Browse Skills — Page 72

error-diagnostics-error-analysis

diegosouzapw/awesome-omni-skills

Error Analysis and Resolution workflow skill. Use this skill when the user needs You are an expert error analysis specialist with deep expertise in debugging distributed systems, analyzing production incidents, and implementing comprehensive observability solutions and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

error-diagnostics-error-analysis-v2

diegosouzapw/awesome-omni-skills

Error Analysis and Resolution workflow skill. Use this skill when the user needs You are an expert error analysis specialist with deep expertise in debugging distributed systems, analyzing production incidents, and implementing comprehensive observability solutions and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

error-diagnostics-error-trace

diegosouzapw/awesome-omni-skills

Error Tracking and Monitoring workflow skill. Use this skill when the user needs You are an error tracking and observability expert specializing in implementing comprehensive error monitoring solutions. Set up error tracking systems, configure alerts, implement structured logging, and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

error-diagnostics-error-trace-v2

diegosouzapw/awesome-omni-skills

Error Tracking and Monitoring workflow skill. Use this skill when the user needs You are an error tracking and observability expert specializing in implementing comprehensive error monitoring solutions. Set up error tracking systems, configure alerts, implement structured logging, and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

error-diagnostics-smart-debug

diegosouzapw/awesome-omni-skills

error-diagnostics-smart-debug workflow skill. Use this skill when the user needs working with error diagnostics smart debug and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

error-diagnostics-smart-debug-v2

diegosouzapw/awesome-omni-skills

error-diagnostics-smart-debug workflow skill. Use this skill when the user needs working with error diagnostics smart debug and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

error-handling

affaan-m/ECC

Patterns for robust error handling across TypeScript, Python, and Go. Covers typed errors, error boundaries, retries, circuit breakers, and user-facing error messages.

error-handling-patterns

wshobson/agents

Master error handling patterns across languages including exceptions, Result types, error propagation, and graceful degradation to build resilient applications. Use when implementing error handling, designing APIs, or improving application reliability.

error-handling-patterns

diegosouzapw/awesome-omni-skills

Error Handling Patterns workflow skill. Use this skill when the user needs Build resilient applications with robust error handling strategies that gracefully handle failures and provide excellent debugging experiences and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

error-handling-patterns-v2

diegosouzapw/awesome-omni-skills

Error Handling Patterns workflow skill. Use this skill when the user needs Build resilient applications with robust error handling strategies that gracefully handle failures and provide excellent debugging experiences and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

error-messages

github/gh-aw

Write consistent, actionable validation error messages in gh-aw.

error-monitoring

TerminalSkills/skills

>-

error-pattern-safety

github/gh-aw

Apply safe error-pattern matching rules for agentic engines.

errors

yonatangross/orchestkit

Error pattern analysis and troubleshooting for Claude Code sessions. Use when handling errors, fixing failures, troubleshooting issues.

erstantwort-generator

Klotzkette/claude-fuer-deutsches-recht

Hauptskill: erstellt die formelle Erstantwort-E-Mail an einen potenziellen Mandanten. Enthaelt Dank fuer die Anfrage, exakte Anrede aus der Eingangsmail, Hinweis auf telefonische Terminvergabe, Bitte um Sachverhaltsschilderung per E-Mail, Hinweis auf den Transkriptionsservice mit DSGVO-Einwilligungserfordernis, Mandatsverhaeltnis-Disclaimer und Schlussformel. Laedt wenn der Nutzer 'Erstantwort schreiben', 'Antwortmail erstellen', 'Eingangsbestaetigung', 'Erstreaktion Mandant' oder 'Antwort auf Anfrage' sagt.

erstgespraech-mandatsannahme

Klotzkette/claude-fuer-deutsches-recht

Strukturierter Erstgespraechsleitfaden fuer Agrar-, Forst- und Lebensmittelrecht: Erfassung der Konstellation, Konflikt- und GwG-Check, Vollmacht, Streitwert/Gebuehrenvereinbarung, Fristen-Erstprognose und Handlungsweichen.

