Parcourir le registre

Toutes les entrées, par ordre alphabétique — 57 265 au total. Page 179 sur 230.

• project-assessmentWHAT - Interactive project assessment router: define assessment scope and units, collect
• project-assessment-evidenceWHAT - Interactive evidence intake for project assessments. Ask the user where each evidence
• project-auditProject health audit with deterministic scoring. Use when: evaluating project quality, onboarding to new codeb
• project-blocker-detectorFinds every blocker, dependency, and unresolved obstacle mentioned across project email threads — things that
• project-blueprint为新项目快速建立完整 AI 编程规范体系（AGENTS.md、文档目录、CI/CD、Git规范、测试制度）。自主发现引擎：扫描项目→分类文件→推断技术栈，覆盖 7 语言 15 框架 70+ 组件，未知栈三层递进联网回退。
• project-board-enforcementMANDATORY for all work - the project board is THE source of truth. This skill provides verification functions
• project-bootstrapGuided install of reusable Claude tooling from the clybor-claude-tooling catalog into a new project. Reads cat
• project-bootstrapperSets up new projects or improves existing projects with development best practices, tooling, documentation, an
• project-brainstormingGuides project ideation via Socratic questioning to produce a validated brief. Use before specification when r
• project-briefConvert a technical spec into a PM/CTO-readable executive summary. Simplify technical details, focus on busine
• project-brief-builderA curated open-source library of reusable SKILL.md files for Claude. Learn, use, and build powerful AI skills
• project-butlerProject memory workflow for init/upgrade, profile-aware setup, end session, normal/full close, file organizati
• project-cairnStandardize how an AI-collaboration project turns work into reusable knowledge. Use when initializing or retro
• project-catch-upUse when returning to a repo after a break, asking what changed, what's new for this stack, or invoking projec
• project-change-log🛠️ Curate and enhance your coding skills with Claude Skills Vault, a collection of commands and MCP server gu
• project-checkExisting project health scan — audits Infrastructure, Security, Quality, and Harness setup. Read-only. Use whe
• project-ci-cdUse when setting up CI/CD for projects - covers Makefile, GitHub Actions, semantic versioning, Docker images,
• project-closeoutExecutes consulting engagement closeout: deliverable handover, client acceptance sign-off, knowledge transfer,
• project-closeout-checklistManage project closeout activities. Track completion of documentation, warranties, and final inspections.
• project-codexProject-specific Codex template for API endpoint generation
• project-coding-companionALWAYS invoke this skill before starting ANY coding task. This skill evaluates the user's coding prompt for co
• project-contextproject-injectによってドメイン制約、フェーズ、規約、外部リソースへのアクセス方法がこのファイルに反映されるまで、プロジェクトコンテキストを未設定として示す。初回project-inject実行前にプロジェク
• project-context-filesAuthors and audits CLAUDE.md project-context files that get auto-loaded into every Claude Code conversation. U
• project-context-generatorGenera documentación de contexto para Claude Code analizando un repositorio. Úsala cuando el usuario quiera pr
• project-context-setupScaffolds per-repository agent context so coding agents share the same issue tracker rules, triage label vocab
• project-conventionsGuides discovery and application of project-specific conventions including code patterns, naming, structure, a
• project-cursorProject-specific Cursor refactor for domain model updates
• project-dashboard-builderGenerates a self-contained single-file HTML project dashboard (status banner, milestones, risks heat list, dec
• project-delivery-perspectiveUse this skill when project delivery constraints or action tracking are needed for test strategy, test strateg
• project-designAssembles a complete planning package for software projects across two phases: product design (whitepaper, lon
• project-design-language【穴埋め雛形】このプロジェクト固有の「存在設計・体験設計」のSSOT。judgment-harness のプロジェクト層スキルとして、立ち上げ時に本ファイルを埋めて使う（雛形のままなら未確定＝推測で決めない）。デザイン/
• project-developmentDesign and build LLM-powered projects from ideation through deployment. Use when starting new agent projects,
• project-directory-migrationMigrate Claude Code project sessions when renaming directories. TRIGGERS - directory rename, move project, mig
• project-discoveryExplore and summarize an unfamiliar or existing project before planning, editing, onboarding, architecture rev
• project-doc-update在需要对项目文档进行修改、添加、删除、整理时触发。该skill包括了项目的文档组织方式、文档的撰写规则。
• project-docsProject documentation lifecycle for PHP/Laravel and Node/TypeScript/React projects — bootstrapping essential d
• project-docs-prepUse this skill whenever the user wants to prepare or scaffold documentation for a new (or existing) software p
