agentsclimarketplace

Context & AI engineering

25,772 rows, by stacks then stars

1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid

  • Model bench

    nateslabach/skills/skills/model-bench Skill

    6★ repo

    Run a 3-leg evaluation against a newly released LLM. Leg 1 is trap questions with deterministic answers, leg 2 is an agentic orchestration task with a planted failure, leg 3 is a brownfield feature build in a real repo. Use when the user wants to vibe-check, test, evaluate, or compare a new frontier model, or mentions model-bench, model vibe check, or launch-day protocol.

  • Subagent

    nateslabach/skills/skills/subagent Skill

    6★ repo

    Ground rules for an effective subagent in a loop, workflow, or graph run. Stay in scope, escalate when stuck, return structured results. Use when acting as a subagent, writing subagent prompts, or reviewing delegated agent behavior.

  • Avdlee xcode build benchmark

    JordanCoin/ios-skills-collection/skills/avdlee--xcode-build-benchmark Skill

    no license6★ repo

    Benchmark Xcode clean and incremental builds with repeatable inputs, timing summaries, and timestamped `.build-benchmark/` artifacts. Use when a developer wants a baseline, wants to compare before and after changes, asks to measure build performance, mentions build times, build duration, how long builds take, or wants to know if builds got faster or slower.

    The same file is in 2 other repositories

  • Avdlee xcode build orchestrator

    JordanCoin/ios-skills-collection/skills/avdlee--xcode-build-orchestrator Skill

    no license6★ repo

    Orchestrate Xcode build optimization by benchmarking first, running the specialist analysis skills, prioritizing findings, requesting explicit approval, delegating approved fixes to xcode-build-fixer, and re-benchmarking after changes. Use when a developer wants an end-to-end build optimization workflow, asks to speed up Xcode builds, wants a full build audit, or needs a recommend-first optimization pass covering compilation, project settings, and packages.

    The same file is in 2 other repositories

  • Daetojemax figma to swiftui skill

    JordanCoin/ios-skills-collection/skills/daetojemax--figma-to-swiftui-skill Skill

    no license6★ repo

    Translate Figma designs into production-ready SwiftUI code with 1:1 visual fidelity using the Figma MCP workflow. Trigger when the user provides Figma URLs or node IDs and wants iOS/SwiftUI implementation, asks to implement a design or component from Figma for an iOS app, or references Figma selections in the context of an Xcode/SwiftUI project. Also trigger when user asks to inspect Figma designs for iOS planning, fetch design tokens for SwiftUI, or convert Figma assets for Xcode. Requires a working Figma MCP server connection. Do NOT trigger for web/React implementations.

  • Dimillian bug hunt swarm

    JordanCoin/ios-skills-collection/skills/dimillian--bug-hunt-swarm Skill

    no license6★ repo

    Parallel read-only multi-agent root-cause investigation for bugs, regressions, crashes, flaky behavior, or unexplained failures. Use when the user asks to investigate a bug, find the root cause, trace a regression, understand why something broke, or wants a ranked diagnosis with the fastest proof path without making code edits.

    The same file is in 8 other repositories

  • Dimillian ios debugger agent

    JordanCoin/ios-skills-collection/skills/dimillian--ios-debugger-agent Skill

    no license6★ repo

    Use XcodeBuildMCP to build, run, launch, and debug the current iOS project on a booted simulator. Trigger when asked to run an iOS app, interact with the simulator UI, inspect on-screen state, capture logs/console output, or diagnose runtime behavior using XcodeBuildMCP tools.

    The same file is in 33 other repositories

  • Dimillian review swarm

    JordanCoin/ios-skills-collection/skills/dimillian--review-swarm Skill

    no license6★ repo

    Parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks, performance or reliability issues, and contract or test coverage gaps. Use when the user asks for a review swarm, parallel review, diff review, regression review, security review, or wants high-signal issues plus a prioritized fix path without editing files.

  • Eronred rating prompt strategy

    JordanCoin/ios-skills-collection/skills/eronred--rating-prompt-strategy Skill

    no license6★ repo

    When the user wants to improve their app's star rating, increase ratings volume, optimize when and how they prompt users for a review, or recover from a bad rating period. Use when the user mentions "app rating", "star rating", "review prompt", "SKStoreReviewRequest", "In-App Review API", "ask for review", "low rating", "rating drop", "get more reviews", or "recover from 1-star". For responding to reviews, see review-management. For overall ASO health, see aso-audit.

