智能体
Agent 规划、多步流程与编排
create-member
atrislabs
"Create and manage AI team members using the MEMBER.md format. Use when the user wants to define a new AI role, set up a team member, create an agent persona, or work with team/MEMBER.md files."
autopilot
atrislabs
"Run ONE autopilot tick. Reads identity (flow) + horizon (endgame), shows a visual status block, picks the next [endgame] task or seeds a new endgame at boundaries, then executes plan→do→review. Lessons compound to atris/lessons.md. Triggers on: autopilot, run one tick, ship one thing, do the next thing, get this done."
member-runtime
atrislabs
"Load and run MEMBER.md team members -- complete AI workers with persona, skills, tools, context, and a journal that learns over time. Use when you want to activate a team member, run 'be my chief of staff', or manage stateful AI workers."
jenkinsfile-generator
akin-ozer
Comprehensive toolkit for generating best practice Jenkinsfiles for both Declarative and Scripted pipeline syntaxes. Use this skill when creating new Jenkins pipelines, implementing CI/CD workflows.
brainctl
TSchonleber
"Unified agent memory CLI — read, write, search, and maintain the shared memory spine (brain.db). Use for persistent cross-session memory, knowledge graph, event logging, decisions, affect tracking, and consolidation."
payram-stablecoin-payments
PayRam
Accept USDT and USDC stablecoin payments with PayRam's self-hosted gateway. No KYC, no signup, no intermediary custody. Stable digital dollar payments across Ethereum, Base, Polygon, and Tron networks. Keyless architecture with smart contract sweeps to cold wallets. Deploy in 10 minutes. Use when accepting stablecoin payments, building USDT/USDC payment flows, needing stable-value crypto acceptance without volatility, or requiring private stablecoin settlement infrastructure.
remediation-verifier
RHEcosystemAppEng
CRITICAL: This skill must be used for remediation verification. DO NOT use raw MCP tools like get_cve or get_host_details directly for verification. Verify CVE remediation success by checking Red Hat Lightspeed CVE status, validating package versions, and confirming service health. Use this skill after executing remediation playbooks to ensure vulnerabilities are properly fixed. This skill orchestrates MCP tools (get_cve, get_cve_systems, get_host_details) to provide comprehensive remediation verification including CVE status checking, package version validation, and service health confirmation. IMPORTANT: ALWAYS use this skill instead of calling verification MCP tools directly.
fleet-inventory
RHEcosystemAppEng
Query and display Red Hat Lightspeed managed system inventory. Use this skill for information-gathering requests about the fleet, registered systems, or inventory queries. This skill focuses on discovery and listing only - for remediation actions, transition to the sre-agents:remediator agent (invoke the sre-agents:remediator agent). When to use this skill: - "Show the managed fleet" - "List all systems registered in Lightspeed" - "What systems are affected by CVE-X?" - "How many RHEL 8 systems do we have?" - "Show me production systems" When NOT to use this skill (use sre-agents:remediator agent instead): - "Remediate CVE-X on these systems" - "Create a playbook for..." - "Patch system Y" This skill orchestrates MCP tools from lightspeed-mcp to provide comprehensive fleet visibility and system inventory management.
playbook-executor
RHEcosystemAppEng
CRITICAL: This skill must be used for Ansible playbook execution. DO NOT use raw MCP tools like execute_playbook or get_job_status directly. Execute Ansible remediation playbooks and track job status through the mock Ansible MCP server. Use this skill after generating a playbook to execute it and monitor completion status. The skill handles temporary file creation, job submission, status polling, and completion reporting. This skill orchestrates MCP tools (execute_playbook, get_job_status) from ansible-mcp-server to provide reliable playbook execution with job tracking and status monitoring. IMPORTANT: ALWAYS use this skill instead of calling execute_playbook or get_job_status directly.
vm-snapshot-create
RHEcosystemAppEng
Create virtual machine snapshots for backup and recovery with comprehensive storage backend analysis. Use when: - "Create a snapshot of VM [name]" - "Backup VM [name] before upgrade" - "Take a snapshot of [vm]" Analyzes storage capabilities, guest agent status, and consistency guarantees before creating snapshots. NOT for VM cloning (use vm-clone to create independent copies).
system-context
RHEcosystemAppEng
CRITICAL: This skill must be used for system inventory and context gathering. DO NOT use raw MCP tools like get_cve_systems or get_host_details directly. Gather comprehensive system inventory and deployment context for CVE-affected systems, including RHEL version detection, environment classification, and deployment analysis. Use this skill when you need to understand system infrastructure before planning remediation. This skill orchestrates MCP tools (get_cve_systems, get_host_details) to provide comprehensive system analysis with RHEL version detection, environment classification, and remediation strategy determination. IMPORTANT: ALWAYS use this skill instead of calling get_cve_systems or get_host_details directly for system context gathering.
execution-summary
RHEcosystemAppEng
This skill should be used when the user asks to "generate execution summary", "create execution report", "summarize what was used", "show execution summary", or "what agents/skills/tools were used". Generates a concise report of agents, skills, tools, and documentation accessed during a workflow for audit and learning purposes.