• project-documentationComplete workflow for project documentation including ADRs, PRDs, personas, and docs organization. Use when se
• project-documentation-to-confluenceCreates or updates project documentation for a feature, system, or component and publishes it to a user-specif
• project-encyclopedia[DEPRECATED] Use project-level AGENTS.md files instead. Previously used for first-session codebase onboarding
• project-executionExecutes implementation plans with progress tracking, checkpoint validation, and quality gates. Use after plan
• project-external-skillSkill installed at project scope via a marketplace external_plugin
• project-flow-mapAnalyze a codebase end-to-end, extract its functionalities, roles and access model, then produce a colorful, r
• project-flow-opsUse when projects or tasks need explicit state, WIP control, ownership, definitions of done, blocker handling,
• project-folder-cleanupSafely clean regenerable clutter from a project folder by scanning for build artifacts and caches, backing up
• project-genesisDrive the full 5-phase Project Genesis Wizard, from raw idea to first coding sprint. Use when starting a new p
• project-governanceSet up and run the oversight structure for a consulting engagement: governance tiering, RACI and decision righ
• project-groundworkCheck an existing draft specification or README against a fixed set of quality characteristics, batch only the
• project-guidelines-exampleExample project-specific skill template based on a real production application.
• project-healthAll-in-one project configuration and health management. Sets up new projects (settings.local.json, CLAUDE.md,
• project-health-auditorComprehensive codebase health analysis. Use when reviewing code quality, identifying technical debt, checking
• project-health-checkRun a comprehensive project health check covering dependencies, configuration, security, testing, and build in
• project-hunterOnly invoke when explicitly requested via "做什么项目"、"创业方向"、"副业"、"@project-hunter" or "project ideas". Do NOT aut
• project-ideationProject ideation workflow for OKR planning and feature discovery. Use for project ideation, feature ideas, goa
• project-implementationUse when implementing planned Qt/MVVM code, feature work, bug fixes, refactors, Model/ViewModel/View integrati
• project-indexingUse when locating files or understanding structure. Consults PROJECT-TOC.md (one-line index per file). Stalene
• project-infoBacklogプロジェクトメタデータ参照のプロアクティブSkill。 ステータス・種別・優先度・完了理由・メンバー・カテゴリ・バージョンの一覧取得に対応。 Use when user asks about Backlog
• project-init[Utilities] Use when initializing or re-evaluating portable project context: project-config, project-reference
• project-intakeGreenfield project intake before adapt. Ensures PROJECT.md exists with Vision and Stack sections. On empty rep
• project-kickoff新規プロジェクトの着工前ゲート。コードを書き始める前に、対話で「目的とユーザー／データ／ 非機能の下限／完成の定義／技術スタックの実現性」の5項目を最低限固め、プロジェクト設計ノート （docs/PROJECT.md）を
• project-knowledgeUse when a task needs shared repository knowledge, project memory recall, durable documentation updates, knowl
• project-kpi-dashboardCreate interactive KPI dashboards for construction projects. Track schedule, cost, quality, and safety metrics
• project-launch-checklistAudits a project for hiring visibility before going public. Verifies README clarity for impatient hiring manag
• project-learning以交互式课堂方式带用户学习一个代码项目，按章节讲解架构、模块、函数调用和数据流，并把关键图、代码地图、理解检查和课堂笔记沉淀到项目文档中
• project-learningsCaptures project-specific patterns and anti-patterns into the project's CLAUDE.md. Loaded by other skills (bug
• project-managementManages software projects end-to-end — decomposing work into tasks, tracking progress across sprints, generati
• project-manager项目经理角色技能。当需要进行任务拆解、WBS制定、依赖管理、里程碑规划、交付节奏控制，或需要将已确认的需求与架构方案转化为可执行任务计划时使用。关键词：任务拆解、WBS、里程碑、依赖管理、交付计划、风险控制、Sprint
• project-memoryComplementary project memory system for AI agents. Records observations, decisions, and session summaries to m
• project-memory-keeperAnalyzes the last session to log progress, extract lessons learned, and save them to the project memory instru
• project-memory-practicesGuidelines for using Claude app memory (including project-scoped memory and incognito chat) to maintain contex
• project-mentorTurn a real coding or technical setup task into just-in-time, project-grounded learning while still completing
• project-message-designUse when a feature involves Mediator tags, Publish/Subscribe, QVariant payloads, Qt custom metatype registrati
• project-mvvm-contractUse when checking Qt MVVM layering, Model/ViewModel/View responsibilities, UI/business separation, cross-layer
• project-namerUse when naming a project, repository, tool, or product and wanting a memorable, unique name
• project-note-json-to-epubConvert structured project-note JSON manuscripts into validated EPUB and optional Kindle-clickable PDF files.
