메뉴
Guide for decomposing large tasks into a structured plan with dependency chains, managing priorities, and distributing work across agents. Outputs plan cards or delegation messages as the team contract; TodoList for personal micro-steps.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | task-planner |
| license | MIT |
| description | Guide for decomposing large tasks into a structured plan with dependency chains, managing priorities, and distributing work across agents. Outputs plan cards or delegation messages as the team contract; TodoList for personal micro-steps. |
This skill helps you turn ambiguous or large requests into a clear, sequenced plan with ownership and verification.
Split work into thin vertical slices:
Common slice types:
When delegating:
Example delegation message:
Please write tests for <feature>.
Constraints:
- Do not change implementation yet
- Use pytest
Acceptance:
- Tests fail before implementation
- Tests cover edge cases: <...>
For visual plans with Mermaid DAG visualization and step-level status tracking, post a plan card to Canvas:
# Post plan card with Mermaid DAG and step list
synapse canvas plan '{"plan_id":"plan-auth","status":"proposed","mermaid":"graph TD; A[Tests]-->B[Impl]-->C[Review]","steps":[{"id":"s1","subject":"Write auth tests","agent":"Tester","status":"pending"},{"id":"s2","subject":"Implement auth","agent":"Impl","status":"pending","blocked_by":["s1"]},{"id":"s3","subject":"Review","agent":"Tester","status":"pending","blocked_by":["s2"]}]}' --title "Auth Plan"
Plan cards are useful when the decomposition should be visible to the team in the Canvas dashboard. Use plan cards for plans with 3+ steps or complex dependency chains that benefit from DAG visualization.
Use a TodoList for your own micro-step tracking within a single task. TodoList items are fine-grained (one per coding step):
Include clear status updates in all communications:
"Write auth tests complete — 4 tests passing""Starting Implement auth module; tests are confirmed""Integration test waiting — implementation not yet complete"Synapse A2A agent communication -- sending messages, spawning agents, delegating tasks, sharing memory, managing the LLM wiki, and coordinating file edits. Use this skill when: running synapse send/reply/broadcast/interrupt, spawning agents with synapse spawn or synapse team start, sharing knowledge with synapse memory, managing wiki pages with synapse wiki, locking files with synapse file-safety, checking agent status with synapse list/status, or orchestrating any multi-agent workflow. For AI/programmatic use, prefer synapse list --json, synapse status <target> --json, or the MCP list_agents tool instead of interactive synapse list.
Multi-agent management workflow — task delegation, progress monitoring, quality verification with regression testing, feedback delivery, and cross-review orchestration. Use this skill when coordinating multiple agents on a shared task, monitoring delegated work, ensuring quality across agent outputs, or implementing a multi-phase plan (3+ phases or 10+ file changes).
Bootstrap a new GitHub issue implementation in one command: fetch the issue body, gather cross-references and code hotspots, infer a branch prefix and slug, generate a structured task brief, create a fresh branch from latest main, and (by default) spawn a codex agent to implement it. Triggered by /dev-issue <number>. Use this skill when starting work on a new issue that follows the standard issue → codex spawn → review → PR pipeline.
Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for", "read the source of", "how does X work internally", "get the implementation of", "opensrc path", or any task requiring access to dependency source code beyond types and docs.
Design, review, and improve Claude/Codex skills based on Anthropic's "The Complete Guide to Building Skills for Claude". Use when creating a new skill, rewriting SKILL.md frontmatter and workflows, fixing under-triggering or over-triggering, designing scripts/references/assets, building test cases, or preparing a skill for upload/distribution.
Guide API design for REST, GraphQL, gRPC, and CLI interfaces. Use this skill when designing new APIs, reviewing existing API contracts, or establishing API conventions for a project. Produces consistent, well-documented API specifications.