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

72%

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

86%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 lean, well-structured instruction skill: concise, clearly sequenced, with verification and authorization checkpoints and a tidy output shape. It is already near ceiling; the only gap is the absence of an explicit error-recovery feedback loop in the workflow.

Dimension	Reasoning	Score
Conciseness	The body is lean (~20 lines) with every line earning its place — it restates the goal, sequences steps, and defines an output shape without explaining concepts Claude already knows. Not below 5 because there is no padding or over-explanation to trim.	5 / 5
Actionability	Each workflow step is a concrete, actionable instruction ('List ordered steps with dependencies', 'Mark verification for each risky step', 'Write the plan into CodeWhale's native plan/Work surface') with a concrete output shape. Not a 5 because, being instruction-only, it stops short of fully copy-paste-ready specifics for how to write into the plan surface.	4 / 5
Workflow Clarity	A clearly numbered 1–5 sequence with explicit checkpoints ('Mark verification for each risky step' and 'Wait for authorization before broad implementation'). Not a 5 because there is no explicit validate→fix→retry feedback loop for error recovery, though planning is not a destructive/batch operation so the 3-cap does not apply.	4 / 5
Progressive Disclosure	Under 50 lines with well-organized sections (When to use, Non-goals, Workflow, Output shape) and no need for external references, which scores 5 per the rubric's simple-skill guidance. No bundle files exist to verify, and none are needed.	5 / 5
	Total	18 / 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 is concrete and distinct, with a clear 'what' and a useful anti-conflict guard, but it lacks an explicit 'Use when' trigger clause and natural trigger synonyms a user would actually say. Adding a 'Use when...' sentence with common phrasings would lift completeness and trigger_term_quality.

Suggestions

Append an explicit 'Use when...' clause with natural user phrasings, e.g. 'Use when the user asks to plan or sequence implementation work, break a task into ordered steps, or lay out a build plan with dependencies.'

Add common synonyms a user would say ('plan the work', 'break down the task', 'sequence the implementation') to broaden trigger_term_quality beyond the single 'implementation plan' phrasing.

Optionally name one or two more concrete plan outputs (e.g. 'verification checklist', 'dependency graph') to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — 'ordered implementation plan with dependencies and verification', 'orchestrate CodeWhale's native plan state', 'do not build a parallel planner' — rather than vague language. It is not a 5 because coverage is narrow (a few actions) rather than comprehensive.	4 / 5
Completeness	It clearly states what the skill does (turn a task into an ordered plan), but provides no explicit 'when should Claude use it' trigger guidance in the description itself, which caps completeness at 3 per the rubric guideline. Not a 2 because the 'what' is clear, not a 4 because 'when' is entirely absent.	3 / 5
Trigger Term Quality	Relevant keywords like 'implementation plan', 'dependencies', and 'verification' appear, but common natural variations or synonyms a user would say (e.g. 'plan the work', 'break down the task') and a 'Use when' trigger phrase are missing. Not a 4 because keyword coverage is thin rather than merely a few terms short.	3 / 5
Distinctiveness Conflict Risk	The CodeWhale plan-state framing and the explicit 'do not build a parallel planner' carve-out give it a clear niche with minor overlap risk. Not a 5 because 'plan' as a verb is still broadly generic and could overlap with adjacent planning-style skills.	4 / 5
	Total	14 / 20 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: 8ae401b

Reviewed: 1 day 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.