erstgespraech-und-mandatsannahme

Klotzkette/claude-fuer-deutsches-recht

Mandatsannahme im Zeugnisrecht. Eingangsbestaetigung an den Mandanten mit Dank fuer das uebersandte Zeugnis, Anforderung der noch fehlenden Unterlagen (Arbeitsvertrag, Aenderungsvereinbarungen, Kuendigungsschreiben, Vorzeugnisse, Aufgabenbeschreibung, Beurteilungen, Krankheits- und Fehlzeitenuebersicht, Abmahnungen, Schriftwechsel zum Zeugnis). Strukturiertes Erstgespraech mit Zielklaerung, Fristen, Vergleichsbereitschaft, Vergueterungsvereinbarung und Hinweis auf Beweislast.

es5-compliance

serac-labs/serac

Enforce ES5-only syntax for ServiceNow server-side scripts (Rhino engine) — convert const/let, arrow functions, template literals, destructuring, for-of, and async/await to ES5 equivalents.

escalate

doodledood/manifest-dev

Structured escalation when /do hits an unrecoverable blocker. Surfaces what was tried, why it failed, and what the user can decide. Called by /do when work is blocked, cannot proceed, hits an unrecoverable failure, needs a user decision, or gets stuck.

escalation

cloudflare/agents

Decide when and how to escalate a customer conversation to a human agent. Use when a request is high-risk, the customer is frustrated, or the issue is outside what you can resolve.

escalation-brief

vm0-ai/vm0-skills

Prepare structured escalation packages for engineering, product, security, or leadership with reproduction steps, business impact, and full context. Activate when a support issue needs to go beyond the support team, when writing an escalation document, when evaluating whether a problem warrants escalation, or when tracking follow-through after handing off an issue.

escalation-flagger

anthropics/claude-for-legal

>

escape-technique

yogsoth-ai/de-anthropocentric-research-engine

Identify dominant thinking pattern and escape it via deliberate pattern-breaking.

esg-greenwashing-csrd

Klotzkette/claude-fuer-deutsches-recht

Unternehmen muss ESG-Bericht erstellen oder verteidigt Greenwashing-Vorwurf. CSRD VO 2022/2464 gestaffelt seit 2024 ESRS-Standards Doppelte Wesentlichkeit EU-Taxonomie VO 2020/852 SFDR. Normen UWG § 5 Irrefuehrung BGH I ZR 252/22 klimaneutral EU-Green-Claims-Richtlinie 2024. Pruefraster Nachhaltigkeitsbericht-Pflicht Wesentlichkeitsanalyse Greenwashing-Risiko-Check. Output ESG-Bericht-Struktur Greenwashing-Verteidigung Werbe-Substantiierung. Abgrenzung zu lksg-csddd-lieferkettensorgfalt (Lieferkette) und umweltrecht-transaktionen-dd (M&A).

esg-reporting

mkurman/zorai

ESG (Environmental, Social, Governance) reporting and analytics. SASB, TCFD, GRI, and CDP frameworks. Carbon accounting, supply chain sustainability, diversity metrics, and regulatory disclosure support.

esignatures-io-automation

ComposioHQ/awesome-claude-skills

"Automate Esignatures IO tasks via Rube MCP (Composio). Always search tools first for current schemas."

eskalations-marker

Klotzkette/claude-fuer-deutsches-recht

Ordnet ein Vertragsproblem dem richtigen Genehmiger per Eskalationsmatrix aus dem Praxisprofil zu und erstellt die Genehmigungsanfrage. Laden, wenn der Nutzer fragt „wer muss das genehmigen\", „eskalieren\", „braucht das GC-Freigabe\", „Genehmigung einholen\" oder ein anderer Skill ein Problem identifiziert, das die Kompetenz des Prüfers übersteigt.