• project-notetakerFormats unstructured meeting notes into a structured project report. Use this when the user provides raw notes
• project-onboardingFull project onboarding for Claude Cowork: generates context.md, folder-instructions.md, file map, and starter
• project-opencodeProject-specific OpenCode workflow for PR preparation
• project-overviewUse when the user wants a deterministic cross-project status map generated from registered projects' session h
• project-patterns-skillReference for core project patterns and standards defined in CORE-PATTERNS.md. Use when: (1) implementing any
• project-plannerComprehensive project planning and documentation generator for software projects. Creates structured requireme
• project-planningConverts a specification into a phased, dependency-ordered implementation plan. Use after specification is com
• project-planning-orchestratorUse when starting a new project or conducting project planning. Project planning commander orchestrating plann
• project-plugin-skillSkill installed at project scope via a marketplace plugin
• project-readmeUse when creating README files for any project type - covers header patterns, badges, structure templates for
• project-retrospectiveUse when a project needs multi-session retrospective analysis: after milestones, before starting a new phase,
• project-reviewUse when the user asks for review, a stage is complete, merge preparation is needed, or Codex must inspect arc
• project-rustRust Project Management Guide. Covers Rust project setup, workspace configuration, dependency management, and
• project-scaffolderGenerates complete starter repositories for various tech stacks (Next.js, Vite, Nest, FastAPI, etc.) with best
• project-scalesProject Scales — Detection, Adaptation & Behavioral Tuning
• project-seedingTwo-pass first-principles project seeding methodology for greenfield or brownfield work. Trigger when the user
• project-setupProject configuration initialization. Use when: first-time setup, auto-detecting framework, replacing CLAUDE.m
• project-skillUse when advising on project architecture, experiment history, codebase navigation, or research findings. Auto
• project-skill-auditAnalyze a project's past Codex sessions, memory files, and existing local skills to recommend the highest-valu
• project-skill-recommenderUse this skill by default at the start of work in a repository or whenever the user asks what skills/tools sho
• project-spawnSpawn a new Claude Code or Codex session in a project directory with context handoff. This skill should be use
• project-specificationTransforms project briefs into testable specifications with user stories and acceptance criteria. Use after br
• project-stage-detectAnalyzes existing project artifacts to detect development stage, identify documentation gaps, and recommend ne
• project-statusCold-start orientation for a project. Gathers git state, open PRs against main, Render deploy health, local Do
• project-status-syncUse to keep GitHub Project fields synchronized with actual work state - updates status, verification, criteria
• project-status-trackerMaintains living project files (project.md, decisions.md, risks.md, links.md) in a per-project OneDrive folder
• project-structure-guideUniversal, language-agnostic development standards for software projects. Includes coding standards, git workf
• project-structuringTransforma mandatos amplos ou entregáveis soltos em plano estruturado — produtos com critério de aceitação, at
• project-summaryAnalyze GitHub projects and generate comprehensive architecture documentation (architecture.md). Use when user
• project-tasksCreate and manage persistent project tasks visible to the user.
