본문으로 건너뛰기
cccskills
무료GitHub에 공개

plan

Shape a request into one end-to-end slice with observable behavior; review write scope and reversible decisions. Use when: planning, breaking down or scoping a change.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(6)

  • SKILL.md7.2 KB
  • references/challenge.md3.4 KB
  • references/ground-truth-routing.md3.7 KB
  • references/plan.feature1.2 KB
  • references/resume-and-handoff.md3.3 KB
  • scripts/validate.sh1.5 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Plan

Shape missing intent into one actionable slice, then stop. A clear change can proceed directly; load a specialist only for the question it answers. Prefer the caller's tracker, if any; otherwise use the conversation or supplied text. Planning produces no AgentOps packet.

A plan meets these rules

  1. One slice, not a roadmap. Shape the narrowest change that produces an observable result end to end, through every layer it touches. No phases, no layer-by-layer breakdown, no backlog: later work stays one coarse line each until new evidence makes it the next slice.
  2. An example before any design. Write at least one Given/When/Then with an observable result. Cover the boundary where a mistake is costly to undo, such as a repeated or external side effect, lost data or widened access, not only the happy path.
  3. Look up facts; ask only for choices. Read code, docs and the tracker instead of asking. Ask the caller at most one question, only for a choice no source can answer, with your recommendation and its tradeoff.
  4. The repository's words. Reuse the term its code, glossary or tracker defines; never coin a parallel name.
  5. Scope by consumer. Name the owners to edit, every live caller and test of the changed behavior, and generated companions as a class. Scope is authority, not a predicted file count.
  6. A discriminating check: what fails today and passes after the slice.

Output

Write this block into the caller's existing intent (tracker item or conversation). It is the whole plan.

Outcome:  <who observes what, in the repository's terms>
Example:  Given <state>, when <event>, then <observable result>
Slice:    <the one end-to-end change that makes the example true>
Scope:    <owners>; consumers: <live callers and tests>; generated: <class> | none
Check:    <the test or observation that fails now and passes after the slice>
Question: <one caller choice, your recommendation, its tradeoff> | none
Later:    <deferred item and the evidence that would make it next> | none

Add an Example line only for another consequential boundary, and a non-goal only where it prevents a plausible scope mistake.

Workflow

  1. Read the accepted intent, any existing plan or native handoff, and the relevant source owners and active constraints. Reuse the acceptance already supplied in the conversation or bead; clarify only what prevents action or judgment. To resume or replace another context, hand a slice on, plan code together with a requested retrospective, or keep an exact snapshot of conversation intent, follow resume and handoff.
  2. Route only the uncertainty that could change the slice (table below).
  3. Fill the block. A mechanical cross-cutting migration that cannot stay working slice by slice uses expand, migrate, contract and states where integration is required. Include recapture of affected bound evidence where necessary; in repositories with AgentOps provenance bindings, ao provenance evidence-orphans finds it. Across an epic, Navigate picks the next bead; Plan shapes that bead.
  4. When evidence disproves an approach, keep the failed assumption, its evidence and the revised check in the existing intent. An approach change within accepted outcome and scope needs no new permission; acceptance or scope expansion needs the caller. Never relabel a failed acceptance condition as a caveat to obtain green.

Stop planning once the implementer can act and the validator can judge. More research, decomposition or review must resolve a named remaining uncertainty; reserve capacity for implementation, integration and repair.

Route uncertainty

UncertaintyNext action
Fact a source can answerInspect the smallest authoritative source and cite it. Research owns deeper tracing; Domain owns disputed vocabulary. Never ask the caller to recite it.
Caller choiceRecover existing authorization first. What remains is the one question, with its concrete tradeoff; an agent cannot supply the caller's answer.
Assumption only an observation can settleState the competing predictions and the smallest observation that separates them, using an optional probe or prototype. A persuasive design or an agent vote cannot settle unobserved behavior.
Safely deferredPut it under Later with the event or evidence that would make it relevant. Deferral cannot hide an unanswered acceptance condition.

