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

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, token-efficient orchestrator document: concrete commands and artifacts, an explicitly sequenced workflow with user checkpoints and a resume path, and clean delegation to per-stage sub-skills. The only weaknesses are mild redundancy in representing the stage order and a few unspecified details (checkpoint rejection handling, quality-gate criteria).

DimensionReasoningScore

Conciseness

The body is lean and table-driven with no explanation of concepts Claude already knows; the only trimmable redundancy is that stage ordering appears three times (Stages table, Workflow list, Dependency graph). Fits anchor 4 (efficient, minor instances that could be trimmed) rather than 5's 'every token earns its place'.

4 / 5

Actionability

Concrete, executable guidance throughout: usage commands ("/plan-pipeline --from=start"), output paths ("docs/plans/plan-{name}.md", "docs/adr/"), and per-stage delegation with explicit resume instructions. Not 5 due to small gaps — e.g., how {name} is chosen and what the quality gate checks are unspecified.

4 / 5

Workflow Clarity

An 8-step numbered workflow with two explicit "CHECKPOINT: ask user to confirm" gates, validation ordered before execute, and an interruption-resume path ("resume with --from=<stage>"). Not 5 because validation detail is delegated to the sub-skill and behavior when a checkpoint is rejected is unspecified.

4 / 5

Progressive Disclosure

No bundle files exist and none are needed; sections are clear and content is appropriately delegated to the sub-skills. It slightly exceeds the under-50-line simple-skill exception and the stage sequence is represented redundantly (table + workflow + dependency graph), fitting anchor 4's 'minor organization gaps' better than 5.

4 / 5

Total

16

/

20

Passed

Description

58%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description clearly communicates a multi-stage planning pipeline with concrete stage names and both individual and full-flow usage, but it omits any 'when to use' trigger guidance and leans on internal stage terminology rather than natural user phrases. It sits solidly at the midpoint-plus of the rubric.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to plan and build a non-trivial feature end-to-end, or to run/validate/execute an existing plan."

Include natural synonyms users would actually say — "feature planning", "PRD", "implementation plan", "break work into tasks" — alongside the stage names.

State the concrete artifacts produced (plan doc in docs/plans/, ADRs, PR) to sharpen the 'what' and improve specificity.

DimensionReasoningScore

Specificity

Quotes: "Orchestrates the complete planning pipeline: product direction (ceo-review) -> architecture (eng-review) -> implementation plan (start) -> validation (validate) -> execution (execute)" — several concrete, named stages/actions. Not 5 because it never states concrete outputs (plan doc, ADRs, PR); clearly above 3's '1-2 concrete actions'.

4 / 5

Completeness

The 'what' is clear ("Run stages individually or let the orchestrator coordinate the full flow"), but there is no 'Use when...' clause or equivalent trigger guidance — the rubric explicitly caps completeness at 3 for this. Not 2 because the 'what' is specific, not vague.

3 / 5

Trigger Term Quality

Keywords like "planning pipeline", "architecture", "implementation plan", "validation" are relevant, but they are mostly the skill's own stage names; common user phrasings ("plan this feature", "PRD", "spec", "task breakdown") are missing. Fits anchor 3 (some relevant keywords, missing variations) better than 4.

3 / 5

Distinctiveness Conflict Risk

"Orchestrates the complete planning pipeline" with five named sub-stages carves a distinct orchestration niche with minor overlap risk against generic planning skills. Not 5 because "planning" broadly could collide with general planning skills lacking the pipeline framing.

4 / 5

Total

14

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

FlorianBruniaux/claude-code-ultimate-guide

Path

examples/skills/plan-pipeline/SKILL.md

Reviewed

Table of Contents

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.