eslint

TerminalSkills/skills

>

eslint-configuration

TheBushidoCollective/han

Use when eSLint configuration including config files, extends, plugins, and environment setup.

eslint-custom

TheBushidoCollective/han

Use when custom ESLint rules and plugins including rule development, AST traversal, and publishing.

eslint-plugin-custom-rule

coinbase/cds

USE THIS when asked to create a new eslint plugin rule for the eslint-plugin-cds package

eslint-rules

TheBushidoCollective/han

Use when eSLint built-in rules including rule configuration, severity levels, and disabling strategies.

esm

K-Dense-AI/scientific-agent-skills

Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel proteins; generating protein embeddings; performing inverse folding; or conducting protein engineering tasks. Supports both local model usage and cloud-based Forge API for scalable inference.

espocrm-automation

ComposioHQ/awesome-claude-skills

"Automate Espocrm tasks via Rube MCP (Composio). Always search tools first for current schemas."

esputnik-automation

ComposioHQ/awesome-claude-skills

"Automate Esputnik tasks via Rube MCP (Composio). Always search tools first for current schemas."

estimate

pixel-cellar/Claude-Code-Game-Studios

通过分析复杂度、依赖关系、历史速度和风险因素来估算任务工作量。生成包含置信水平的结构化估算。

estimation-fermi

lyndonkl/claude

Decomposes complex unknowns into estimable components to produce rapid order-of-magnitude answers with bounded uncertainty. Use when making quick estimates (market sizing, resource planning, feasibility checks), bounding unknowns with upper/lower limits, sanity-checking strategic assumptions, or when user mentions Fermi estimation, back-of-envelope calculation, order of magnitude, ballpark estimate, or triangulation.

etermin-automation

ComposioHQ/awesome-claude-skills

"Automate Etermin tasks via Rube MCP (Composio). Always search tools first for current schemas."

etetoolkit

K-Dense-AI/scientific-agent-skills

Phylogenetic tree toolkit (ETE). Tree manipulation (Newick/NHX), evolutionary event detection, orthology/paralogy, NCBI taxonomy, visualization (PDF/SVG), for phylogenomics.

etf-analysis

HKUDS/Vibe-Trading

ETF分析：产品筛选、费率对比、跟踪误差、流动性评估、策略应用与中国市场ETF量化配置框架。

ethers-js

TerminalSkills/skills

>-

etherscan

TermiX-official/cryptoclaw

Query block explorer APIs (Etherscan, BSCScan, Polygonscan, etc.) for transactions, contracts, and gas data.

ethics-safety-impact

lyndonkl/claude

Guides structured identification of potential harms, benefits, and differential impacts across stakeholder groups for decisions affecting people. Covers stakeholder mapping, fairness evaluation, risk mitigation design, and monitoring. Use when decisions could affect groups differently, need to anticipate harms/benefits, assess fairness and safety, identify vulnerable populations, or when user mentions ethical review, impact assessment, differential harm, safety analysis, bias audit, or responsible AI/tech.

ETL Pipeline

aAAaqwq/AGI-Super-Team

Design and automate Extract, Transform, Load data pipelines for data integration and analytics

etsy

vm0-ai/vm0-skills

Etsy Open API v3 for shop and listing management. Use when user mentions "Etsy", "shop listings", "Etsy orders", "product listings", or "Etsy seller".

eu-ai-act-specialist

alirezarezvani/claude-skills

EU AI Act (Regulation (EU) 2024/1689) operational compliance for compliance teams. Three Article-level decisions: (1) What's the risk tier of this AI system — prohibited (Art. 5), high-risk (Art. 6 + Annex III), limited-risk (Art. 50), or minimal-risk? (2) For high-risk systems, what's the Article 43 conformity assessment route (Module A internal control vs Module H full QMS + notified body) and what goes in the Annex IV technical documentation? (3) Per organizational role (provider / deployer / importer / distributor / authorized representative), what are the active obligations and deadlines? Use during AI system intake review, when planning conformity assessment, or when scoping deployer obligations. Cites Articles + Annexes for every output. NOT executive AI strategy (see chief-ai-officer-advisor). NOT a legal substitute.