Resolve reversible implementation details within accepted scope. Mark inference and missing evidence; never promote either into a source fact or a settled caller choice. For consequential uncertainty that survives source checks and observation, an optional challenge returns advice or a next discriminator, never permission or acceptance. Memory recall helps only when prior evidence could change the next action.

Who decides

Use real undo cost, affected users and existing authority. A material irreversible choice outside that authority goes to the caller; prior authorization stays valid. Reviewer agreement is evidence, not permission to replace the caller's intent: explain a consequential disagreement and its support instead of silently changing acceptance. A proposed process artifact needs a concrete consumer, the decision it gates, an observed defect and a retirement condition; otherwise omit it.

Examples and naming

An example can be plain text; BDD needs no .feature file or interview. In a repository that calls queued work a Job:

Given a Job has already completed, when the worker receives it again, then its completed result is returned and its side effect is not repeated.

Write "Job", not a parallel label such as "task item". Keep the accepted example available to Implement and Validate; tests added after coding may supplement it but cannot redefine what was promised. For product planning, separate demonstrated behavior from aspiration; an ordinary feature needs no product document.

Scope

Use normalized repository-relative scope patterns. An uncovered live consumer needs a concise exact-file amendment to the caller; continue independent in-scope work meanwhile. Generated companions already in scope need no extra permission. Boundaries keep work and status in the caller's tracker and delivery under repository policy.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Use AtomLane to compile and execute safe atomic parallel plans on macOS and native Windows Preview for worthwhile independent argv tasks, dependency DAGs, supported platform entrypoints, or Apple-silicon operators. Use at task start or an execution boundary when structured local work may contain two or more worthwhile units; skip plain answers, one quick command, and work whose effects cannot be safely bounded.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

hashgraph-online/awesome-codex-plugins1.4천2026년 10월 19일 업데이트

add

무료

Register a deferred decision in the debt registry. Trigger by judgment, not a marker scan, whenever a future reader would ask "why this way?": an unmade decision, stub, loosened type, bypassed check, swallowed error, a default picked "for now", or a TODO/FIXME/HACK/XXX marker. Trigger immediately whenever you defer work, or when the user invokes $add. Over-register freely; the developer drops with "drop A", "drop A,C", or "drop all".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

hashgraph-online/awesome-codex-plugins1.4천2026년 10월 19일 업데이트

ADK 框架适配层。为 LangChain / EINO / AutoGen / AgentScope / CrewAI 提供框架特定的 代码模板、惯用模式、API 映射和项目结构,供 agent-dev-workshop Phase 5 代码生成使用。 每个框架 reference 文件标注 verified_date 用于版本锁定。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

hashgraph-online/awesome-codex-plugins1.4천2026년 10월 19일 업데이트

中文调试修复技能。用于报错、测试失败、页面异常、功能不符合预期、需要定位根因并做最小修复时。触发语包括"进入调试模式""帮我修问题""报错了""测试失败""页面坏了""找根因"。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

hashgraph-online/awesome-codex-plugins1.4천2026년 10월 19일 업데이트

交互式 AI Agent 开发工作坊:通过 6 阶段深度协作对话,引导用户完成 Agent 需求分析、架构设计、 工具定义、Prompt 与编排设计、代码生成、验证迭代,产出可直接运行的 Agent 项目。 框架无关设计优先,支持 LangChain / EINO / AutoGen / AgentScope / CrewAI 等 ADK 框架。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

hashgraph-online/awesome-codex-plugins1.4천2026년 10월 19일 업데이트

中文漂移审计技能。用于项目或学习过程变乱、上下文漂移、任务分叉、多个方案冲突、命名不一致、Codex 可能顺手改多了时。触发语包括"漂移检查""感觉跑偏了""项目变乱了""检查是否失控""分叉太多""上下文漂移"。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

hashgraph-online/awesome-codex-plugins1.4천2026년 10월 19일 업데이트

hashgraph-online의 스킬 모두 보기

이 스킬의 문제 신고