Updated Claude CodeCodexUnverifiedInstall
novelty-duplication-advisorywanshuiyin/Anti-AutoresearchMEMO-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".Stars: 180Updated Claude CodeCodexUnverifiedInstall
presentation-signalswanshuiyin/Anti-AutoresearchCheckable-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".Stars: 180Updated Claude CodeCodexUnverifiedInstall
proof-derivation-forensicswanshuiyin/Anti-AutoresearchFamily-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".Stars: 180Updated Claude CodeCodexUnverifiedInstall
anti-autoresearchwanshuiyin/Anti-AutoresearchEnd-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".Stars: 180Updated Claude CodeCodexUnverifiedInstall
ghm-gate-checkmattgierhart/PRD-driven-context-engineeringValidates gate criteria before PRD lifecycle advancement by delegating to the readiness scoring pipeline (scripts/readiness.py). Returns a graduated PASS / WARN / BLOCK verdict with top blockers and their causal chain. Triggers before advancing from v0.X to v0.Y or explicit `/ghm-gate-check`.Stars: 179Updated Claude CodeCodexUnverifiedInstall
ghm-harvestmattgierhart/PRD-driven-context-engineeringExtracts durable insights from temp/ files to SoT during EPIC Phase E. Triggers at EPIC completion or explicit `/ghm-harvest` invocation. Outputs new SoT entries and archive manifest.Stars: 179Updated Claude CodeCodexUnverifiedInstall
ghm-id-registermattgierhart/PRD-driven-context-engineeringValidates and registers new SoT IDs with cross-reference integrity. Triggers when creating BR-XXX, UJ-XXX, API-XXX, or CFD-XXX entries. Outputs formatted SoT entry with validated cross-references.Stars: 179Updated Claude CodeCodexUnverifiedInstall
ghm-self-installmattgierhart/PRD-driven-context-engineeringInstall the PRD-Driven Context Engineering methodology into a fresh OR existing repository — the subscription-native alternative to forking the whole repo. Runs an interactive wizard that seeds the framework (.claude/ hooks, skills, agents, rules, scripts) without clobbering product content. Triggers on "install the methodology", "adopt this into my repo", "self-install", "set up PRD lifecycle here", "onboard existing project". Outputs an installed framework + a verification report.Stars: 179Updated Claude CodeCodexUnverifiedInstall
ghm-sot-buildermattgierhart/PRD-driven-context-engineeringCreates new Source of Truth (SoT) files when existing templates don't fit your needs. Triggers on requests to create a new SoT file, add a new artifact type, or when user says "I need to track [X] but there's no SoT for it", "create SoT", "new source of truth". Outputs a properly structured SoT.*.md file with ID prefix, frontmatter, and update protocol.Stars: 179Updated Claude CodeCodexUnverifiedInstall
ghm-status-syncmattgierhart/PRD-driven-context-engineeringSynchronizes README.md Command Center with current project state. Triggers on gate changes, EPIC status changes, or explicit `/ghm-status-sync` invocation. Outputs updated README.md dashboard with current lifecycle stage, blockers, and metrics.Stars: 179Updated Claude CodeCodexUnverifiedInstall
ghm-template-syncmattgierhart/PRD-driven-context-engineeringDetect template version drift and guide migration to the latest template version. Compares current repo against the template, identifies what's outdated, and automates safe updates while protecting product-specific content. Triggers on requests to sync with template, update template version, check for template drift, or when user asks "sync template", "update to v3", "template drift", "check template version".Stars: 179Updated Claude CodeCodexUnverifiedInstall
initmattgierhart/PRD-driven-context-engineeringSeed a fresh (greenfield) repository with the PRD-Driven Context Engineering scaffold — PRD.md, SoT/ knowledge files, EPIC templates, domain-profile config, and agent MEMORY starters. Invoked as /prd-ce:init when the plugin is installed. The framework itself (skills, agents, hooks, scripts) ships LIVE in the plugin; this skill only plants the consumer-owned files the plugin cannot carry as behavior. Triggers on "/prd-ce:init", "set up PRD lifecycle here", "scaffold a new PRD-CE project", "initialize the methodology". Outputs a seeded scaffold + a verification report.Stars: 179Updated Claude CodeCodexUnverifiedInstall
prd-v01-problem-framingmattgierhart/PRD-driven-context-engineeringTransform vague product ideas into evidence-anchored problem statements for PRD v0.1 Spark. Triggers on starting new products/features, validating market opportunities, drafting PRD Why sections, or requests like "frame the problem", "define pain points", "write problem statement", "start v0.1", "what problem are we solving". Outputs structured problem tables with CFD evidence IDs.Stars: 179Updated Claude CodeCodexUnverifiedInstall
