plan-writing

Structured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work.

Quality

63%

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 ./.agents/skills/plan-writing/SKILL.md

Quality

Content

67%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.

The body is a well-organized, actionable planning guide with concrete examples and strong verification emphasis, weakened mainly by redundant restatement of the same principles across three sections.

Suggestions

Collapse 'Task Breakdown Principles', 'Planning Principles', and 'Best Practices Quick Reference' into a single section to remove redundant tokens.

Add an explicit feedback loop for plan execution (e.g., if a task fails verification, fix and re-verify before proceeding) to strengthen workflow clarity.

Tighten the 'Dynamic Naming' and scripts sections, which currently repeat warnings that could be stated once.

Dimension	Reasoning	Score
Conciseness	Per-section content is tight and uses compact wrong/right tables, but the same guidance is restated across 'Task Breakdown Principles', 'Planning Principles', and 'Best Practices Quick Reference', adding redundant tokens Claude doesn't need, fitting the 3-anchor.	3 / 5
Actionability	Concrete examples with real commands ('npx create-next-app', 'npm run dev', curl returning 200) and a copy-paste plan template give mostly executable guidance, with only minor gaps keeping it below 5.	4 / 5
Workflow Clarity	The plan structure (Goal -> Tasks with per-task 'Verify:' -> Done When) is a clear sequence with verification checkpoints emphasized ('Verification is always LAST'), but there is no explicit feedback loop for the plan-writing process itself, so 4 not 5.	4 / 5
Progressive Disclosure	No bundle files exist and the document is a single well-sectioned guide with clear headers and no nested references; minor organization gaps from cross-section redundancy keep it at 4 rather than 5.	4 / 5
	Total	15 / 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 states both purpose and trigger conditions in third person, but its triggers lean generic ('multi-step work') and its capabilities are stated abstractly rather than as a comprehensive concrete action list.

Suggestions

Replace the generic trigger 'any multi-step work' with more specific natural phrases like 'breaking down features into tasks' or 'defining task dependencies'.

Expand capabilities from abstract nouns to concrete actions, e.g. 'Breaks work into 2-5 minute tasks, maps dependencies, and defines per-task verification criteria'.

Add a few synonyms users actually say (planning, task breakdown, roadmap) to improve trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Structured task planning') plus three concrete elements ('clear breakdowns, dependencies, and verification criteria'), but these remain somewhat abstract and not a comprehensive list of concrete actions, fitting the 3-anchor rather than 4.	3 / 5
Completeness	Explicitly answers both what ('Structured task planning with clear breakdowns, dependencies, and verification criteria') and when ('Use when implementing features, refactoring, or any multi-step work'); the when is concrete but could be more specific, so 4 rather than 5.	4 / 5
Trigger Term Quality	'implementing features, refactoring, or any multi-step work' provides relevant natural keywords, but 'multi-step work' is generic and common synonyms (e.g., 'planning', 'task breakdown', 'roadmap') are missing, matching the 3-anchor.	3 / 5
Distinctiveness Conflict Risk	'Structured task planning' is a recognizable niche, but the broad trigger 'any multi-step work' creates real overlap risk with general coding/task skills, landing at the 3-anchor.	3 / 5
	Total	13 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: vudovn/ag-kit
Path: .agents/skills/plan-writing/SKILL.md
Commit: 211561c

Reviewed: 8 days 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.