    The same file is in 2 other repositories

  • Jordancoin pencil ios design

    JordanCoin/ios-skills-collection/skills/jordancoin--pencil-ios-design Skill

    no license6★ repo

    iOS-specific Pencil MCP design workflow. Creates iOS screens on canvas following Apple HIG with proper SF Pro typography, semantic colors, and 8pt spacing grid. Use when designing iOS UI in .pen files. Requires Pencil MCP server.

    The same file is in 1 other repository

  • Kimsungwhee apple docs mcp

    JordanCoin/ios-skills-collection/skills/kimsungwhee--apple-docs-mcp Skill

    no license6★ repo

    MCP server for Apple Developer Documentation. Search iOS/macOS/SwiftUI/UIKit docs, WWDC videos with transcripts, sample code, and framework APIs. Use when you need to look up Apple APIs, check platform compatibility, find WWDC sessions, or browse framework symbols. Install the MCP server first, then use its tools.

  • Rudrankriyam asc testflight orchestration

    JordanCoin/ios-skills-collection/skills/rudrankriyam--asc-testflight-orchestration Skill

    no license6★ repo

    Orchestrate TestFlight distribution, groups, testers, and What to Test notes using asc. Use when rolling out betas.

    The same file is in 2 other repositories

  • Ai agent design

    Muvon/octomind-tap/skills/ai-agent-design Skill

    6★ repo

    Operational playbook for designing production LLM agents in 2026. Covers agent loop patterns (ReAct, Reflexion, Plan-and-Execute, function calling, Anthropic tool use), tool schema engineering (JSON Schema, strict mode, description craft, anti-patterns), the Agent Skills open standard (Anthropic Dec 2025), Model Context Protocol (MCP) integration, multi-agent orchestration (LangGraph, CrewAI, AutoGen — with cost trade-offs), error handling and infinite-loop prevention, observability via OpenTelemetry GenAI semantic conventions, the OWASP LLM Top 10 v2025 and OWASP Top 10 for Agentic Applications 2026, and the context-engineering discipline that replaced 'prompt engineering' in 2026. Use when designing a new agent, picking an orchestration framework, debugging a misbehaving agent, or hardening tool exposure. Output: agent specs with named patterns, cost projections, observability hooks, and OWASP-mapped risk surfaces.

  • Ai cost finops

    Muvon/octomind-tap/skills/ai-cost-finops Skill

    6★ repo

    Operational playbook for cutting LLM application cost in 2026. Covers provider pricing (Anthropic Claude Opus/Sonnet/Haiku, OpenAI GPT-4o/o-series, Google Gemini Pro/Flash), Anthropic prompt caching (90% discount on cached tokens, up to 85% latency cut), OpenAI automatic prompt caching (50% discount), Anthropic/OpenAI/Gemini Batch APIs (50% off), model routing patterns (Martian, NotDiamond, OpenRouter Auto vs manual rules), token economics (output 3–8× input), structured output cost wins, RAG cost stack (embeddings, rerank, vector DBs), and FinOps observability (Helicone, Langfuse, Phoenix, LangSmith, Vantage). Use when projecting LLM cost, hunting waste in an existing pipeline, picking a model, or setting up per-feature attribution. Output: cost projections with cited prices and quantified optimization levers.

  • Ai evals design

    Muvon/octomind-tap/skills/ai-evals-design Skill

    6★ repo

    Operational playbook for designing production LLM evaluation in 2026. Covers eval framework selection (Promptfoo, DeepEval, Maxim, LangSmith, Braintrust, Phoenix, Galileo, Patronus), golden dataset construction (size, stratification, versioning), synthetic data generation, LLM-as-judge design with G-Eval methodology (Liu et al., EMNLP 2023), preference-leakage mitigation (Wong et al. 2025), statistical significance testing (McNemar's, paired t, Bayesian pairwise, bootstrap), RAG metrics (RAGAS, TruLens RAG Triad), agent trajectory evaluation, drift detection, eval-driven development (Red Hat, March 2026), CI/CD prompt-regression gates, and benchmark literacy (GAIA, BFCL, SWE-Bench Verified, MMLU-Pro, GPQA Diamond, HELM, τ-Bench). Use when designing an eval suite, validating a prompt change, gating a deploy, or diagnosing production quality drift. Output: eval verdicts with statistical evidence, not vibe judgments.