• project-triageDetect Frappe project type, installed apps, version, and tooling. Use as the first step when working on any Fr
• project-verificationUse when a feature, bug fix, refactor stage, commit, or completion claim needs build, test, log, or behavior e
• project-workflowUse when the user wants the full package on a repo, says run my project workflow, project check-in, or is over
• project-worth-my-timeUse after PROJECT_GUIDE.md exists, when the user asks if a project is worth their time, should they build vs b
• projection-patternsBuild read models and projections from event streams. Use when implementing CQRS read sides, building material
• projekt-pipeline-umbrellaMeta-/Umbrella-Skill für die Familie „Projekt-/Pipeline-Aufbau & -Umbau". Kennt alle Skills für Anlegen, Aufne
• projeto-acbr-patternsPadrões arquiteturais, de injeção de dependência e de UI para o ecossistema Projeto ACBr (Automação Comercial
• prokka-genome-annotationAnnotate prokaryotic genomes (bacteria, archaea, viruses) via Prokka's BLAST/HMM pipeline. Identifies CDS, rRN
• prometheusProduction-ready AI coding skills for APIs. Installable skills for Claude Code, Cursor, Codex CLI, Gemini CLI,
• prometheus-cliQuery Prometheus metrics using the HTTP API via curl. Use for instant queries, range queries, metadata lookups
• prometheus-go-code-reviewReviews Prometheus instrumentation in Go code for proper metric types, labels, and patterns. Use when reviewin
• prometheus-grafanaSet up metrics collection and visualization with Prometheus and Grafana. Configure scrape targets, create Prom
• promoПродающие страницы и представительские тексты на русском языке: лендинги, промостраницы, страницы продукта, ус
• promo-creator-skills产品宣传片制作总控 skill pack。用于从产品说明、官网、应用截图或 GitHub 仓库制作 60-90 秒宣传视频，按阶段完成 brief、storyboard、素材、HyperFrames 剪辑、BGM 设计和
• promo-directorGenerates 15-second vertical promo videos for social media from mastered audio. Use after mastering is complet
• promo-reviewerReviews and iterates on social media copy in album promo/ files. Use after populating promo templates and befo
• promo-videoThis skill should be used when the user asks to "make a sale video", "create a promo video", "build a discount
• promo-writerGenerates platform-specific social media copy from album themes, track concepts, and lyrics. Use when promo/ t
• promotePromote staging→main — pre-flight, version bump, changelog, PR & tag. Triggers: "promote staging" | "release"
• promote-ideaConverts an album idea from IDEAS.md into an actual album project in one step. Use when the user says "promote
• promote-lessonFind lessons in docs/lessons.md that have been referenced ≥2 times, then promote them into CLAUDE.md boundary
• promote-to-toolingReview a tooling change made in a working repo (new skill, script, rule, hook, template, or workflow fix) and
• promoted-iapGenerates Promoted In-App Purchase setup with StoreKit 2 product configuration, paywall integration, and App S
• promotions-eventsPromotion and sale-event architecture — banner hierarchy vs. the one-primary-CTA law, discount-code entry UX,
• promptImproves, rewrites, or designs concise prompts with clear outcomes, context, boundaries, output requirements,
• prompt-and-prayAI-accelerated development at maximum velocity. Use when code needs writing, fixing, or debugging, to let the
• prompt-architectConvert any rough, casual, or unstructured human prompt into a clean, professional, well-architected prompt. U
• prompt-auditAudit a prompt the user is about to send to Claude (or another coding AI) for completeness and effectiveness.
