Name: plan-writing
Rating: 56.00000000000001 (1 reviews)
Author: administrakt0r

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/plan-writing/SKILL.md

The canonical home for this skill is plan-writing in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

56%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 actionable and gives a clear, verification-centric plan template, but it suffers from heavy cross-section redundancy and cites project-specific scripts that are not actually bundled, which weakens both conciseness and navigation.

Suggestions

Collapse 'Task Breakdown Principles', 'Planning Principles', 'Best Practices', and 'When to Use' into a single principles section to eliminate the repeated verification and brevity guidance.

Either ship the referenced audit/validator scripts in a scripts/ directory or remove the Principle 4 table that lists them as available per-project-type tools.

Fix the unterminated code fence around the 'Plan Structure' / 'Notes' block (line 135 closes a fence that has no matching opener) so the template renders correctly.

Dimension	Reasoning	Score
Conciseness	The same principles are restated across 'Task Breakdown Principles', 'Planning Principles', 'Best Practices', and 'When to Use' (e.g. verification and 'keep it short' appear 3-4 times), making it noticeably padded despite accurate content — fitting the 2 anchor over 3.	2 / 5
Actionability	Concrete ❌/✅ tables and specific commands ('npx create-next-app', 'npm run dev', 'curl localhost:3000/api/users') give mostly executable guidance with minor gaps; appropriate for an instruction-only meta-skill per the code-vs-instruction note.	4 / 5
Workflow Clarity	The 'Plan Structure' template sequences Goal → Tasks (each with a Verify) → Done When, and 'Verification is always LAST' gives explicit checkpoints; minor gaps (no error-recovery loop) keep it at 4 rather than 5.	4 / 5
Progressive Disclosure	Sections are well-organized with clear headers, but Principle 4 names six scripts (ux_audit.py, api_validator.py, security_scan.py, mobile_audit.py, schema_validator.py, accessibility_checker.py) that do not exist in any bundle directory — broken references that undercut navigation, fitting the 3 anchor.	3 / 5
	Total	13 / 20 Passed

Description

71%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 cleanly states both capability and trigger and uses natural terms, but the 'when' clause is overly broad — 'any multi-step work' would fire on almost every engineering request, blurring its niche against the skills it coordinates.

Suggestions

Tighten the trigger to planning-specific phrasing, e.g. 'Use when work is complex enough to need an explicit written plan before implementation' rather than 'any multi-step work'.

Make capabilities more concrete by swapping abstract nouns for actions, e.g. 'Breaks work into 5-10 verifiable tasks, identifies dependencies, and defines done-criteria'.

Add a boundary cue that distinguishes planning from execution, e.g. 'Produces a plan file; does not itself write the implementation code'.

Dimension	Reasoning	Score
Specificity	Quotes 'clear breakdowns, dependencies, and verification criteria' — names the planning domain with 2-3 capability nouns, but these are abstract categories rather than the concrete actions (e.g. 'extract text', 'fill forms') that anchor a 4.	3 / 5
Completeness	Explicitly answers what ('Structured task planning with clear breakdowns, dependencies, and verification criteria') and when ('Use when implementing features, refactoring, or any multi-step work') with concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	'implementing features, refactoring, or any multi-step work' are natural phrases users say; coverage is good though a few synonyms (e.g. 'plan this work', 'break this down') are missing, fitting the 4 anchor.	4 / 5
Distinctiveness Conflict Risk	The trigger 'any multi-step work' is extremely broad — nearly every coding request qualifies — creating high overlap risk with the very implementation skills this plans around, fitting the 2 ('very broad; high overlap risk') better than 3.	2 / 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/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.