  • Ai prompt injection defense

    Muvon/octomind-tap/skills/ai-prompt-injection-defense Skill

    6★ repo

    Operational playbook for defending LLM applications against prompt injection (direct + indirect), and red-teaming them in 2026. Covers OWASP Top 10 for LLM Applications v2025 (LLM01–LLM10), OWASP Top 10 for Agentic Applications 2026 (ASI01–ASI10), foundational research (Greshake et al. on indirect injection, Anthropic Many-Shot Jailbreaking, Constitutional AI), documented real-world exploits (Slack AI Aug 2024, EchoLeak CVE-2025-32711, GitHub Copilot RCE CVE-2025-53773, Bing/Sydney), defense layers (XML tag separation per Anthropic docs, structured outputs, content filters via Llama Guard 3 / OpenAI Moderation / Anthropic classifiers, NeMo Guardrails), and red-team tooling (garak, PyRIT, Promptfoo red-team mode). Use when auditing an LLM app for injection, designing defense-in-depth, mapping OWASP risks, or building a red-team suite. Output: red-team findings + defense recommendations with reproducible payloads.

  • Ai rag patterns

    Muvon/octomind-tap/skills/ai-rag-patterns Skill

    6★ repo

    Operational playbook for designing and tuning production RAG (Retrieval-Augmented Generation) systems in 2026. Covers chunking strategies (fixed/recursive, semantic, late chunking, Anthropic Contextual Retrieval), retrieval (BM25, dense, hybrid with reciprocal rank fusion, ColBERT late-interaction), query rewriting (HyDE, multi-query, decomposition), reranking (Cohere Rerank, cross-encoders, BGE-Reranker), evaluation (RAGAS metrics, TruLens RAG Triad, DeepEval), the seven failure modes (Barnett et al.), agentic RAG patterns, multi-modal RAG (ColPali), and the long-context-vs-RAG trade-off. Use when designing a new RAG pipeline, diagnosing why an existing one underperforms, or evaluating retrieval quality. Output: architecture decisions with cited numbers, not vibes.

  • Device computer automation

    Muvon/octomind-tap/skills/device-computer-automation Skill

    6★ repo

    Operate the local computer's native UI — macOS, Linux, or Windows — via the desktop-automation MCP server. Covers OS accessibility / screen-recording permissions, pixel-anchor targeting (no semantic UI tree), region-capture discipline under the MCP response cap, window focus and multi-monitor handling, keyboard / mouse / clipboard sequencing, and the safety boundary around destructive desktop actions and screen-lock / biometric bypass. Activate when the user wants to drive a native desktop app or the OS shell at the GUI layer. Pairs with the device:operator agent which carries the shared snapshot → verify → record discipline; this skill carries the desktop-specific tooling and rules and pulls the device-computer capability automatically.

  • Device mobile automation

    Muvon/octomind-tap/skills/device-mobile-automation Skill

    6★ repo

    Operate iOS and Android devices — real hardware, simulators, and emulators — via the mobile-mcp server. Covers device discovery and selection, app install / launch / terminate, accessibility-tree targeting, taps / swipes / typing / device-button presses, orientation handling, and the safety boundary around app-store / jailbreak / biometric / in-app-purchase protections. Activate when the user wants to drive a phone or tablet (iPhone, Android, iOS Simulator, Android Emulator) through a UI flow. Pairs with the device:operator agent which carries the shared snapshot → verify → record discipline; this skill carries the mobile-specific tooling and rules and pulls the device-mobile capability automatically.

  • Octomind workflow

    Muvon/octomind-tap/skills/octomind-workflow Skill

    6★ repo

    Complete guide for octomind workflow files — pipeline design (pattern selection, step decomposition, sentinel handoff contracts, loop convergence, context economics) plus the exact TOML syntax for the external orchestrator that chains octomind run subprocesses. Covers sequential/parallel/loop/conditional steps, variable substitution, session modes, pre-flight validation, and the CLI. Activate when designing, authoring, validating, or debugging a workflow .toml file.