cve-impact
RHEcosystemAppEng
CRITICAL: This skill must be used for ALL CVE discovery and listing queries. DO NOT use raw MCP tools like get_cves directly. Use this skill when users request: - Listing critical/high-severity CVEs: "show me critical vulnerabilities", "what are the most critical CVEs", "list all high-severity vulnerabilities" - CVE discovery: "what vulnerabilities affect my account", "show me all CVEs", "what are my security risks" - CVE impact analysis for specific CVEs: "what's the impact of CVE-X?", "analyze CVE-Y" - Risk assessment: "which CVEs are most urgent?", "prioritize vulnerabilities" - Understanding affected systems for a CVE - Comparing CVE severity levels - CVE discovery and prioritization (information gathering) DO NOT use this skill when users request remediation actions like: - "Create a remediation playbook" (use sre-agents:remediator agent) - "Patch CVE-X on system Y" (use sre-agents:remediator agent) - "Remediate these CVEs" (use sre-agents:remediator agent) This skill orchestrates MCP tools (get_cves, get_cve, get_cve_systems) to provide comprehensive CVE analysis with Red Hat Lightspeed context. When users ask for remediation after seeing the analysis, invoke the sre-agents:remediator agent. IMPORTANT: ALWAYS use this skill instead of calling get_cves or other vulnerability MCP tools directly.
find-cause
Jamie-BitFlight
Wraps investigation requests with evidence-chain discipline. Use when asked to find out why something happens, research a root cause, debug an issue, or investigate unexpected behavior. Transforms vague investigation requests into reproducible-proof investigations with a 5-step protocol — disambiguate, reproduce, read source, build evidence chain, present findings. Invoke with /find-cause followed by a description of what to investigate.
codebase-auditor
Jamie-BitFlight
"Local codebase analysis research angle — derives behavioral contracts, coding conventions, SKILL.md flow insertion points, and agent data availability maps from actual source files. Use when the blocking question is answered by reading the repository: what does this function actually do, what pattern does the codebase use for X, where in this workflow does a new step go, or what data does this agent already have."
arl
Jamie-BitFlight
Knowledge reference for Autonomous Refinement Loop research — pattern research into prerequisites for autonomous execution without synchronous human blocking gates. Defines failure categories, prerequisites, and conditions for replacing human judgment with machine-verifiable checks. Use when designing or evaluating autonomous agent loops, gate conditions, or HOOTL execution patterns.
agent-capability-analyzer
Jamie-BitFlight
Runs the description-drift experiment — spawns all Claude Code agents simultaneously to collect self-reported capabilities, then compares them against static frontmatter descriptions to reveal how reliable orchestrator routing based on descriptions actually is. Use when measuring description drift across the agent fleet, re-running the capability collection experiment, analyzing a specific agent's self-reported capabilities, or auditing whether frontmatter descriptions accurately reflect agent behavior.
orchestrator-discipline
Jamie-BitFlight
Orchestrator context window discipline enforcement. Prevents the orchestrator from reading source files it will not edit, running diagnostic commands that waste context, and rationalizing delegation bypasses. Use when setting up orchestrator guardrails, reviewing delegation discipline, or diagnosing context window waste in multi-agent workflows. Activates PreToolUse hooks that surface decision points before source file reads and diagnostic command execution.
agent-creator
Jamie-BitFlight
Create high-quality Claude Code agents from scratch or by adapting existing agents as templates. Use when the user wants to create a new agent, modify agent configurations, build specialized subagents, or design agent architectures. Guides through requirements gathering, template selection, and agent file generation following Anthropic best practices (v2.1.63+).
session-historian
Jamie-BitFlight
Look up prior Claude Code sessions when context is lost or forgotten. Use when asked what was done before, what happened in the last session, or any request to recall past conversation history, prior decisions, experiments, or outcomes. Indexes and searches raw JSONL transcripts from ~/.claude/projects/ via DuckDB. Returns verbatim user messages, summarizes AI actions and sub-agent outcomes, detects tool errors and user frustration signals, and reports tool usage statistics. Summaries cached at ~/.claude/kaizen/session-summaries/.
agentskills
Jamie-BitFlight
Agent Skills Open Standard reference (agentskills.io). Use when creating portable skills for Claude Code, Cursor, Gemini CLI, OpenAI Codex, VS Code, Roo Code, and 20+ compatible agents. Covers frontmatter schema, naming rules, directory structure, progressive disclosure, validation, and authoring. Load before creating cross-agent skills.
external-pattern-integrator
Jamie-BitFlight
Integrates patterns from external sources (URLs or local files) into local skills, agents, and plugins. Use when comparing external agent definitions against local equivalents, extracting best practices from frameworks like GSD or BMAD-METHOD, enhancing local skills with external workflow patterns, or adding interoperability with external tool ecosystems. Runs a 3-phase workflow — parallel candidate mapping, contextual enhancement, and validation — with source attribution and backlog tracking for deferred enhancements.
assessor
Jamie-BitFlight
Assess a plugin and create refactoring task files for parallel agent execution. Use when you need to analyze a plugin structure, score its quality, and generate a phased refactoring plan with design map and implementation tasks.
prepare-walkthrough-presentation
Jamie-BitFlight
Transforms validated /linear-walkthrough artifacts into one presentation-ready deck outline per major codebase component. Use when the user asks to create a presentation, prepare a walkthrough deck, build an onboarding deck, produce an architecture review deck, or summarize a codebase for a technical audience. Requires walkthrough directory output -- reads unified walkthrough, per-section files, validation reports, coverage maps, entry points, and open questions -- then orchestrates four parallel agent phases to produce slide outlines with speaker notes, evidence references, and suggested visuals.