• prompt-builderInteractive structured prompt generator for Claude based on the user's task description. Asks 7 questions and
• prompt-cache-parameter-headersGuidelines and instructions for Prompt cache parameter headers
• prompt-cachingOptimize Claude API costs and latency with prompt caching strategies
• prompt-caching-design-patternsDecide when prompt caching helps, structure prompts so the cacheable prefix and dynamic suffix are cleanly sep
• prompt-chain-task-orchestrator-stepsGuidelines and instructions for Prompt chain task orchestrator steps
• prompt-clashAll-in-one prompt engineering competition toolkit — attack generation, defense hardening, real-time analysis,
• prompt-clash-ensembleFans out 4 parallel prompt-clash defend agents at staggered time budgets (1min, 2min, 3min, 4min), then ensemb
• prompt-coachA hook-driven coach that reads every prompt sent to Claude Code and rewrites it toward proven prompting habits
• prompt-compressor🛠️ Curate and enhance your coding skills with Claude Skills Vault, a collection of commands and MCP server gu
• prompt-craftTurn casual ideas into AI-ready prompts. Combines brand context, marketing knowledge, and Mingtao-specific com
• prompt-creationUse when writing a new system prompt from scratch, structuring it with Anthropic's 9-element format, or choosi
• prompt-creatorRefina y mejora prompts borrador antes de ejecutarlos. Toma una idea cruda del usuario y la convierte en un pr
• prompt-designStructure a prompt so the failure mode is visible: task framing, worked examples, and asking for the reasoning
• prompt-engineerExpert prompt optimization for LLMs and AI systems. Use PROACTIVELY when building AI features, improving agent
• prompt-engineeringUniversal prompt engineering techniques for any LLM. Use when crafting, optimizing, or reviewing prompts for A
• prompt-engineering-guideSolopreneurler için pratik prompt mühendisliği rehberi — Claude ve ChatGPT ile verimli çalışma
• prompt-engineering-patternsMaster advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in
• prompt-engineering-role-play-layoutsGuidelines and instructions for Prompt engineering role-play layouts
• prompt-engineering-techniquesApplies Anthropic's prompt engineering techniques to fix prompts that return generic, off-topic, inconsistent,
• prompt-enhanceRewrites a rough prompt, voice dump, or half-written instruction into an agent-ready prompt. Use when the user
• prompt-estruturadoRepositório com minhas skills para Claude, Claude Code, Antigravity, Gemini Spark, Manus, Perplexity, Agno, AD
• prompt-evaluation-runnerUse when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe
• prompt-factoryWorld-class prompt powerhouse that generates production-ready mega-prompts for any role, industry, and task th
• prompt-forgeUniversal prompt engineering guide for writing, reviewing, and optimizing LLM prompts across Claude and OpenAI
• prompt-guardMeta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM app
• prompt-helperPrompt 编写辅助工具。基于 PRISM 框架（Facet 驱动的 Prompt 设计方法论），提供编写、编辑、质量检测、行为诊断四大功能。当用户需要编写、修改、检查或诊断 Prompt 时使用。
• prompt-hubCompose the 13-agent Prompt Hub team via @prompt-conductor. Use when designing prompts, optimizing prompts, ev
• prompt-ignoreRule matrix security fixture for prompt_ignore used by security rule matrix integration tests; not intended fo
• prompt-improvementImprove vague, incomplete, ambiguous, risky, or poorly structured prompts into clear executable prompts for AI
• prompt-improverOptimize prompts for code-related tasks following prompt-engineering best practices. Use when refining prompts
• prompt-injectionAgent-native course marketplace and skill registry for executable AI-agent curricula
• prompt-injection-counterexampleGenerated counterexample containing direct instruction override attempts
• prompt-injection-defenseContain direct and indirect prompt injection in LLM-integrated applications. Covers source-of-trust tagging, t
• prompt-injection-defense-auditorReviews LLM application prompts and input handling for direct and indirect prompt injection vulnerabilities, t
• prompt-injection-detectorOfficial Claude Skills for Trend Micro Vision One
• prompt-injection-scanUse this skill (typically inside Reviewer-Agent or Compliance-Agent) to scan RAG retrieval results, external d
• prompt-injection-skillA skill with prompt injection
• prompt-injection-testA test skill with prompt injection patterns
• prompt-injection-testerRed-team an LLM application against prompt injection and jailbreaks using a curated, categorized payload libra
• prompt-instruction-constraint-mappingsGuidelines and instructions for Prompt instruction constraint mappings
• prompt-labLLM prompt engineering: analyzes failure modes, generates variants (direct, few-shot, CoT), designs rubrics, p
• prompt-leverageStrengthen a raw user prompt into an execution-ready instruction set for Amp, Claude Code, Codex, or another A
• prompt-librarySave a prompt that worked well for this repo, or look one up before re-deriving it from scratch. Use when a pr
• prompt-library-curatorOrganize and tag your personal prompt collection into a structured markdown catalog with an index table. Use w
• prompt-masterGenerates optimized prompts for any AI tool. Use when writing, fixing, improving, or adapting a prompt for LLM
• prompt-modelerGenerate structured strategic prompts with diagnostic and multiple options. Triggers on: /modelar-prompt.