  • Prompt engineering

    Muvon/octomind-tap/skills/prompt-engineering Skill

    6★ repo

    Generate, improve, analyze, and debug LLM prompts. Activate only when the user explicitly asks to write, rewrite, optimize, diagnose, or design a prompt/system prompt, or names a prompt-engineering technique.

  • Tap agent authoring

    Muvon/octomind-tap/skills/tap-agent-authoring Skill

    6★ repo

    Deep guide for writing Octomind agent manifests: TOML format, required fields, system prompt structure, temperature guidelines, workflow/layer patterns, and the pre-write checklist. Activate when creating or editing agents/<domain>/<spec>.toml files.

  • Tap skill authoring

    Muvon/octomind-tap/skills/tap-skill-authoring Skill

    6★ repo

    Complete guide for creating AgentSkills-compliant SKILL.md packs in the octomind-tap registry: frontmatter fields, body structure, auto-activation rules, validate scripts, and quality principles. Activate when creating or editing skills/<name>/SKILL.md files.

  • Parallel worktree supervisor

    ldilov/harness-forge/skills/parallel-worktree-supervisor Skill

    6★ repo

    plan and supervise low-overlap parallel work across git worktrees or stacked branches. use when a backlog could be split safely, when multiple small dependent changes need reviewable sequencing, or when merge-blocking risks must be made explicit before parallel execution.

  • Observability and eval

    ldilov/harness-forge/skills/observability-and-eval Skill

    6★ repo

    AI coding agent runtime that makes LLMs understand your codebase with repository-aware context, memory, and continuous learning

  • Dynamic mcp

    valkryhx/google_adk_agent/skills/dynamic-mcp Skill

    no license6★ repo

    动态 MCP 工具加载器,支持运行时连接远程 HTTP/SSE MCP 服务或启动本地 MCP 进程,让 Agent 根据需求即时扩展能力。适用于用户提到不熟悉的 MCP 服务时,通过搜索发现连接方式后动态加载。

  • Mcp integration

    valkryhx/google_adk_agent/skills/mcp_integration Skill

    no license6★ repo

    集成 Model Context Protocol (MCP) 工具,通过 HTTP 连接与外部 MCP 服务交互,提供参数管理、工单生成等功能。

  • Memory retrieval system

    valkryhx/google_adk_agent/skills/memory_retrieval_system Skill

    no license6★ repo

    专门针对记忆归档库的 L0(广度扫描) 到 L2(精准读取) 的两级检索引擎。

  • Param mcp

    valkryhx/google_adk_agent/skills/param_mcp Skill

    no license6★ repo

    集成参数 Model Context Protocol (MCP) 工具,通过 HTTP 连接与外部参数 MCP 服务交互,提供参数管理、工单生成等功能。

  • Programmatic tool calling

    valkryhx/google_adk_agent/skills/programmatic-tool-calling Skill

    no license6★ repo

    编程化工具调用指南。允许 Agent 编写并执行 Python 代码,从而能够在一个沙箱环境中动态调用其他工具,实现循环、批处理和复杂逻辑。

  • Github triage agent

    yu-iskw/github-project-skills/agents/github-triage-agent Skill

    no license6★ repo

    Expert triage agent. Use proactively to categorize, label, and assign new issues.

  • Write agent handoff

    Daaaaave/agentic-workspace-core/payload/.agents/skills/write-agent-handoff Skill

    6★ repo

    Use when temporary task state, delegation payload, cold-start resume packet, review/debug brief, or compaction snapshot must be handed to another agent, workspace, subagent, reviewer, or future session. Do not use for durable project facts, raw transcript dumps, or ordinary same-session status summaries.

  • Write agent skill

    Daaaaave/agentic-workspace-core/payload/.agents/skills/write-agent-skill Skill

    6★ repo

    Use when creating, changing, reviewing, securing, or evaluating an agent skill; deciding whether behavior belongs in a skill; designing skill trigger boundaries, bundled resources, frontmatter, eval prompts, split/merge decisions, or skill security/supply-chain checks; or improving false-positive/false-negative skill activation. Do not use for ordinary project documentation or durable facts.

