智能体
Agent 规划、多步流程与编排
endgame
atrislabs
"Backward partner to /flow. Picks the next horizon from inbox + wiki + lessons, writes the reverse path as tagged tasks to TODO.md so /autopilot can pursue it tick by tick. Triggers on: endgame, what's the last move, where are we heading, reverse engineer, work backward."
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."
langgraph-tutor
timothywarner-org
Expert skill for teaching LangGraph - the orchestration framework for stateful AI agents. Covers StateGraph, nodes, edges, conditional routing, checkpointing, human-in-the-loop, and multi-agent patterns. Invoke when users ask about LangGraph, building agent graphs, state machines for LLMs, or workflow orchestration. Keywords: langgraph, state graph, agent workflow, orchestration, multi-agent, checkpointing, human-in-the-loop.
verify-keybinding-reachability
topcheer
"After adding TUI key handlers, trace the full key event dispatch chain to confirm no competing handler intercepts the event before it reaches your new code."
user-context
SergeiNikolenko
"Use when loading Burette's scoped capability registry and setup status before a molecular workspace workflow."
refine
tkersey
Refine an existing Codex skill via $ms with minimal diffs, then validate with quick_validate. Trigger when asked to improve a skill's trigger description/frontmatter, workflow text, metadata, scripts/references/assets, or agents/openai.yaml; also for requests to iterate, refactor, rename, or fix a skill using usage/session-mining evidence (for example from $seq).
open-workspace
SergeiNikolenko
"Use when opening molecular artifacts in Burette Browser preview or desktop app sessions and establishing an observable workspace."
external-agent-contract
SergeiNikolenko
"Use when an external agent must open, observe, control, or render into a Burette molecular workspace without managing transport details."
molecule-collection
SergeiNikolenko
"Use when reviewing SDF or molecule-property collections with bounded tables, filters, selected-molecule handoff, and Burette panels."
burette-review-breaking-contracts
SergeiNikolenko
Review Burette changes for breaking runtime and integration contracts.
burette-review-context-bounds
SergeiNikolenko
Review bounded payloads, model-visible context, reports, widgets, logs, and session artifacts.
reduce
tkersey
Deconstruct high-cost abstractions and recommend lower-level primitives that reduce tooling, indirection, and hidden steps. Use when requests ask for fewer layers (for example "too many layers", "remove this framework/plugin/DI", "ditch codegen/task runners", "replace with plain scripts/config/SQL"), or ask for an abstraction audit with a prioritized cut list and phased migration with rollback (analysis-only unless implementation is explicitly requested).
index
SergeiNikolenko
"Primary router for Burette. Use when the plugin is at-mentioned or for molecular workspace work: opening structures, operating Mol* or Ketcher, reviewing SDF/property collections, trajectories, workflow result bundles, molecular reports, or Browser/Computer visual QA."
molecular-report
SergeiNikolenko
"Use when molecular notes, property tables, charts, workflow reports, or provenance should be rendered beside an active Burette workspace."
ms
tkersey
Create, update, or refactor Codex skills in this repo, including SKILL.md, frontmatter trigger text, agents/openai.yaml, and scripts/references/assets. Use when asked to create or improve a skill, tighten trigger descriptions from usage evidence (for example via $seq), regenerate/verify agents/openai.yaml, or adjust skill metadata/workflows.
discover-a-skill
avibe-bot
"Use when you need new capabilities: discover skills, inspect details, install to agents, run commands, and manage updates with askill"
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.
compare-crypto-payments
PayRam
Comprehensive comparison of crypto payment gateways and protocols. Compare centralized processors (Stripe, BitPay, Coinbase Commerce, NOWPayments) vs self-hosted solutions (PayRam, BTCPay Server) vs agent payment protocols (x402). Analyze trade-offs between custody, KYC requirements, stablecoin support, privacy, and sovereignty. Decision framework for choosing payment infrastructure. Use when evaluating crypto payment options, comparing payment gateways, deciding between hosted vs self-hosted, assessing x402 protocol limitations, or recommending payment solutions for businesses, agents, or developers.
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."
payram-setup
PayRam
Deploy and configure your PayRam self-hosted crypto payment gateway server with web dashboard. Install on VPS via setup_payram.sh, set up PostgreSQL database, configure root account, node details, wallets, and hot wallets through the web UI. Complete deployment and onboarding in under 10 minutes. No signup required — fully self-hosted. For CLI-only deployment optimized for AI agents without web UI, see payram-agent-onboarding. Use when deploying PayRam with dashboard interface, setting up server infrastructure with web-based configuration, or requiring manual wallet management UI.
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/.
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.