Use when the user wants to A/B test content variations — compare quality scores across different prompt approaches, headline styles, or content versions to find what works best.
Score 70/100
Adapte un prompt d'un modèle/plateforme à un autre en préservant l'intention. À utiliser pour porter un prompt de ChatGPT vers Claude, de Midjourney vers DALL-E, ou entre modèles.
Score 70/100
Optimisation systématique des prompts d'agents pour améliorer performance et fiabilité. Se déclenche avec "optimiser prompt agent", "agent prompt", "améliorer mon agent", "prompt…
Score 70/100
Rewrite user prompts for clarity, fix typos, and make them more actionable before execution. Display the rewrite for approval.
Score 70/100
Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices.
Score 70/100
CLI for querying Prometheus and PromQL-compatible engines (Thanos, Cortex, VictoriaMetrics, Grafana Mimir, Grafana Tempo...) — instant queries, range queries, metric discovery…
Score 70/100
Design QA audit — red flags, severity classification, visual quality scorecard. Use when asked to "QA the design", "check visual quality", "design review before launch", "visual…
Score 70/100
Create formal, verifiable proofs of claims with machine-checkable reasoning. Use when asked to prove, verify, fact-check, or rigorously establish whether a claim is true or false…
Score 70/100
Enforce validation and evidence before declaring work complete. Use for acceptance criteria and done gates.
Score 70/100
Proof writing and verification techniques for mathematical reasoning. Covers 13 proof strategies with canonical worked examples — direct, contrapositive, contradiction, cases,…
Score 70/100
Corrige et améliore un texte en français (grammaire, style, clarté, ton). À utiliser quand l'utilisateur veut relire, corriger ou améliorer un texte français.
Score 70/100
Audit real estate investment software for IRR/NPV/cap rate/cash-on-cash return calculations, pro forma income modeling (GPR, vacancy, rent growth, NNN pass-throughs), equity…
Score 70/100
Accept, defer, dismiss, or resolve a proposal. For accepted proposals, asks how to proceed — create a session task or note for manual implementation.
Score 70/100
Creates a proposal for a high-leverage improvement discovered during work. Only for ideas with real impact — not trivial fixes.
Score 70/100
Lists all proposals with their status, source, and age. Shows auto-detected proposals prominently. Activates on messages like "what have you noticed", "any improvements", "any…
Score 70/100
Analyze manual edits to prose-craft output and propose improvements to registers, skill rules, and review agents. Invoke after manually editing a piece generated with prose-craft.
Score 70/100
Locate an existing OpenProse installation using a prioritized signal chain — env var, AIWG config, AIWG-local install, project plugin manifest, user home directory, or global CLI.
Score 70/100
Install OpenProse for AIWG use when no existing installation is found. Tries npx skills add first, falls back to git clone, then saves the resolved path to .aiwg/config.json.
Score 70/100
Read and parse an OpenProse program file, extracting its contract (requires, ensures, strategies, errors, invariants) and services into a structured representation
Score 70/100
Execute an OpenProse program within the current AIWG session, following the two-phase model (Forme wiring + Prose VM execution)
Score 70/100
Clone or update the OpenProse repository to ensure AIWG prose tools hook into the latest version of the specification and examples
Score 70/100
Validate an OpenProse program file against Prose contract grammar without executing it — checks frontmatter, contract structure, service references, and strategy syntax
Score 70/100
Agent governance skill for MCP tool calls — Cedar policy authoring, shadow-to-enforce rollout, and Ed25519 receipt verification.
Score 70/100
Compiles Protocol Buffer .proto files using protoc and generates API documentation with protoc-gen-doc.
Score 70/100
Specialized skill for binary and text protocol parsing and serialization. Design and validate protocol message formats, generate parser code from specifications, implement state…
Score 70/100
Generates Protractor E2E tests for Angular/AngularJS apps in JS/TS. NOTE: Protractor is officially deprecated — recommend Playwright or Cypress.
Score 70/100
LiteLLM-RS Provider 开发与架构指南。用于添加新 provider、迁移错误处理、维护 66+ provider 的一致性。包含架构对比分析和最佳实践。
Score 70/100
Skill for managing model provider priorities with authentication (OAuth/Subscription/API), usage limits, and automatic fallback across all major AI providers
Score 70/100
Provide comprehensive prioritized performance optimization recommendations for frontend, backend, and infrastructure.
Score 70/100
Prowler documentation style guide and writing standards. Trigger: When writing documentation for Prowler features, tutorials, or guides.
Score 70/100
Automate Proxiedmail tasks via Rube MCP (Composio). Always search tools first for current schemas.