  • Market orchestrator

    LuckyOneTwoThree/pm-skill/pm-01-discovery/orchestrators/market-orchestrator Skill

    no license6★ repo

    当需要执行完整的市场与竞品分析流程时使用。市场竞品指挥官,调度market-tam-som/pest/competitor-analysis。关键词:市场分析、竞品分析、TAM/SAM/SOM、PEST、竞品情报、四象限、市场规模、行业分析、竞争对手、竞品调研。

  • Opportunity orchestrator

    LuckyOneTwoThree/pm-skill/pm-01-discovery/orchestrators/opportunity-orchestrator Skill

    no license6★ repo

    当需要执行完整的机会识别与定义流程时使用。机会识别指挥官,调度opportunity-definition完成机会评分、问题陈述、HMW发散和机会简报。关键词:机会识别、机会评分、HMW、Problem Statement、Opportunity Brief、产品机会、机会评估、问题定义。

  • User research orchestrator

    LuckyOneTwoThree/pm-skill/pm-01-discovery/orchestrators/user-research-orchestrator Skill

    no license6★ repo

    当需要执行完整的用户研究流程时使用。用户研究指挥官,调度voice-analysis/behavior-analysis/user-modeling/interview-assist/report。关键词:用户研究、VOC分析、行为分析、Persona、访谈辅助、用户调研、用户画像、用户反馈、用户访谈。

  • Business orchestrator

    LuckyOneTwoThree/pm-skill/pm-02-strategy/orchestrators/business-orchestrator Skill

    no license6★ repo

    当需要设计或评估产品商业模式时使用。商业模式指挥官,调度business-model-canvas/value-fit/pricing/strategy-report。关键词:商业模式、商业画布、定价策略、商业战略报告、怎么赚钱、盈利模式、收费模式、商业评估。

  • Planning orchestrator

    LuckyOneTwoThree/pm-skill/pm-02-strategy/orchestrators/planning-orchestrator Skill

    no license6★ repo

    当需要进行产品立项、战略规划或路线图制定时使用。战略规划指挥官,调度产品提案、战略分析(SWOT/Ansoff/波特五力)、OKR、北极星、路线图等子Skill。关键词:产品立项、战略规划、SWOT、OKR、路线图、战略分析、制定目标、产品规划、年度规划。

  • Positioning orchestrator

    LuckyOneTwoThree/pm-skill/pm-02-strategy/orchestrators/positioning-orchestrator Skill

    no license6★ repo

    当需要确定产品定位或评估差异化策略时使用。产品定位指挥官,调度positioning-strategy。关键词:产品定位、差异化、价值曲线、竞争策略、品牌定位、市场定位、竞争优势。本编排器为透传编排器,仅调度1个子Skill(positioning-strategy),上层编排器也可直接调用positioning-strategy。

  • Stakeholder orchestrator

    LuckyOneTwoThree/pm-skill/pm-02-strategy/orchestrators/stakeholder-orchestrator Skill

    no license6★ repo

    当需要进行Stakeholder管理或战略文档编写时使用。Stakeholder对齐指挥官,调度stakeholder-analysis。关键词:Stakeholder对齐、战略文档、战略沟通、利益相关者、干系人管理、对齐沟通。

  • Design orchestrator

    LuckyOneTwoThree/pm-skill/pm-03-design/orchestrators/design-orchestrator Skill

    no license6★ repo

    当需要生成PRD、信息架构、用户流程、原型或交互规范时使用。产品设计指挥官,调度design-prd/design-ia/design-userflow/design-prototype/interaction-spec/design-handoff-spec/change-impact-analysis。需求管理功能(需求收集、理解、优先级排序、需求规格)已由 design-prd 覆盖。PRD变更时触发 change-impact-analysis 评估下游影响。关键词:产品设计、PRD、信息架构、原型、交互规范、设计交接、写PRD、产品文档、设计输出、变更影响分析。

  • Ideation orchestrator

    LuckyOneTwoThree/pm-skill/pm-03-design/orchestrators/ideation-orchestrator Skill

    no license6★ repo

    当需要发散创意或构思解决方案时使用。创意发散与方案构思子模块指挥官,调度子Skill:ideation-workshop。关键词:创意发散、HMW、SCAMPER、方案构思、产品创意、思维逆转、方案收敛、头脑风暴、创新方案、创意工作坊。

