Explore skills
Showing 19291–19320 of 36859 skills
krillinai/OpenCreator
Stars: 14kClaude CodeCodexUse to build or rebuild the documentation site of the project from the repo, the architecture, the data lineage, the call graph, the data model, the data quality, the runs and the data catalog.
DataWithBaraa/claude-code-data-engineering-skills
Stars: 102Claude CodeCodexBuild applications with Univer Office SDK, covering the Web SDK (browser Office editors, headless Sheets and Docs in Node), Server SDK (self-hosted OT collaboration, storage, auth, Office import/export), AI SDK (agent-operated Office CLIs, reviewable Worktrees), and Binding SDK (plain HTML pages bound to live Sheet data). Use when starting or designing any Univer-based app or choosing Univer packages, including when the user describes a spreadsheet, document, collaboration, or AI-office need without naming a Univer package.
dream-num/skills
Stars: 79Claude CodeCodexTransparent, 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".
wanshuiyin/Anti-Autoresearch
Stars: 180Claude CodeCodexAudit 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?".
wanshuiyin/Anti-Autoresearch
Stars: 180Claude CodeCodexAudit 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".
wanshuiyin/Anti-Autoresearch
Stars: 180Claude CodeCodexAudit 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".
wanshuiyin/Anti-Autoresearch
Stars: 180Claude CodeCodexMEMO-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".
wanshuiyin/Anti-Autoresearch
Stars: 180Claude CodeCodexCheckable-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".
wanshuiyin/Anti-Autoresearch
Stars: 180Claude CodeCodexEnd-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".
wanshuiyin/Anti-Autoresearch
Stars: 180Claude CodeCodexMap dbt `schema.yml` / `properties.yml` models and sources into ktx semantic-layer overlays and column notes. Covers `sources:` vs `models:`, column `data_tests` (not_null, unique, accepted_values, relationships), and how bundle-time writes complement manifest backfill from git sync. Load when the WorkUnit's `skillNames` includes `dbt_ingest` or when raw files are dbt YAML under `models/` / `sources/`.
Kaelio/ktx
Stars: 1.6kClaude CodeCodexClassify and resolve conflicts detected during bundle ingest (structural duplicates, definitional contradictions, near-duplicate clusters, re-ingest changes, evictions).
Kaelio/ktx
Stars: 1.6kClaude CodeCodexInspect ADR health read-only; optionally select one ADR with --adr N.
arbiterForge/codeArbiter
Stars: 153Claude CodeCodexInspect ADR health read-only; optionally select one ADR with --adr N.
arbiterForge/codeArbiter
Stars: 153Claude CodeCodexUse when a user asks to edit Russian prose that sounds formulaic or machine-generated while preserving its meaning and authorial voice.
ilyautov/humanizer-ru
Stars: 575Claude CodeCodexUse when a user asks to edit Russian prose that sounds formulaic or machine-generated while preserving its meaning and authorial voice.
ilyautov/humanizer-ru
Stars: 575Claude CodeCodex請求書の画像を読み取り構造化データを返す。 他のスキルから呼び出されるほか、直接ユーザーが呼び出すことも可能。
kazukinagata/shinkoku
Stars: 372Claude CodeCodex支払調書の画像を読み取り構造化データを返す。 他のスキルから呼び出されるほか、直接ユーザーが呼び出すことも可能。
kazukinagata/shinkoku
Stars: 372Claude CodeCodex源泉徴収票の画像を読み取り構造化データを返す。 他のスキルから呼び出されるほか、直接ユーザーが呼び出すことも可能。
kazukinagata/shinkoku
Stars: 372Claude CodeCodexAutomate 21risk tasks via Rube MCP (Composio). Always search tools first for current schemas.
composio-community/awesome-codex-skills
Stars: 17kClaude CodeCodexAutomate 2chat tasks via Rube MCP (Composio). Always search tools first for current schemas.
composio-community/awesome-codex-skills
Stars: 17kClaude CodeCodexAutomate SEO research with Ahrefs -- analyze backlink profiles, research keywords, track domain metrics history, audit organic rankings, and perform batch URL analysis through the Composio Ahrefs integration.
composio-community/awesome-codex-skills
Stars: 17kClaude CodeCodexAutomate Anthropic Admin tasks via Rube MCP (Composio): API keys, usage, workspaces, and organization management. Always search tools first for current schemas.
composio-community/awesome-codex-skills
Stars: 17kClaude CodeCodexAutomate web scraping and data extraction with Apify -- run Actors, manage datasets, create reusable tasks, and retrieve crawl results through the Composio Apify integration.
composio-community/awesome-codex-skills
Stars: 17kClaude CodeCodexAutomate Apollo.io lead generation -- search organizations, discover contacts, enrich prospect data, manage contact stages, and build targeted outreach lists -- using natural language through the Composio MCP integration.
composio-community/awesome-codex-skills
Stars: 17kClaude CodeCodexAutomate recruiting and hiring workflows in Ashby -- manage candidates, jobs, applications, interviews, and notes through natural language commands.
composio-community/awesome-codex-skills
Stars: 17kClaude CodeCodexAutomate Attio CRM operations -- search records, query contacts and companies with advanced filters, manage notes, list attributes, and navigate your relationship data -- using natural language through the Composio MCP integration.
composio-community/awesome-codex-skills
Stars: 17kClaude CodeCodexBraintree Automation: manage payment processing via Stripe-compatible tools for customers, subscriptions, payment methods, and transactions
composio-community/awesome-codex-skills
Stars: 17kClaude CodeCodexAutomate Capsule CRM tasks via Rube MCP (Composio): contacts, opportunities, cases, tasks, and pipeline management. Always search tools first for current schemas.
composio-community/awesome-codex-skills
Stars: 17kClaude CodeCodexAutomate Capsule CRM operations -- manage contacts (parties), run structured filter queries, track tasks and projects, log entries, and handle organizations -- using natural language through the Composio MCP integration.
composio-community/awesome-codex-skills
Stars: 17kClaude CodeCodex