writing-plans

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

Quality

62%

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 ./eval/local/skills/benchmarks/dependency/superpowers/writing-plans/SKILL.md

The canonical home for this skill is writing-plans in obra/superpowers

Quality

Content

88%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 content is a strong, highly actionable instruction skill: complete templates, exact commands, an embedded TDD validation loop per task, and an explicit self-review checklist leave little ambiguity about what to produce. It is lean and self-contained, with only minor redundancy (the 'Remember' recap) keeping it from full marks on conciseness.

Dimension	Reasoning	Score
Conciseness	The body is terse and assumes competence ('DRY. YAGNI. TDD. Frequent commits.') with no explanations of concepts Claude already knows. Minor redundancy keeps it below lean-and-perfect: the 'Remember' section restates earlier rules ('Exact file paths always', 'DRY, YAGNI, TDD') and the granularity sections partially repeat what the Task Structure template already demonstrates.	4 / 5
Actionability	Fully executable, copy-paste-ready guidance throughout: a complete plan-document header template, a full task template with real code and exact commands ('pytest tests/path/test.py::test_name -v', expected FAIL/PASS output, git commit commands), an exact save path pattern, and a verbatim execution-handoff script.	5 / 5
Workflow Clarity	A clear end-to-end sequence (Scope Check → File Structure → Task Right-Sizing → write plan → Self-Review → Execution Handoff) with explicit validation checkpoints: every task embeds a TDD fail-then-pass loop ('Run test to verify it fails' / 'verify it passes'), and the Self-Review section is a three-item checklist (spec coverage, placeholder scan, type consistency) with a fix-and-move-on feedback loop.	5 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are all absent) and the skill is a single, well-sectioned document whose templates genuinely belong inline. Structure is good with clear headers and no buried references, but at ~175 lines — above the under-50-line simple-skill exception — it earns 'good structure; most content appropriately placed' rather than the top anchor.	4 / 5
	Total	18 / 20 Passed

Description

36%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 a pure trigger with no capability statement: it says clearly when to use the skill but never what the skill does (write implementation plans). Its trigger terms are natural but miss the 'plan/planning' vocabulary users would most likely use. Adding a what-clause and plan-related trigger terms would move it from poor to good.

Suggestions

Add a capability clause before the trigger, e.g. 'Writes comprehensive, bite-sized implementation plans with exact file paths, code, and TDD steps. Use when you have a spec or requirements for a multi-step task, before touching code.'

Include the skill's core noun family — 'plan', 'implementation plan', 'planning' — in the trigger so users asking to 'write a plan' or 'plan this feature' match naturally.

Sharpen distinctiveness by signaling that this skill is for producing the plan document itself (not for executing or reviewing plans), to avoid overlap with executing-plans and subagent-driven-development.

Dimension	Reasoning	Score
Specificity	The description names its domain ('spec or requirements for a multi-step task, before touching code') but states no capabilities at all — it never says the skill writes implementation plans, so it sits between the vague anchor 1 and the 1-2-concrete-actions anchor 3, matching 'actions are minimal or generic' at 2.	2 / 5
Completeness	Only the 'when' is present without any 'what': 'Use when you have a spec or requirements...' gives an explicit trigger but the description never states what the skill does. This matches the anchor-2 example 'Use when working with documents'; it cannot be a 3 because the 'what' is absent rather than weakly implied.	2 / 5
Trigger Term Quality	Natural terms like 'spec', 'requirements', and 'multi-step task' are present, but the skill's core noun — 'plan', 'implementation plan', 'planning' — is completely absent, which is exactly the phrase a user would say. This missing synonym family keeps it at 'some relevant keywords but missing common variations' rather than good coverage.	3 / 5
Distinctiveness Conflict Risk	'Spec or requirements for a multi-step task' is somewhat specific, but the skill's own body references sibling planning skills (superpowers:executing-plans, superpowers:subagent-driven-development) with which this trigger could overlap, plus brainstorming-type skills. It is not mostly-distinct enough for a 4.	3 / 5
	Total	10 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rpamis/comet
Path: eval/local/skills/benchmarks/dependency/superpowers/writing-plans/SKILL.md
Commit: 899d1fb

Reviewed: 7 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.