  • Requirements orchestrator

    LuckyOneTwoThree/pm-skill/pm-03-design/orchestrators/requirements-orchestrator Skill

    no license6★ repo

    当需要管理产品需求时使用。需求管理子模块指挥官,调度子Skill:requirements-collection、requirements-understanding、requirements-prioritization。关键词:需求管理、需求收集、需求优先级、需求分析、需求分类、RICE评分、MoSCoW。

  • Validation orchestrator

    LuckyOneTwoThree/pm-skill/pm-03-design/orchestrators/validation-orchestrator Skill

    no license6★ repo

    当需要验证产品方案时使用。方案验证子模块指挥官,调度子Skill:validation-assumption-map、validation-mvp、validation-experiment、validation-usability。关键词:方案验证、假设验证、MVP、可用性测试、实验设计、假设地图、风险评估、验证想法、最小可行产品。

  • Design handoff spec

    LuckyOneTwoThree/pm-skill/pm-03-design/skills/design-handoff-spec Skill

    no license6★ repo

    当设计阶段完成需要交付给开发团队时使用。开发交接摘要自动生成,整合页面清单、路由结构、功能需求和待确认项,产出面向开发的交接文档。关键词:设计交接、设计交付、Handoff、开发对接、交付文档。

  • Metrics orchestrator

    LuckyOneTwoThree/pm-skill/pm-04-metrics-design/orchestrators/metrics-orchestrator Skill

    no license6★ repo

    当需要构建产品度量体系时使用。产品度量设计子模块指挥官,调度子Skill:metrics-system(指标体系自动构建)、tracking-plan(埋点方案自动生成)、metrics-dashboard(Dashboard自动配置)。关键词:度量设计、指标体系、埋点方案、Dashboard配置、数据指标、KPI设计、数据埋点。

  • Analysis orchestrator

    LuckyOneTwoThree/pm-skill/pm-05-metrics-ops/orchestrators/analysis-orchestrator Skill

    no license6★ repo

    当需要进行数据异常检测、漏斗分析或留存分析时使用。数据分析指挥官,调度analysis-anomaly/funnel/retention/data-analysis-report。关键词:数据分析、异常检测、漏斗分析、留存分析、Aha Moment、看数据、数据不好、数据洞察。

  • Decision orchestrator

    LuckyOneTwoThree/pm-skill/pm-05-metrics-ops/orchestrators/decision-orchestrator Skill

    no license6★ repo

    当需要将数据分析结果转化为决策行动时使用。数据驱动决策指挥官,调度 decision-dace(DACE决策循环+洞察转化)、decision-culture(数据文化建设),实现从数据到决策的闭环。关键词:数据决策、DACE循环、数据洞察、决策框架、数据文化、decision-dace、decision-culture、数据驱动、决策支持。

  • Experiment orchestrator

    LuckyOneTwoThree/pm-skill/pm-05-metrics-ops/orchestrators/experiment-orchestrator Skill

    no license6★ repo

    当需要设计或执行A/B测试实验时使用。实验验证指挥官,调度experiment-design/execution。关键词:A/B测试、实验设计、统计显著性、实验执行、效果验证、AB测试、对照实验。

  • Acquisition orchestrator

    LuckyOneTwoThree/pm-skill/pm-06-growth/orchestrators/acquisition-orchestrator Skill

    no license6★ repo

    当需要评估获客渠道或优化获客漏斗时使用。用户获取指挥官,调度 acquisition-analysis(获客分析一体化),实现从渠道评估到漏斗优化的闭环。关键词:用户获取、获客渠道、漏斗优化、渠道评估、获客策略、acquisition-analysis、拉新、获客。

  • Activation orchestrator

    LuckyOneTwoThree/pm-skill/pm-06-growth/orchestrators/activation-orchestrator Skill

    no license6★ repo

    当需要识别Aha Moment或设计Onboarding流程时使用。用户激活指挥官,调度activation-aha/onboarding。关键词:用户激活、Aha Moment、Onboarding、新用户引导、新手引导、激活率。

