plan

Turn a sufficiently understood task into an ordered implementation plan with dependencies and verification. Orchestrate CodeWhale’s native plan state; do not build a parallel planner.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./crates/tui/assets/skills/plan/SKILL.md

Quality

Content

72%

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

The content is commendably concise and well-organized for a simple skill, but its workflow guidance is procedural and abstract, lacking a concrete example plan and explicit process validation. Adding an illustrative plan and a feedback loop would lift actionability and workflow clarity.

Suggestions

Include a short, concrete example of the expected output (e.g., a sample plan with Goal / ordered Steps / Verification markers / Risks) so the guidance is copy-paste ready rather than abstract.

Tighten step 3 by specifying what "risky step" means and how verification should be marked (e.g., a per-step "verify:" line with the check to run), and add a feedback loop for when a step's dependencies cannot be satisfied.

Clarify the authorization gate by stating what Claude should do while waiting (e.g., hold and surface open questions) so the checkpoint is explicit rather than implied.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no explanation of what planning is, no padding, every section (When to use, Non-goals, Workflow, Output shape) earns its place.	3 / 3
Actionability	The workflow gives a clear procedure but the steps are abstract ("Restate the goal and constraints," "List ordered steps with dependencies") with no concrete example plan and no specifics on how to mark verification or what counts as a risky step, so it is incomplete rather than fully actionable.	2 / 3
Workflow Clarity	A clear numbered sequence exists with a verification mention (step 3) and an authorization gate (step 5), but the checkpoints are implicit — step 3 marks verification in the output rather than validating the plan — and there is no error-recovery feedback loop (e.g., what to do if dependencies cannot be resolved).	2 / 3
Progressive Disclosure	Under 50 lines, single-purpose, with well-organized sections and no need for external references — meeting the rubric's allowance for simple skills to score 3 on progressive disclosure with just clear organization.	3 / 3
	Total	10 / 12 Passed

Description

60%

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 states concrete, distinctive actions but lacks an explicit "Use when..." trigger and broad natural keyword coverage, leaving completeness and trigger-term quality at the mid level. It is solid but would benefit from explicit usage triggers.

Suggestions

Add an explicit "Use when..." clause naming the situations that call for planning (e.g., multi-step tasks with dependencies, when the next edit is not obvious) to raise completeness to 3.

Broaden trigger terms to natural user phrasings like "plan the work," "break down the task," "implementation plan," "sequence the steps," so the skill surfaces for more query variations.

Sharpen distinctiveness by pairing "plan" with the native-state constraint up front (e.g., "Use CodeWhale's plan state rather than a separate planner") to reduce overlap with generic planning skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: "Turn a sufficiently understood task into an ordered implementation plan with dependencies and verification," "Orchestrate CodeWhale's native plan state," and "do not build a parallel planner" — specific rather than vague.	3 / 3
Completeness	The "what" is clearly stated, but the "when" is only implied ("sufficiently understood task") with no "Use when..." clause, which per the guidelines caps completeness at 2 rather than 3.	2 / 3
Trigger Term Quality	"plan" and "implementation plan" are natural terms, but coverage is thin: no common variations and no explicit trigger phrase, so it sits at the "some relevant keywords but missing variations" anchor rather than a 3.	2 / 3
Distinctiveness Conflict Risk	"Orchestrate CodeWhale's native plan state; do not build a parallel planner" gives it a niche, but "plan" is a generic concept that could overlap with other planning/breakdown skills, so it is not clearly conflict-free.	2 / 3
	Total	9 / 12 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Hmbown/CodeWhale
Path: crates/tui/assets/skills/plan/SKILL.md
Commit: bc17240

Reviewed: about 14 hours ago

Table of Contents

Discovery Implementation Validation

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.