ohdearquant/lionagi

debug

Systematic debug workflow: research → orchestrate agents → escalate. Suggest when: stuck after 2-3 attempts, unfamiliar tooling, tempted to "try random things", or errors don't match documentation.

原文の言語: 英語

fanout

Fan one task out to multiple independent lionagi workers through `fanout.submit`, optionally synthesizing their answers. Use when several parallel perspectives can work without dependency handoffs.

原文の言語: 英語

flow

Plan and run a dependency-aware lionagi DAG through `flow.submit`, including dry runs and reactive follow-up capacity. Use when work has stages, dependencies, parallel branches, or a final synthesis step.

原文の言語: 英語

orchestrate

Plan and execute multi-agent workflows through lionagi's orchestration MCP tool: flow.submit (DAG pipelines), fanout.submit (parallel workers), agent.submit (one agent), and play.submit (saved playbooks). Use when a task needs multiple agents working in…

原文の言語: 英語

play

Run an existing lionagi playbook through the orchestration MCP server and retrieve its background result. Use when a saved `.playbook.yaml` workflow should be executed with concrete input or declared arguments.

原文の言語: 英語

playbook

Author lionagi playbooks — reusable YAML workflow templates that define parametric agent tasks. Playbooks live at ~/.lionagi/playbooks/ and run via the `play.submit` MCP verb (or `li play <name>` from a lionagi checkout). Use when: creating reusable…

原文の言語: 英語

pr-review

Multi-perspective PR review procedure. Plan a minimal DAG of specialists scoped to what the PR actually touches, synthesize with a critic, post ONE consolidated comment per verbosity tier. Pull before any structured PR review so the methodology stays…

原文の言語: 英語

review

General-purpose code review checklist. Use when reviewing any code change without a narrower specialization. Complements security-review, pr-review (multi-perspective), and the other review skills — pull this when you need the standard correctness/quality…

原文の言語: 英語

security-review

Threat-model rubric for a focused security review of a code change. Use when reviewing auth / input validation / crypto / secrets / supply chain, or as the "security" dimension of a multi-perspective PR review. Pull this skill before starting so severity…

原文の言語: 英語

show

Orchestrate multi-play shows: decompose a complex goal into sequential plays (each a play.submit run through the plugin's MCP server), gate each output for quality, adapt the plan based on results, and merge work into an integration branch. Shows are rows in…

原文の言語: 英語

summarize

Mid-session context capture and proactive decision/pattern capture. Use when: significant progress made but session continues, approaching context limits, switching topics, checkpoint learnings, significant decisions made, patterns emerge, or session is…

原文の言語: 英語

tdd

Guide test-driven development workflow. Suggest when: "test first", "TDD", "write tests before", "red green refactor" mentioned, or when implementing features or bug fixes where a test-first approach is beneficial. Enforces Red-Green-Refactor cycle.

原文の言語: 英語

commit

Conventional Commits style guide + safety rules. Pull this before any git commit so the message shape and staging rules stay consistent.

原文の言語: 英語

hello

Minimal example — verify `li skill` prints the body.

原文の言語: 英語