eu-bekanntmachung-marktdefinition-2024

Klotzkette/claude-fuer-deutsches-recht

Skill zur neuen EU-Kommissions-Bekanntmachung zur Marktdefinition (Februar 2024) und ihrer praktischen Anwendung. Vergleich zur Bekanntmachung von 1997. Neue Elemente: digitale Maerkte Innovationswettbewerb Datenmaerkte beidseitiger SSNIP-Test und qualitative Evidenz. Fundstelle ABl 2024/C 1645.

eu-datenbank-registrierung-art-49-und-71

Klotzkette/claude-fuer-deutsches-recht

Registrierungspflichten in der EU-Datenbank nach Art. 49 und 71 KI-VO: Anbieter vor Inverkehrbringen oeffentliche Stellen als Betreiber vor Verwendung. Inhalt nach Anhang VIII Fristen Vertraulichkeit oeffentliche Zugaenglichkeit.

eu-vorabentscheidung-pruefen

Klotzkette/claude-fuer-deutsches-recht

Prueft die Voraussetzungen des Vorabentscheidungsersuchens nach Art. 267 AEUV: Vorlagebefugnis und -pflicht, CILFIT-Ausnahmen (acte clair/eclaire), Consorzio-Erweiterung, Vorlagepflicht letzter Instanz, Formulierung der Vorlagefrage, curia.europa.eu-Fundstellen.

eugh-rechtsprechung-leitentscheidungen

Klotzkette/claude-fuer-deutsches-recht

Einschlägige EuGH/EuG/BGH/BKartA-Leitentscheidungen zur Marktdefinition mit Pinpoint-Zitaten: Continental Can Rs 6/72 United Brands Rs 27/76 Hoffmann-La Roche Rs 85/76 Michelin I Rs 322/81 Tetra Pak II T-83/91 Microsoft T-201/04 Google Shopping T-612/17 Google Android T-604/18 Servier C-176/19 und weitere.

euipo-widerspruchsverfahren

Klotzkette/claude-fuer-deutsches-recht

EUIPO-Widerspruchsverfahren nach Art. 8 UMV: Verwechslungsgefahr Art. 8 I lit. b, Bekanntheitsschutz Art. 8 V, Beschwerdekammer (BoA), Gebuehren, Fristen, Benutzungsnachweis. Laedt, wenn der Nutzer 'EUIPO Widerspruch', 'Opposition EUIPO', 'Verwechslungsgefahr EU', 'Bekanntheitsschutz EUIPO' oder 'BoA Beschwerde' sagt.

europarecht-anwendbarkeit-vorrang-vorabentscheidung

Klotzkette/claude-fuer-deutsches-recht

Europarecht in der Hausarbeit Anwendungs-Vorrang VO direkt geltend RL Umsetzungs-Pflicht richtlinien-konforme Auslegung Marleasing Vorabentscheidungs-Verfahren Art 267 AEUV. EU-konforme Auslegung nationales Recht. EuGH-Linien Grundfreiheiten Diskriminierungs-Verbot. Grundrechte-Charta GRC. Beispiele Verbraucherrechte-RL Datenschutz-GVO Lieferketten-RL.

europarecht-beihilfen-vergaben

Klotzkette/claude-fuer-deutsches-recht

Prüft staatliche Mittel, Vorteil, Selektivität, Wettbewerb, Notifizierung, De-minimis, AGVO und Vergabe-Schnittstellen.

europarecht-delegierte-durchfuehrungsakte

Klotzkette/claude-fuer-deutsches-recht

Prüft Level-2- und Level-3-Regulierung, delegierte Akte, Durchführungsakte, RTS ITS Leitlinien und Fristen.

