CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ce-plan

Create structured plans for multi-step work, including software and non-software tasks. Use when asked to plan, break down implementation, plan from requirements, or deepen an existing plan; prefer ce-brainstorm for exploratory framing.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An exemplary orchestration skill body: a lean overview that delegates detail to a well-organized one-level-deep reference bundle, with fully concrete routing rules, exact interaction phrasings, and explicit validation and recovery checkpoints throughout the phase workflow. The only weakness is density — the completion-contract and handoff sections compress many conditions into run-on sentences that could be tightened. Suggestions: none needed.

DimensionReasoningScore

Conciseness

The body is dense with operational rules and contains no explanations of concepts Claude already knows, but the "Mandatory Completion Contract" paragraph ("A run is complete when its output contract's done condition is met. Every normal interactive branch that produces a plan artifact or checkpoint is incomplete until...") and the Phase 5 STOP paragraph overlap and pack many nested conditions into long run-on sentences that could be trimmed. This fits 'efficient; minor instances of over-explanation that could be trimmed' rather than the fully lean 5 or the noticeably verbose 3.

4 / 5

Actionability

For an instruction-only orchestration skill the guidance is fully executable: exact phrasings to use ("ask exactly: 'Plan ready at `<absolute path to plan>`. What would you like to do next?'"), exact failure tokens ("Return the exact token `settled-decision-invalidated`"), exact blocked-state fields ("`status: blocked`, `phase`, `blocker`, and `recovery_path`"), and exact per-phase reference reads. Specific decision rules cover the common routing cases (Durable-regardless-of-size conditions, tier escalation), matching 'copy-paste ready... specific examples cover the common cases'.

5 / 5

Workflow Clarity

Phases 0-5 run in explicit order with checkpoints and error recovery: the resume check (Phase 0.1), source check (Phase 0.2), scoping synthesis, the Phase 5.1.5 confirmation before writing, the confidence path, and mandatory non-interactive document review. Failure handling is explicit ("If a required reference cannot be read, stop before the action it governs and report the blocker and recovery path"; "If the selection arrives after a user turn, reload `references/plan-handoff.md` before acting"), and completion criteria are precisely defined per output tier. This matches the 'clear sequence with explicit validation steps; feedback loops for error recovery' anchor.

5 / 5

Progressive Disclosure

The 60-line body is a pure overview that routes each phase to a named, existing bundle file read at the moment it is needed (output-mode.md, resume.md, intake.md, research.md, structure.md, plan-sections.md, final-review.md, reasoning-elevation.md, plan-handoff.md, output-contracts.md, all verified present in references/), with the bulk of detail correctly split into references/, references/agents/, and scripts/. References are one level deep, clearly signaled with when-to-read instructions, and navigation is easy, matching the 'clear overview with well-signaled one-level-deep references' anchor.

5 / 5

Total

19

/

20

Passed

Description

83%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.

A strong description that clearly and explicitly states both capability and trigger conditions, with a useful boundary pointer to a sibling skill. Keyword coverage is good though missing a few natural synonyms, and the enumerated actions are variants of one core capability rather than a comprehensive set. Suggestions: none needed.

DimensionReasoningScore

Specificity

"Create structured plans for multi-step work" plus "plan, break down implementation, plan from requirements, or deepen an existing plan" lists several distinct concrete actions with a stated domain ("software and non-software tasks"), matching the 'several specific actions; minor gaps' anchor. It falls short of 5 because the actions are all variants of 'plan' rather than a comprehensive set of distinct capabilities, and above 3 because more than 1-2 concrete actions are explicitly named.

4 / 5

Completeness

The 'what' is explicit ("Create structured plans for multi-step work, including software and non-software tasks") and the 'when' is explicit with concrete trigger phrases ("Use when asked to plan, break down implementation, plan from requirements, or deepen an existing plan"), directly matching the anchor for clearly answering both what AND when. Not below 5 because neither half is vague or merely implied.

5 / 5

Trigger Term Quality

"asked to plan, break down implementation, plan from requirements, or deepen an existing plan" covers the natural phrasings users would say for this skill ("plan", "break down", "requirements", "deepen"). A few natural synonyms are missing (e.g., 'roadmap', 'task breakdown', 'spec out'), which fits the 'good keyword coverage; a few natural terms missing' anchor rather than the comprehensive 5.

4 / 5

Distinctiveness Conflict Risk

"prefer ce-brainstorm for exploratory framing" explicitly delineates the nearest sibling skill, and the planning niche is distinct from execution, giving mostly-distinct triggers. It is not 5 because broad triggers like "asked to plan" still carry minor overlap risk with other related skills (e.g., execution/work skills) that are not addressed in the description itself.

4 / 5

Total

17

/

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

EveryInc/compound-engineering-plugin

Path

skills/ce-plan/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.