plan-writing

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

Quality

51%

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 ./skills/plan-writing/SKILL.md

Quality

Content

50%Scale 1-5

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

This skill provides a reasonable framework for task planning with good use of comparison tables and a flexible template. Its main weaknesses are: references to scripts that aren't linked or documented, some repetitive emphasis on avoiding templates, and lack of explicit validation/feedback steps in the planning workflow itself. The content is moderately actionable but leans more toward philosophy than executable guidance.

Suggestions

Either link to or document the referenced scripts (ux_audit.py, api_validator.py, etc.) with paths and usage examples, or remove the references entirely since they create dead ends.

Add an explicit validation step to the workflow, e.g., 'After drafting the plan, verify: each task has a concrete verb, a specific file/command, and a verification criterion.'

Consolidate the five principles into a more compact format—the wrong/right tables are effective but could be combined into a single reference table to reduce repetition and length.

Consider splitting the project-type-specific guidance (new project vs feature vs bug fix) into a separate reference file to keep the main skill focused on the core planning workflow.

Dimension	Reasoning	Score
Conciseness	The skill has some unnecessary verbosity—tables contrasting wrong vs right are helpful but repeated across five principles, and some points are belabored (e.g., the 'NO fixed templates' warning repeated in different forms). The content could be tightened by ~30% without losing clarity. However, it doesn't explain concepts Claude already knows extensively.	3 / 5
Actionability	The skill provides concrete examples of good vs bad task descriptions and a flexible plan template, but the guidance is more about how to write plans than executable steps. The script references (ux_audit.py, api_validator.py, etc.) are mentioned without paths or usage instructions, and the plan template is illustrative rather than fully actionable. It's a mix of concrete examples and vague references.	3 / 5
Workflow Clarity	There's a logical flow from principles to structure to best practices, and the plan template shows a clear sequence. However, the actual workflow of creating a plan lacks explicit validation steps—there's no checkpoint like 'review the plan for completeness before starting execution' or feedback loop for plan revision. The 'Update as you go' note is implicit rather than a structured verification step.	3 / 5
Progressive Disclosure	The content is reasonably structured with headers and sections, but everything is inlined in a single file with no references to supporting documents. The script references (ux_audit.py, accessibility_checker.py, etc.) are mentioned but never linked or explained where they live. For a skill of this length (~100 lines of substantive content), some separation or at least clear references would improve navigation.	3 / 5
	Total	12 / 20 Passed

Description

53%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 communicates the general purpose of the skill (structured task planning) and includes a 'Use when' clause, which is good. However, it lacks concrete action verbs describing what the skill actually does, relies on somewhat abstract terminology, and the trigger scope is overly broad ('any multi-step work'), which increases conflict risk with other skills.

Suggestions

Add concrete action verbs describing what the skill produces, e.g., 'Creates numbered task lists with dependencies, identifies blockers, and defines verification criteria for each step.'

Narrow the 'Use when' clause or add more specific trigger terms like 'break down,' 'plan,' 'step by step,' 'checklist,' 'task list,' 'decompose' to improve trigger term quality and reduce conflict risk.

Replace the catch-all 'any multi-step work' with more specific scenarios to reduce overlap with other skills, e.g., 'Use when the user asks to break down a feature, plan a refactor, or create a step-by-step implementation plan.'

Dimension	Reasoning	Score
Specificity	Names the domain (task planning) and mentions a few abstract concepts like 'breakdowns, dependencies, and verification criteria,' but these are more like attributes of a plan than concrete actions. No specific actions like 'creates task lists,' 'identifies blockers,' or 'generates dependency graphs' are mentioned.	2 / 5
Completeness	Has both 'what' (structured task planning with breakdowns, dependencies, verification criteria) and 'when' ('Use when implementing features, refactoring, or any multi-step work'). The 'when' clause is present and reasonably explicit, though 'any multi-step work' is quite broad and could be more specific.	4 / 5
Trigger Term Quality	Includes some relevant terms like 'task planning,' 'implementing features,' 'refactoring,' and 'multi-step work,' but misses natural user phrases like 'break this down,' 'plan this out,' 'step by step,' 'todo list,' 'checklist,' or 'project plan.'	3 / 5
Distinctiveness Conflict Risk	The description is somewhat specific to planning/breakdown but 'implementing features, refactoring, or any multi-step work' is extremely broad and could overlap with many coding, project management, or workflow skills. The phrase 'any multi-step work' especially increases conflict risk.	3 / 5
	Total	12 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/plan-writing/SKILL.md
Commit: 57c135b

Reviewed: 3 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.