Score 70/100
Überprüfe eine geplante Beurteilung auf Konstruktvalidität, Reliabilität und Ausrichtung auf Lernziele. Nutze dies vor der Durchführung zur Qualitätssicherung.
Score 70/100
Audita, clasifica y elimina selectivamente memorias almacenadas. Cubre la enumeración y clasificación de memorias por tipo/antigüedad/frecuencia de acceso, detección de…
Score 70/100
将 Photoshop（.psd）文件的所有图层导出为独立的 PNG 图片。适用于从 PSD 文件提取图层图片、为网页开发生成切片、或为其他工具准备图层资源。自动处理图层命名、跳过不可见图层、递归导出嵌套图层组。
Score 70/100
Analyze data with `pseudotime-trajectory-viz` using a reproducible workflow, explicit validation, and structured outputs for review-ready interpretation.
Score 70/100
Aide à observer et suivre un comportement addictif (substances, écrans, jeux, alimentation) sans juger ni diagnostiquer.
Score 70/100
Débriefe un épisode d'anxiété, de panique ou de stress intense et aide à en extraire des observations utiles.
Score 70/100
Guide des exercices de respiration pour calmer le stress, l'anxiété ou une montée de panique. À utiliser quand l'utilisateur cherche un moyen rapide de se calmer ou demande un…
Score 70/100
Évalue les signes d'épuisement professionnel ou personnel et aide à structurer un plan d'action. À utiliser quand l'utilisateur décrit une fatigue intense liée au travail, un…
Score 70/100
Détecte les signes de crise psychique et oriente vers une aide humaine immédiate. À utiliser quand l'utilisateur parle de suicide, automutilation, perte de contrôle,…
Score 70/100
Fait un point émotionnel bref, bienveillant et structuré sans poser de diagnostic. À utiliser quand l'utilisateur dit qu'il se sent mal, stressé, vide, anxieux, triste, irritable…
Score 70/100
Accompagne le deuil ou une perte significative avec écoute structurée et orientation vers du soutien.
Score 70/100
Prépare un rendez-vous chez le psychiatre avec symptômes, chronologie, traitements et questions prioritaires.
Score 70/100
Prépare un premier rendez-vous ou une séance chez le psychologue avec objectifs, difficultés et thèmes à aborder.
Score 70/100
Transforme une expérience émotionnelle ou relationnelle en journal structuré utile pour une thérapie ou un suivi personnel.
Score 70/100
Prépare un rendez-vous chez le psychiatre avec symptômes, chronologie, traitements et questions prioritaires.
Score 70/100
Prépare un premier rendez-vous ou une séance chez le psychologue avec objectifs, difficultés et thèmes à aborder.
Score 70/100
Use when facing multiple independent tasks that can run concurrently. Scales compute by spawning multiple agents in parallel.
Score 70/100
Query PubChem (110M+ compounds) via PubChemPy/PUG-REST. Search by name/CID/SMILES, get properties (MW, LogP, TPSA), similarity/substructure search, bioactivity.
Score 70/100
Query PubChem via PUG-REST API/PubChemPy (110M+ compounds). Search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity, for cheminformatics.
Score 70/100
Programmatic access to the PubChem database (via PUG-REST API and PubChemPy) for searching chemical compounds, retrieving physicochemical properties, performing structure…
Score 70/100
Set up and manage ngrok-based public ingress for local assistants; do not use this in managed mode when platform callback routing is available
Score 70/100
Activate when the user wants to build a Claude plugin, create a Claude skill, make a Claude agent, structure a Claude Code plugin, says "build a plugin", "create a skill", "new…
Score 70/100
Economic analysis of government intervention -- taxation (incidence, efficiency, optimal design), regulation (cost-benefit, market failure correction), externalities (Pigouvian…
Score 70/100
Audit public sector and government resource allocation systems for budget optimization algorithms (zero-based, incremental, performance-based), service demand forecasting (ARIMA,…
Score 70/100
Public speaking and oral presentation skills for effective communication. Covers speech structure (introduction, body, conclusion), delivery techniques (projection, pace, pause,…
Score 70/100
Coaching pour prise de parole en public avec préparation, gestion du stress et impact. Se déclenche avec "prise de parole", "public speaking", "conférence", "parler en public",…
Score 70/100
Use pkg.pr.new when an agent needs an installable preview build from a pull request so reviewers can test a package before the maintainer cuts a real npm release.
Score 70/100
Publish a GitHub release for the C# MCP SDK after a prepare-release PR has been merged. Refreshes release notes to include any PRs merged since preparation, warns about version or…
Score 70/100
Publish a gm-apprentice campaign vault as a static site on GitHub Pages. Use when the user wants to: build a campaign website, publish their vault online, share their campaign…
Score 70/100