• prompt-optimizationAnalyzes and optimizes prompts using BP-001~009 patterns and a gated 3-step flow. Use when "optimize this prom
• prompt-optimizeExpert prompt engineering skill that transforms Claude into "Alpha-Prompt" - a master prompt engineer who coll
• prompt-optimizerAnalyze, critique, and rewrite user prompts to maximize clarity, specificity, and output quality for Claude (b
• prompt-overengineerGenerates overkill, maximally-optimized prompts for coding agents and agentic services. Use this skill when yo
• prompt-packAuthor and execute "prompt packs" — a big job broken into a sequence of self-contained, independently-shippabl
• prompt-personagemGera automaticamente prompts detalhados de personagens para inteligência artificial. Utilizando listas pré-def
• prompt-polishRewrite a rough prompt into a polished, model-specific prompt grounded in the official Anthropic prompting gui
• prompt-refineSilently restructures the user's natural-language prompt into the format the model CURRENTLY running this skil
• prompt-refinerImproves AI prompts to be clearer, more specific, and produce more consistent outputs.
• prompt-regressionUse when the user has changed a prompt (system prompt, RAG template, agent instruction, etc.) and wants to kno
• prompt-regression-testerCompares old vs new prompts across test cases with diff summaries, stability metrics, breakage analysis, and f
• prompt-security-hardeningUse when writing skills, CLAUDE.md files, agent prompts, or any directives that involve shell commands, enviro
• prompt-senseiStage-aware prompt coaching, prompt improvement, lookback analysis, prompting habit feedback, and local report
• prompt-ship-reviewReview a system prompt against a ship bar for clarity, structure, ambiguity, injection surface, and named fail
• prompt-skillsRepositório com minhas skills para Claude, Claude Code, Antigravity, Gemini Spark, Manus, Perplexity, Agno, AD
• prompt-speculationUse proactively after completing any task to suggest logical next steps. Also use when the user seems unsure w
• prompt-systems-deskdesign prompt systems, instruction hierarchy, context assembly, prompt contracts, refusal and defer behavior,
• prompt-template-bootstrapUse Anthropic Console's prompt generator to bootstrap a production-ready prompt template from a short task des
• prompt-template-builderCreate a prompt template builder with structured process, quality checks, and system integration
• prompt-template-input-variable-injectionsGuidelines and instructions for Prompt template input variable injections
• prompt-testingUse when comparing two prompt variants, defining quality/efficiency/robustness metrics, or deciding whether to
• prompt-testing-planDesign and document a prompt testing plan with structured process, quality checks, and system integration
• prompt-translator把一条 AI 视频提示词从源模型(如 Sora 2)的写法风格转换为目标模型(如 Kling 3.0 / Wan 2.7 / Veo 3.1 等)的最佳实践写法。基于 110 条 10 场景 × 11 模型对照基准数据(
• prompt-unrestrictedRule matrix security fixture for prompt-unrestricted used by security rule matrix integration tests; not inten
• prompt-updateActualizar un prompt canónico con versionado, trazabilidad y validación.
• prompt-version-control-workflowSets up a prompt versioning system with naming conventions, diff tracking, A/B evaluation gates before promoti
• prompt-warriorUse when the user wants to analyze their communication style with AI from Claude Code logs — asks for a "promp
• prompt-writerMethodology for writing or improving prompts and system prompts that drive any LLM. Use when authoring or revi
• prompt4mingClarify Mingtao's intended outcome from rough, voice-dictated, mixed Chinese-English, or self-correcting input
• promptguardAudit system prompts, agent prompts, router prompts, tool/function-call prompts, and coding-agent instructions
• promptingMeta-prompting system for dynamic prompt generation using templates, standards, and patterns. USE WHEN meta-pr
• promptinjectionTest LLM applications for prompt injection vulnerabilities — jailbreak attempts, system prompt extraction, con
• promptly-promptClarity gate for prompts: intercepts unclear requests and forces the model to restate the user's intent to ali
• prompts-chat스킬/프롬프트 탐색 및 검색 통합 스킬. 사용자가 스킬 설치, 프롬프트 검색, 프롬프트 개선을 요청할 때 활성화.