  • Growth orchestrator

    LuckyOneTwoThree/pm-skill/pm-06-growth/orchestrators/growth-orchestrator Skill

    no license6★ repo

    当需要制定增长策略或系统化推进增长时使用。增长策略总指挥官,先诊断增长模式,再按需调度获客/激活/留存/变现子编排器。关键词:增长策略、增长模式、AARRR、增长飞轮、增长体系、用户增长、增长瓶颈、增长诊断。

  • Retention orchestrator

    LuckyOneTwoThree/pm-skill/pm-06-growth/orchestrators/retention-orchestrator Skill

    no license6★ repo

    当需要降低流失率或提升用户参与度时使用。用户留存指挥官,调度 retention-management(留存管理一体化),实现从流失预防到用户促活的闭环。关键词:用户留存、流失预警、分层运营、参与度、留存策略、retention-management、防流失、促活。

  • Revenue orchestrator

    LuckyOneTwoThree/pm-skill/pm-06-growth/orchestrators/revenue-orchestrator Skill

    no license6★ repo

    当需要优化付费转化或提升收入时使用。商业化指挥官,调度 revenue-funnel(付费漏斗分析)、revenue-nrr(NRR追踪预警)、revenue-upsell(升级转化),实现从付费漏斗分析到增购策略的闭环。关键词:商业化、付费漏斗、NRR、增购策略、收入优化、revenue-funnel、revenue-nrr、revenue-upsell、赚钱、变现、付费转化。

  • Diagnosis orchestrator

    LuckyOneTwoThree/pm-skill/pm-07-monitoring/orchestrators/diagnosis-orchestrator Skill

    no license6★ repo

    当需要诊断产品健康度或追踪竞品动态时使用。智能诊断指挥官,调度 diagnosis-health、diagnosis-competition、competitor-monitoring-report、product-sunset-plan 子Skill执行。关键词:智能诊断、健康度评分、竞品追踪、问题归因、MTTR、竞品监控、产品下线、产品诊断、问题排查。

  • Iteration orchestrator

    LuckyOneTwoThree/pm-skill/pm-07-monitoring/orchestrators/iteration-orchestrator Skill

    no license6★ repo

    当需要规划迭代周期或调整产品优先级时使用。迭代决策指挥官,调度 iteration-decision 子Skill执行。关键词:迭代决策、Backlog优化、优先级调整、迭代复盘、迭代规划、需求重组、RICE评分、迭代管理。本编排器为透传编排器,仅调度1个子Skill(iteration-decision),上层编排器也可直接调用iteration-decision。

  • Monitoring orchestrator

    LuckyOneTwoThree/pm-skill/pm-07-monitoring/orchestrators/monitoring-orchestrator Skill

    no license6★ repo

    当需要建立产品监控体系或处理异常告警时使用。监控预警指挥官,调度 monitoring-pipeline、user-feedback-loop-report 子Skill执行。关键词:监控预警、异常检测、告警分级、监控系统、健康监控、监控仪表盘、告警升级、反馈闭环、线上告警、系统监控。

  • Release orchestrator

    LuckyOneTwoThree/pm-skill/pm-07-monitoring/orchestrators/release-orchestrator Skill

    no license6★ repo

    当需要执行产品发布交付流程时使用。发布交付指挥官,调度质量验收、发布检查、灰度发布和发布说明的完整发布流程。关键词:产品发布、上线、灰度、发布检查、发布说明、交付、验收发布。

  • Agile orchestrator

    LuckyOneTwoThree/pm-skill/pm-08-project/orchestrators/agile-orchestrator Skill

    no license6★ repo

    当需要管理Sprint周期或追踪敏捷执行时使用。敏捷执行指挥官,调度 agile-sprint-planning、agile-daily-sync、agile-review 子Skill执行。agile-review 已合并 retrospective-auto 的自动回顾能力。关键词:敏捷执行、Sprint规划、每日站会、Sprint评审、敏捷管理、Sprint复盘、迭代复盘、敏捷开发、复盘报告、自动回顾。

  • Project planning orchestrator

    LuckyOneTwoThree/pm-skill/pm-08-project/orchestrators/project-planning-orchestrator Skill

    no license6★ repo

    当需要启动新项目或进行项目规划时使用。项目规划指挥官,调度 planning-project-charter、planning-resource、planning-kickoff 子Skill执行。关键词:项目规划、项目宪章、资源规划、Kickoff、项目启动、项目章程、资源分配、立项。