europarecht-deutscher-denkfehler-scanner

Klotzkette/claude-fuer-deutsches-recht

Findet typische deutsche Missverständnisse im Europarecht und übersetzt sie in unionsrechtlich saubere Prüfungsschritte.

europarecht-gesetzgebung-trilog

Klotzkette/claude-fuer-deutsches-recht

Erklärt Kommissionsvorschlag, Rat, Parlament, Trilog, Änderungsanträge, Umsetzungsfenster und Lobbying-Strategie.

europarecht-grundfreiheiten-binnenmarkt

Klotzkette/claude-fuer-deutsches-recht

Prüft Waren, Personen, Dienstleistungen, Niederlassung, Kapital, Beschränkung, Rechtfertigung und Verhältnismäßigkeit.

europarecht-grundrechte-charta

Klotzkette/claude-fuer-deutsches-recht

Prüft Charta-Anwendbarkeit, Grundrechtsstandard, EMRK-Bezug und Zusammenspiel mit deutschem Verfassungsrecht.

europarecht-klagearten-eugh

Klotzkette/claude-fuer-deutsches-recht

Ordnet Nichtigkeitsklage, Untätigkeitsklage, Amtshaftung, Vorabentscheidung und nationale Rechtsschutzwege ein.

europarecht-kommandocenter

Klotzkette/claude-fuer-deutsches-recht

Startet EU-Rechtsmandate mit Kompetenzcheck, Rechtsquellenhierarchie, Denkfehler-Scan, Verfahrensweg und Arbeitsprodukt.

europarecht-mandantenmemo

Klotzkette/claude-fuer-deutsches-recht

Erstellt verständliche EU-Rechtsmemos mit Rechtsquellen, Ampel, Umsetzungsplan, Risiken und Management-Entscheidungen.

europarecht-nationales-verfahren-effektivitaet

Klotzkette/claude-fuer-deutsches-recht

Prüft Äquivalenz, Effektivität, nationale Verfahrensautonomie, Rechtsschutz und unionsrechtliche Grenzen.

europarecht-quality-gate

Klotzkette/claude-fuer-deutsches-recht

Prüft jedes EU-Arbeitsprodukt auf Rechtsquelle, CELEX, Anwendungsbeginn, nationale Umsetzung, Verfahren und offene Vorlagefragen.

europarecht-richtlinie-umsetzung

Klotzkette/claude-fuer-deutsches-recht

Führt Richtlinienprüfung von Ziel, Frist, Umsetzung, Auslegung, Defizit, Sanktion und Mandantenrisiko.

europarecht-simulation-behoerde-gericht

Klotzkette/claude-fuer-deutsches-recht

Simuliert EU-bezogene Behörden-, Gerichts- und Kommissionsverfahren mit Lernkurve für junge Juristinnen und Juristen.

europarecht-verordnung-beschluss-soft-law

Klotzkette/claude-fuer-deutsches-recht

Unterscheidet EU-Verordnung, Richtlinie, Beschluss, Empfehlung, Leitlinie, Mitteilung und behördliche Praxiswirkung.

europarecht-vertragsverletzung-durchsetzung

Klotzkette/claude-fuer-deutsches-recht

Erklärt Beschwerden, Pilotverfahren, Mahnschreiben, Reasoned Opinion, EuGH-Verfahren und nationale Parallelwege.

europarecht-vorlageverfahren-art-267

Klotzkette/claude-fuer-deutsches-recht

Entwickelt Vorlagefragen, Entscheidungserheblichkeit, letztinstanzliche Vorlagepflicht und Verfahrensstrategie.

europarecht-vorrang-unmittelbare-wirkung

Klotzkette/claude-fuer-deutsches-recht

Prüft Anwendungsvorrang, unmittelbare Wirkung, richtlinienkonforme Auslegung und Staatshaftung ohne Vermischung.

europarecht-wettbewerb-kartell

Klotzkette/claude-fuer-deutsches-recht

Ordnet Art. 101, Art. 102, Fusionskontrolle, Vertical Block Exemption, DMA und nationale Schnittstellen ein.

