writing-plans

Use when you have a spec or requirements for a multi-step task, before touching code

Quality

52%

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/writing-plans/SKILL.md

Quality

Content

77%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 is a strong, actionable skill that provides a clear TDD-based planning workflow with excellent validation checkpoints and concrete templates. Its main weaknesses are minor verbosity (repeated principles, some unnecessary philosophical framing) and lack of bundle files to support the referenced sub-skills and templates. The task structure template is exemplary in its specificity and executability.

Suggestions

Remove the duplicate mention of 'DRY, YAGNI, TDD, frequent commits' — it appears in both the Overview and Remember sections.

Trim the Overview's characterizations ('questionable taste', 'know almost nothing') to focus on the actionable implication: document everything explicitly with full file paths and code.

Consider extracting the plan header template and task structure template into bundle files (e.g., templates/plan-header.md, templates/task-template.md) to improve progressive disclosure and reduce SKILL.md length.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient but includes some unnecessary padding. The 'Overview' section over-explains the philosophy ('questionable taste', 'assume they don't know good test design') and the 'Remember' section partially repeats guidance already embedded in the task structure template. The acronym list (DRY, YAGNI, TDD) appears twice.	3 / 5
Actionability	Highly actionable with concrete, copy-paste-ready templates for plan headers, task structures, exact pytest commands with expected outputs, git commit commands, and file path conventions. The task structure template is fully executable and covers the complete TDD cycle with specific code examples.	5 / 5
Workflow Clarity	The workflow is clearly sequenced: write failing test → verify failure → implement → verify pass → commit. Each step includes explicit validation checkpoints with expected outcomes (e.g., 'Expected: FAIL with "function not defined"'). The execution handoff provides clear branching paths with required sub-skills. The feedback loop of test-verify-implement-verify is well-defined.	5 / 5
Progressive Disclosure	The skill references other skills (superpowers:executing-plans, superpowers:subagent-driven-development, brainstorming skill) but no bundle files are provided to support these references. The content is moderately well-structured with clear sections, but the plan template and task structure template are inlined rather than being in a separate template file, which would be cleaner for a skill of this length. References to external skills use '@ syntax' but don't provide navigable links.	3 / 5
	Total	16 / 20 Passed

Description

27%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.

This description is severely lacking in specificity and completeness. It only provides a 'when' trigger without explaining what the skill actually does, making it nearly impossible for Claude to confidently select it over other planning or pre-coding skills. The trigger terms are somewhat relevant but too generic to reliably distinguish this skill from others.

Suggestions

Add a clear 'what' clause describing the concrete actions this skill performs (e.g., 'Creates an implementation plan by breaking down specs into ordered subtasks with dependencies')

Include more natural trigger terms and synonyms users might say, such as 'plan', 'breakdown', 'implementation steps', 'architecture', 'design doc'

Make the description more distinctive by specifying the output format or unique approach (e.g., 'Generates a numbered task list with file-level changes before writing any code')

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. It doesn't say what the skill does—only when to use it. There are no verbs describing capabilities like 'generates', 'plans', 'breaks down', etc.	1 / 5
Completeness	Has only a 'when' clause with no 'what' component. The description tells Claude when to use the skill but never explains what the skill actually does. Per the rubric, a missing 'what' caps this at 2.	2 / 5
Trigger Term Quality	Contains some relevant terms like 'spec', 'requirements', and 'multi-step task' that users might naturally say, but misses common synonyms like 'plan', 'design', 'architecture', 'breakdown', 'implementation plan', or 'before coding'.	3 / 5
Distinctiveness Conflict Risk	Very broad and vague—'multi-step task' and 'before touching code' could apply to many planning, architecture, or task-decomposition skills. Without specifying what it produces or how it works, it has high overlap risk.	2 / 5
	Total	8 / 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/writing-plans/SKILL.md
Commit: 900c504

Reviewed: 23 minutes 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.