writing-plans

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

3.58x

Quality

67%

Does it follow best practices?

Impact

86%

3.58x

Average score across 8 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/writing-plans/SKILL.md

Quality

Content

85%

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 strong, actionable planning template with explicit TDD validation checkpoints and concrete commands. Its only weakness is mild redundancy between the overview, the bite-sized list, and the expanded task template.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes Claude's competence, but the five micro-steps are listed twice (quick list in "Bite-Sized Task Granularity" then expanded in "Task Structure") and the "Remember" section repeats DRY/YAGNI/TDD already stated in the Overview.	2 / 3
Actionability	Guidance is fully concrete and copy-paste ready: exact file paths, exact commands (pytest ...::test_name -v), expected PASS/FAIL outcomes, and a complete git commit example.	3 / 3
Workflow Clarity	The TDD sequence (write failing test → verify fail → implement → verify pass → commit) is clearly ordered with explicit validation checkpoints and expected-output feedback at each step.	3 / 3
Progressive Disclosure	The skill is self-contained with well-organized sections and no nested references; sub-skills are signaled one level deep via the superpowers:executing-plans @ syntax, which is appropriate navigation.	3 / 3
	Total	11 / 12 Passed

Description

50%

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 has a strong, explicit trigger clause but never states what the skill actually does, relying on the name to carry the capability. It is concrete enough to avoid vagueness but not comprehensive enough to score top marks.

Suggestions

Lead with the action, e.g. "Writes bite-sized, TDD-based implementation plans from a spec or requirements" before the Use-when clause.

Add natural trigger variations such as "plan", "implementation plan", or "before coding" alongside "spec" and "requirements".

State the output explicitly (e.g. "saves a plan to docs/plans/") so the what is unambiguous from the description alone.

Dimension	Reasoning	Score
Specificity	"spec or requirements for a multi-step task, before touching code" names a concrete scenario but states no actions the skill performs; the what is only implied by the skill name rather than by the description text itself.	2 / 3
Completeness	The explicit "Use when..." clause answers when clearly, but the description never states what the skill does (no verb like "Writes" or "Generates"), so what is only implied.	2 / 3
Trigger Term Quality	"spec", "requirements", and "multi-step task" are terms a user might naturally say, but common variations like "plan", "implementation plan", or "before coding" are missing.	2 / 3
Distinctiveness Conflict Risk	The "spec or requirements... before touching code" framing carves a planning niche distinct from execution skills, but it could still overlap with adjacent brainstorming or executing-plans skills.	2 / 3
	Total	8 / 12 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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/writing-plans/SKILL.md
Commit: f627ab5

Reviewed: about 10 hours 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.