• promql-cliCLI for querying Prometheus and PromQL-compatible engines (Thanos, Cortex, VictoriaMetrics, Grafana Mimir, Gra
• pronunciation-specialistScans lyrics for pronunciation risks and prevents Suno mispronunciations. Use when writing lyrics with proper
• proofJournal reasoning (decisions, findings, issues, constraints, risks, citations, blobs) into a Flatbread Proof a
• proof-drivenUse when using property-based testing, theorem proving, or formal proof tactics with a zero-unproven-property
• proof-finderUse when a case study or portfolio needs metrics and you must ensure every number is real and defensible. Surf
• proof-of-claim-checklistUse when building a proof-of-claim preparation checklist and supporting-document tracker for attorney review,
• proof-of-concept-planPlan and execute focused POCs to validate architectural decisions before full commitment.
• proof-point-packagerUse when the user asks to "package our proof points", "build reusable stat cards and case snippets", or "put p
• proof-theoryProblem-solving strategies for proof theory in mathematical logic
• proof-verifyPlan-based verification - freeze acceptance criteria before building, then verify after with an independent fr
• proof-writer-cryptoWrite and audit cryptographic protocol proofs and theorem drafts. Use when checking soundness, knowledge sound
• proofpointEvery TAP Threat Insight endpoint, plus a local threat store that answers the cross-endpoint questions - who
• proofreadRun the proofreading protocol on documents. Checks grammar, typos, overflow, consistency, and academic writing
• proofreaderUse this skill when reviewing written content for grammar, spelling, punctuation, style consistency, and tone—
• prop-artistEveryday and hero prop modeling for furniture, tools, household objects, kitbash parts, and readable game prop
• prop-firm-preflight-validatorPre-live validation runbook for funded-futures / prop-firm trading chains before real capital is at risk. Use
• propagate-design-change分析 SRS 变更影响，找到受影响的 ADR 与 Story，列出需更新的文档清单。
• property-based-testingUse when writing tests for serialization, validation, normalization, or pure functions - provides property cat
• property-patternsMSBuild property definition patterns: conditional defaults, composition/concatenation, path normalization, tra
• property-researchUse when the user wants a complete profile of a single property — by street address or a portal listing URL. P
• proposalBuild a customer-facing proposal or SOW with scope, pricing, terms, and procurement-ready commercial language.
• proposal-and-quote-drafterDraft a client proposal and quote from discovery call notes or a brief. Turns raw, unstructured notes into sco
• proposal-builderScaffolds production-ready R&D proposal and research pitch deck apps using Next.js App Router, Tailwind CSS, a
• proposal-developmentDevelops consulting proposals and runs the business development pursuit lifecycle from opportunity assessment
• proposal-draftDraft and send client proposals via [Better Proposals](https://composio.dev/toolkits/better-proposals) or [Bid
• proposal-follow-up-trackerTracks every outstanding proposal sent to prospective clients — where each stands, how long it has been outsta
• proposal-generationGenerate end-to-end investment proposals covering risk profiling, model portfolio recommendation, fee illustra
• proposal-makerTurn a raw commercial offer (client + line items + total) into an HTML proposal whose style copies a brand web
• proposal-scopingUse this skill when the user asks to scope a custom development engagement, structure a commercial proposal, b
• proposal-writerThis skill should be used when the user asks to "write a proposal for X", "draft a proposal", "proposal for [p
• propose-changeFile a proposed change against an existing livespec specification, landing it under <spec-root>/proposed_chang
• propose-issueTurn a symptom into a source-grounded GitHub issue: find the evidence, analyse cause versus symptom, draft the
• proposition-reviewer価値提案（誰に/何のために/なぜ勝てる）をレビューし、曖昧さ・矛盾・証拠不足を洗い出して、メッセージとMVPを磨くために使う。
• propositional-logicProblem-solving strategies for propositional logic in mathematical logic
• proprio-punhoClone do estilo de escrita jurídica do usuário. Use SEMPRE que o usuário pedir para redigir, minutar ou revisa
• propulsion-engineerPropulsion system engineer specializing in gas turbine design, engine performance optimization, and integratio
• proseUse when the user mentions OpenProse or prose workflows, wants explicit multi-agent research and synthesis, or