plan-pipeline

GitHub

编排从产品方向到执行的全流程规划流水线,包含CEO审查、架构评审、计划制定、验证及执行五个阶段,支持单阶段运行或全流程协调。

examples/skills/plan-pipeline/SKILL.md FlorianBruniaux/claude-code-ultimate-guide

Trigger Scenarios

需要规划新功能或复杂任务 协调多阶段开发流程 进行产品方向或架构决策

Install

npx skills add FlorianBruniaux/claude-code-ultimate-guide --skill plan-pipeline -g -y
More Options

Non-standard path

npx skills add https://github.com/FlorianBruniaux/claude-code-ultimate-guide/tree/main/examples/skills/plan-pipeline -g -y

Use without installing

npx skills use FlorianBruniaux/claude-code-ultimate-guide@plan-pipeline

指定 Agent (Claude Code)

npx skills add FlorianBruniaux/claude-code-ultimate-guide --skill plan-pipeline -a claude-code -g -y

安装 repo 全部 skill

npx skills add FlorianBruniaux/claude-code-ultimate-guide --all -g -y

预览 repo 内 skill

npx skills add FlorianBruniaux/claude-code-ultimate-guide --list

SKILL.md

Frontmatter
{
    "name": "plan-pipeline",
    "effort": "high",
    "description": "Orchestrates the complete planning pipeline: product direction (ceo-review) -> architecture (eng-review) -> implementation plan (start) -> validation (validate) -> execution (execute). Run stages individually or let the orchestrator coordinate the full flow.",
    "allowed-tools": "Read Write Bash Task"
}

Plan Pipeline Orchestrator

Orchestrates the complete plan-to-execution pipeline. Can run the full pipeline or a single isolated stage.

Stages

Stage Skill Purpose
1 /plan-pipeline:ceo-review Challenge the brief, lock product direction
2 /plan-pipeline:eng-review Lock architecture, diagrams, and test matrix
3 /plan-pipeline:start 5-phase planning: PRD, research, ADRs, task list
4 /plan-pipeline:validate 2-layer validation before any code is written
5 /plan-pipeline:execute Worktree isolation, parallel agents, quality gate, PR

Usage

/plan-pipeline                     # full pipeline, asks for context
/plan-pipeline --from=start        # skip gates, start from planning phase
/plan-pipeline --from=validate     # validate an existing plan
/plan-pipeline --from=execute      # execute a validated plan

When to Use Each Stage

ceo-review: use before any significant feature when the direction is not locked. Especially valuable when the request is specific (specificity signals collapsed solution space).

eng-review: use after direction is locked. Required for features with async components, external dependencies, or multi-step flows.

start: use for any non-trivial feature touching more than 2 files or involving architecture decisions.

validate: always before execute. The cost of validation is negligible against the cost of discovering issues mid-execution.

execute: after validate confirms all issues are resolved.

Workflow

  1. Collect context: what are we building, and what stage do we start from?
  2. ceo-review: product direction gate (can be skipped with --from=eng-review or later)
  3. eng-review: architecture gate (can be skipped with --from=start or later)
  4. CHECKPOINT: ask user to confirm direction and architecture before planning
  5. start: run 5-phase planning, produce docs/plans/plan-{name}.md
  6. CHECKPOINT: present plan for review before validation
  7. validate: 2-layer validation (structural + specialist agents)
  8. execute: worktree isolation -> parallel agents -> quality gate -> PR

Dependency Graph

   ceo-review
        |
   eng-review
        |
      start
        |
    validate
        |
    execute

Notes

Each stage writes its output to disk before the next stage begins. If the pipeline is interrupted, resume with --from=<stage> using the correct stage name. All decisions are recorded in docs/plans/plan-{name}.md and the corresponding ADRs in docs/adr/.

Version History

  • fa57065 Current 2026-07-25 10:19

Same Skill Collection

.agents/skills/guide-recap/SKILL.md
.agents/skills/self-assessment/SKILL.md
.agents/skills/source-command-audit-prose/SKILL.md
.agents/skills/source-command-audit-whitepapers/SKILL.md
.agents/skills/source-command-ccguide-daily/SKILL.md
.agents/skills/source-command-ccguide-diff-docs/SKILL.md
.agents/skills/source-command-ccguide-init-docs/SKILL.md
.agents/skills/source-command-ccguide-refresh-docs/SKILL.md
.agents/skills/source-command-methodology-advisor/SKILL.md
.agents/skills/source-command-track-mentions/SKILL.md
.agents/skills/source-command-update-infos-release/SKILL.md
.claude/skills/self-assessment/SKILL.md
examples/skills/audit-agents-skills/SKILL.md
examples/skills/audit-codebase/SKILL.md
examples/skills/autoresearch/SKILL.md
examples/skills/canary/SKILL.md
examples/skills/catchup/SKILL.md
examples/skills/ccboard/SKILL.md
examples/skills/check-cache-bugs/SKILL.md
examples/skills/ci-all/SKILL.md
examples/skills/ci-pipeline/SKILL.md
examples/skills/ci-status/SKILL.md
examples/skills/ci-tests/SKILL.md
examples/skills/commit/SKILL.md
examples/skills/cyber-defense-team/SKILL.md
examples/skills/design-patterns/SKILL.md
examples/skills/diagnose/SKILL.md
examples/skills/eval-agents/SKILL.md
examples/skills/eval-hooks/SKILL.md
examples/skills/eval-rules/SKILL.md
examples/skills/eval-skills/SKILL.md
examples/skills/explain/SKILL.md
examples/skills/git-ai-archaeology/SKILL.md
examples/skills/git-worktree-clean/SKILL.md
examples/skills/git-worktree-remove/SKILL.md
examples/skills/git-worktree-status/SKILL.md
examples/skills/git-worktree/SKILL.md
examples/skills/guide-recap/SKILL.md
examples/skills/handoff-create/SKILL.md
examples/skills/handoff-resume/SKILL.md
examples/skills/handoff-update/SKILL.md
examples/skills/investigate/SKILL.md
examples/skills/issue-triage/SKILL.md
examples/skills/land-and-deploy/SKILL.md
examples/skills/landing-page-generator/SKILL.md
examples/skills/learn-alternatives/SKILL.md
examples/skills/learn-quiz/SKILL.md
examples/skills/learn-teach/SKILL.md
examples/skills/mcp-integration-reference/SKILL.md
examples/skills/methodology-advisor/SKILL.md

Metadata

Files
0
Version
a8d88fe
Hash
b6e720c7
Indexed
2026-07-25 10:19

Главная - Вики-сайт
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-22 05:38
浙ICP备14020137号-1 $Гость$