智能体
Agent 规划、多步流程与编排
agents-md-improver
ericmjl
Keeps repo-local agent instructions consistent by proposing updates to AGENTS.md when a user corrects the coding agent or asks to change AGENTS.md, CLAUDE.md, .claude/CLAUDE.md, or GEMINI.md.
find-skills
xopcai
Find and evaluate installable agent skills across the XOPC Store, ClawHub, and skills.sh. Use when a user asks whether a skill exists, wants capability recommendations, or wants help choosing a high-value skill.
agent-tail
gillkyle
Capture browser console logs and dev server output to files with agent-tail. Use when debugging runtime errors, checking console output, tailing or diagnosing logs, or setting up Vite/Next.js log capture.
context-degradation
shipshitdev
Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent performance degrades unexpectedly, or debugging agent failures.
dispatching-parallel-agents
derKlinke
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
ai-dev-loop
shipshitdev
Orchestrate autonomous AI development with task-based workflow and QA gates
context-optimization
shipshitdev
Apply optimization techniques to extend effective context capacity. Use when context limits constrain agent performance, when optimizing for cost or latency, or when implementing long-running agent systems.
evaluation
shipshitdev
Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.
multi-agent-ai-projects
ilude
Guidelines for multi-agent AI and learning projects with lesson-based structures. Activate when working with AI learning projects, experimental directories like .spec/, lessons/ directories, STATUS.md progress tracking, or structured learning curricula with multiple modules or lessons.
researching-web
alexei-led
Web research via Perplexity AI. Use for technical comparisons (X vs Y), best practices, industry standards, documentation. Triggers on "research", "compare", "vs", "best practice", "which is better", "pros and cons".
creating-an-agent
ed3dai
Use when creating specialized subagents for Claude Code plugins or the Task tool - covers description writing for auto-delegation, tool selection, prompt structure, and testing agents
verification-before-completion
ed3dai
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
testing-skills-with-subagents
ed3dai
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes
using-generic-agents
ed3dai
Use to decide what kind of generic agent you should use
walkie
vikasprogrammer
P2P communication between AI agents using walkie-sh CLI. Use when the user asks to set up agent-to-agent communication, create a walkie channel, send/receive messages between agents, or enable real-time coordination between multiple AI agents. Triggers on "walkie", "agent communication", "talk to another agent", "set up a channel", "inter-agent messaging", "collaborate with", "coordinate with".
ux-lean-ux
geekatron
"Lean UX hypothesis-driven design sub-skill for the /user-experience parent skill. Facilitates Build-Measure-Learn cycles using Jeff Gothelf and Josh Seiden's Lean UX methodology (3rd ed. 2021). Produces hypothesis backlogs, assumption maps, MVP experiment designs, and validated learning logs. Invoke when teams need hypothesis-driven iteration, assumption mapping, experiment design, or validated learning documentation. Invoked by ux-orchestrator during Wave 2 lifecycle-stage routing or when user intent is \"testing hypotheses\" during the \"During design\" stage. Triggers: lean UX, hypothesis, assumption mapping, build-measure-learn, MVP experiment, validated learning, experiment design, hypothesis backlog."
ux-atomic-design
geekatron
"Atomic Design component taxonomy sub-skill for the /user-experience parent skill. Implements Brad Frost's 5-level component hierarchy (Atoms, Molecules, Organisms, Templates, Pages) for design system architecture. Produces component inventories, design token audits, composition rules, and Storybook coverage reports. Invoke when teams need component taxonomy construction, design system architecture, Storybook integration, design token consistency analysis, or component reuse auditing. Invoked by ux-orchestrator during Wave 3 lifecycle-stage routing or when user intent is \"Building component system\" during the \"During design\" stage. Triggers: atomic design, component taxonomy, design tokens, Storybook, atoms molecules organisms, design system, component inventory, component library."
