CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

plan-pipeline

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.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./examples/skills/plan-pipeline/SKILL.md
SKILL.md
Quality
Evals
Security

Plan pipeline orchestrator

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

Stages

StageSkillPurpose
1/plan-pipeline:ceo-reviewChallenge the brief, lock product direction
2/plan-pipeline:eng-reviewLock architecture, diagrams, and test matrix
3/plan-pipeline:start5-phase planning: PRD, research, ADRs, task list
4/plan-pipeline:validate2-layer validation before any code is written
5/plan-pipeline:executeWorktree 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/.

Repository

FlorianBruniaux/claude-code-ultimate-guide

Path

examples/skills/plan-pipeline/SKILL.md

Last updated
First committed

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.