europarechtskonformitaet

Klotzkette/claude-fuer-deutsches-recht

Gesetzesentwurf oder Verordnung auf Vereinbarkeit mit EU-Recht pruefen. Anwendungsfall Referent oder Verband fragt ob nationales Vorhaben mit EU-Recht vereinbar ist oder ob Notifizierungspflicht besteht. Primaerrecht EUV AEUV Grundrechtecharta Sekundaerrecht Verordnungen Richtlinien. Pruefung Anwendungsbereich Schutzbereich Eingriff Rechtfertigung Verhaeltnismaessigkeit. Notifizierungspflicht Richtlinie 2015/1535 technische Vorschriften IT-Vorschriften. Subsidiaritaet Verhaeltnismaessigkeit Art. 5 EUV Vorlagepflicht Art. 267 AEUV. Output Pruefgutachten ein bis drei Seiten Notifizierungs-Vermerk Empfehlung. Abgrenzung zu verfassungsmaessigkeit-quercheck nationales Verfassungsrecht.

eva-skill

openai/plugins

Submit compact EVA REST requests for species metadata and archived variant lookups. Use when a user wants concise European Variation Archive summaries

eval

alirezarezvani/claude-skills

Evaluate and rank agent results by metric or LLM judge for an AgentHub session. Use when the user runs /hub:eval or asks to score, compare, or pick a winner among completed AgentHub agents.

eval-audit

hamelsmu/evals-skills

>

eval-cache

closedloop-ai/claude-plugins

|

eval-config

indranilbanerjee/digital-marketing-pro

Configure content eval settings. Use when: adjusting score thresholds, dimension weights, or auto-reject rules.

eval-content

indranilbanerjee/digital-marketing-pro

Evaluate content quality. Use when: scoring drafts, checking hallucinations, or assessing brand voice compliance.

eval-driven-dev

github/awesome-copilot

>

eval-harness

affaan-m/ECC

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles

eval-performance

microsoft/testfx

Guide for diagnosing and improving MSBuild project evaluation performance. Only activate in MSBuild/.NET build context. USE FOR: builds slow before any compilation starts, high evaluation time in binlog analysis, expensive glob patterns walking large directories (node_modules, .git, bin/obj), deep import chains (>20 levels), preprocessed output >10K lines indicating heavy evaluation, property functions with file I/O ($([System.IO.File]::ReadAllText(...))), multiple evaluations per project. Covers the 5 MSBuild evaluation phases, glob optimization via DefaultItemExcludes, import chain analysis with /pp preprocessing. DO NOT USE FOR: compilation-time slowness (use build-perf-diagnostics), incremental build issues (use incremental-build), non-MSBuild build systems. INVOKES: dotnet msbuild -pp:full.xml for preprocessing, /clp:PerformanceSummary.

eval-quality-workflow

UKGovernmentBEIS/inspect_evals

Fix or review a single evaluation against all EVALUATION_CHECKLIST.md standards. Use "fix" mode to refactor an eval into compliance, or "review" mode to assess compliance without making changes. Use when user asks to fix, review, or check an evaluation's quality. Trigger when the user asks you to run the "Fix An Evaluation" or "Review An Evaluation" workflow. Do NOT use for reviewing ALL evals against a single code quality standard (use code-quality-review-all instead).

eval-report-workflow

UKGovernmentBEIS/inspect_evals

Create an evaluation report for a README by selecting models, estimating costs, running evaluations, and formatting results tables. Use when user asks to make/create/generate an evaluation report. Trigger when the user asks you to run the "Make An Evaluation Report" workflow.

eval-suite

indranilbanerjee/digital-marketing-pro

Batch evaluate multiple content pieces. Use when: scoring a content library, campaign assets, or deliverable set.