ux-ai-first-design
geekatron
"AI-first interaction design sub-skill (CONDITIONAL) for the /user-experience parent skill. Provides trust-calibrated AI interaction design guidance using Yang et al.'s trust-risk and error-risk classification framework. Produces interaction pattern recommendations, trust calibration assessments, feedback loop designs, and progressive disclosure strategies for AI-powered features. CONDITIONAL: requires WSM >= 7.80 AND enabler research (FEAT-020) complete; otherwise routes to /ux-heuristic-eval with PAIR protocol. Invoke when teams need to design AI-powered interactions, calibrate user trust in AI outputs, classify AI error risks, design human-AI handoff patterns, or audit existing AI interfaces for trust and safety. Triggers: AI-first design, AI interaction, trust calibration, AI UX, conversational UX, AI interface, LLM interface, agentic UX, human-AI interaction, AI transparency, AI error handling, AI onboarding, progressive AI disclosure, trust-risk, error-risk."
pm-pmm
geekatron
Product management and product marketing decision framework. Invoke when users need product strategy (PRDs, vision, roadmaps), customer insight (personas, journey maps, VOC), business analysis (business cases, market sizing, pricing), competitive intelligence (battle cards, win/loss, competitive analysis), or go-to-market planning (GTM plans, positioning, MRDs, buyer personas). Uses 18 validated industry frameworks organized around Cagan's Value Risk and Business Viability Risk domains. Supports discovery mode (hypothesis-driven) and delivery mode (stakeholder-ready). Trigger keywords: PRD, product requirements, roadmap, prioritize, RICE, persona, journey map, VOC, business case, market sizing, TAM, competitive analysis, battle card, GTM, go-to-market, positioning, messaging, MRD.
orchestration
geekatron
Multi-agent workflow orchestration with state tracking, checkpointing, and cross-pollinated pipelines. Use when coordinating parallel agent pipelines, managing sync barriers, or tracking complex workflow execution state across sessions.
ux-heuristic-eval
geekatron
"Nielsen heuristic evaluation sub-skill for the /user-experience parent skill. Evaluates interfaces against Nielsen's 10 usability heuristics, produces severity-rated findings on a 0-4 scale (Cosmetic to Catastrophic), and generates remediation recommendations with effort estimates. Invoke when teams need structured usability evaluation, interface review, heuristic audit, or severity-rated UX findings. Invoked by ux-orchestrator during Wave 1 lifecycle-stage routing or CRISIS mode triage. Triggers: heuristic evaluation, usability audit, Nielsen heuristics, interface review, severity rating, usability inspection, UX evaluation."
adversary
geekatron
On-demand adversarial quality reviews using strategy templates. Selects strategies by criticality level, executes adversarial templates against deliverables, and scores quality using LLM-as-Judge rubric. Integrates with quality-enforcement.md SSOT.
ux-behavior-design
geekatron
"Fogg Behavior Model B=MAP bottleneck diagnosis sub-skill for the /user-experience parent skill. Diagnoses why users fail to take desired actions by analyzing the three B=MAP factors (Motivation, Ability, Prompt) and identifying which factor falls below the action threshold. Produces bottleneck diagnoses, factor-level assessments, and intervention recommendations with synthesis confidence gates. Invoke when teams need to understand why users are not completing a specific action, diagnose behavioral bottlenecks, design behavior change interventions, or analyze post-launch user inaction patterns. Invoked by ux-orchestrator during Wave 4 lifecycle-stage routing or when user intent is \"Users not completing action\" during the \"After launch\" stage. Triggers: behavior design, B=MAP, Fogg model, behavior bottleneck, motivation analysis, ability analysis, prompt design, why users don't, user inaction, behavior diagnosis, tiny habits, action threshold."
ux-jtbd
geekatron
"Jobs-to-Be-Done research and analysis sub-skill for the /user-experience parent skill. Conducts JTBD job statement synthesis, switch interview analysis (Moesta/Spiek four forces), outcome-driven innovation (Ulwick ODI), and job mapping for tiny teams (1-5 people). Invoked by ux-orchestrator when users need to understand user motivations, map jobs to be done, identify switch triggers, or produce job maps with outcome expectations. Sub-skill of /user-experience; routed via ux-orchestrator lifecycle-stage triage. Triggers: JTBD, jobs to be done, switch interview, job mapping, user motivation, outcome, hiring criteria, user jobs, switch forces."