prd-v01-user-value-articulationmattgierhart/PRD-driven-context-engineeringTransform validated pain points into articulated user value statements for PRD v0.1 Spark. Triggers on completing problem framing, defining user outcomes, articulating value propositions, or requests like "what value do users get", "define outcomes", "articulate the benefit", "finish v0.1", "pain to value", "what do they gain". Outputs CFD- entries tagged as value hypotheses with evidence tiers. Follows Problem Framing skill in workflow.Stars: 179Updated Claude CodeCodexUnverifiedInstall
prd-v02-competitive-landscape-mappingmattgierhart/PRD-driven-context-engineeringMap the competitive landscape before positioning your product for PRD v0.2 Market Definition. Triggers on completing v0.1 Spark, analyzing competitors, researching market, or requests like "competitive analysis", "who else solves this", "market landscape", "what alternatives exist", "competitor research", "feature comparison". Outputs CFD- entries for competitive intelligence and BR- entries for positioning rules.Stars: 179Updated Claude CodeCodexUnverifiedInstall
prd-v02-product-type-classificationmattgierhart/PRD-driven-context-engineeringClassify product approach into one of six types (Clone, Unbundle, Undercut, Slice, Wrapper, Innovation) based on competitive landscape. Triggers on PRD v0.2 work after competitive analysis, or when user asks "what type of product should we build?", "should we clone or innovate?", "is this a fast-follow opportunity?", "how should we position against competitors?", "clone vs undercut", "unbundle vs slice", or requests help choosing product strategy. Outputs BR- entries for product type classification and inherited GTM constraints.Stars: 179Updated Claude CodeCodexUnverifiedInstall
prd-v03-features-value-planningmattgierhart/PRD-driven-context-engineeringDefine and prioritize features with strategic traceability during PRD v0.3 Commercial Model. Triggers on requests to define features, prioritize capabilities, scope MVP, map features to pricing tiers, identify parity vs. delta features, or when user asks "what features do we build?", "what's in MVP?", "which features matter?", "feature priority", "parity features", "what's our delta?". Consumes KPI- (Outcome Definition), BR- (Pricing Model, Moat), and CFD- (Market Moat Analysis) from v0.3. Outputs FEA- entries with strategic traceability and BR-FEA- governance rules. Feeds v0.4 User Journeys.Stars: 179Updated Claude CodeCodexUnverifiedInstall
prd-v03-moat-definitionmattgierhart/PRD-driven-context-engineeringAssess competitor defensibility and define our own moat strategy during PRD v0.3 Commercial Model. Triggers on requests to analyze competitor moats, define our defensibility, assess switching costs, identify vulnerabilities, find wedge opportunities, or when user asks "what's our moat?", "how defensible are they?", "where can we compete?", "switching costs?", "defensibility", "who to target". Consumes Competitive Landscape (v0.2) CFD- entries. Outputs CFD- entries for competitor moats and BR- entries for targeting rules and our defensibility strategy.Stars: 179Updated Claude CodeCodexUnverifiedInstall
prd-v03-outcome-definitionmattgierhart/PRD-driven-context-engineeringDefine measurable success metrics (KPIs) tied to product type during PRD v0.3 Commercial Model. Triggers on requests to define success metrics, set KPI targets, determine what to measure, establish go/no-go thresholds, or when user asks "how do we measure success?", "what metrics matter?", "what's our target?", "how do we know if this works?", "define KPIs", "success criteria". Consumes Product Type Classification (BR-) from v0.2. Outputs KPI- entries with thresholds, evidence sources, and downstream gate linkages.Stars: 179Updated Claude CodeCodexUnverifiedInstall
prd-v03-pricing-modelmattgierhart/PRD-driven-context-engineeringSelect and validate pricing model for PRD v0.3 Commercial Model. Triggers on requests to set pricing, choose monetization model, design pricing tiers, validate willingness to pay, or when user asks "how much should we charge?", "what pricing model?", "freemium vs paid?", "how to structure tiers?", "price point?". Consumes Competitive Landscape (CFD-) and Product Type (BR-) from v0.2. Outputs BR- entries for pricing rules, tier boundaries, and competitive positioning.Stars: 179Updated Claude CodeCodexUnverifiedInstall
prd-v04-persona-definitionmattgierhart/PRD-driven-context-engineeringSynthesize behavioral personas from prior stage evidence for journey mapping and marketing during PRD v0.4 User Journeys. Triggers on requests to define personas, create user profiles, identify target users, or when user asks "who are our users?", "define personas", "user profiles", "target users", "persona creation", "who uses this product?". Consumes CFD- (v0.1-v0.3), BR- (targeting from v0.3 Moat), FEA- (v0.3 Feature Value Planning). Outputs PER- entries with behavioral profiles and feature relationships. Feeds v0.4 User Journey Mapping.Stars: 179Updated Claude CodeCodexUnverifiedInstall