eval-validity-review

UKGovernmentBEIS/inspect_evals

Review a single evaluation's validity — whether its claims hold up, whether its name is accurate, whether samples can be both succeeded and failed at, and whether scoring measures ground truth. Use when user asks to check validity of an eval, or as part of the Master Checklist workflow. Do NOT use for code quality or test coverage (use eval-quality-workflow or ensure-test-coverage instead).

eval-writer

langchain-ai/deepagentsjs

"Create new eval suites for the deepagentsjs monorepo. Handles dataset design, test case scaffolding, scoring logic, vitest configuration, and LangSmith integration. Use when the user asks to: (1) create an eval, (2) write an evaluation, (3) add a benchmark, (4) build an eval suite, (5) evaluate agent behaviour, (6) add test cases for a capability, or (7) implement an existing benchmark (e.g. oolong, AgentBench, SWE-bench). Trigger on phrases like 'create eval', 'new eval', 'add eval', 'benchmark', 'evaluate', 'eval suite', 'write evals for'."

evaluate

ghaida/intent

>

evaluate-dependencies

686f6c61/alfred-dev

Usar para evaluar si una dependencia merece la pena antes de añadirla. Activar cuando el usuario quiera añadir una librería, saber si merece la pena esta dependencia, evaluar un paquete antes de instalarlo, hacer npm install o pip install de algo nuevo, buscar alternativas a una librería o decidir si implementar algo internamente.

evaluate-plugin

openai/plugins

Evaluate a local Codex plugin in engineer-friendly language. Use when the user says "evaluate this plugin", "audit this plugin", "why did this score that way", "what should I fix first", "help me benchmark this plugin", or asks for a plugin-wide report before comparing versions.

evaluate-rag

hamelsmu/evals-skills

>

evaluate-skill

openai/plugins

Evaluate a local Codex skill in engineer-friendly terms. Use when the user says "evaluate this skill", "give me an analysis of the game dev skill", "audit this skill", "why did this score that way", "what should I fix first", or asks for a skill-specific report before benchmarking it.

evaluating-code-models

Orchestra-Research/AI-Research-SKILLs

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

evaluating-cosmos-policy

Orchestra-Research/AI-Research-SKILLs

Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines.

evaluating-llms-harness

NousResearch/hermes-agent

lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).

evaluating-threat-intelligence-platforms

mukul975/Anthropic-Cybersecurity-Skills

>

evaluation

guanyang/antigravity-skills

This skill should be used when building agent evaluation systems: deterministic checks, regression suites, multi-dimensional rubrics, quality gates, production monitoring, baseline comparison, and outcome measurement for agent pipelines.

evaluation-filtering

yogsoth-ai/de-anthropocentric-research-engine

Multi-dimensional evaluation and tiered filtering of generated ideas. Orchestrates novelty assessment → feasibility check → ranking → selection.

evaluation-methodology

wshobson/agents

"PluginEval quality methodology — dimensions, rubrics, statistical methods, and scoring formulas. Use this skill when understanding how plugin quality is measured, when interpreting a low score on a specific dimension, when deciding how to improve a skill's triggering accuracy or orchestration fitness, when calibrating scoring thresholds for your marketplace, or when explaining quality badges to external partners like Neon."

evaluation-protocol-comparison

yogsoth-ai/de-anthropocentric-research-engine

Compare implementation differences of same benchmark across papers

evaluation-rubrics

lyndonkl/claude

Designs structured scoring tools with explicit criteria, performance scales, and descriptors for consistent, transparent quality assessment. Use when need quality criteria and scoring scales to evaluate work consistently, compare alternatives objectively, set acceptance thresholds, reduce subjective bias, or when user mentions rubric, scoring criteria, quality standards, evaluation framework, inter-rater reliability, or grading/assessing work.

evaluation-v2

diegosouzapw/awesome-omni-skills

Evaluation Methods for Agent Systems workflow skill. Use this skill when the user needs Build evaluation frameworks for agent systems. Use when testing agent performance systematically, validating context engineering choices, or measuring improvements over time and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.