CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

writing-plans

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

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

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

SKILL.md
Quality
Evals
Security

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 body is an exemplary instruction-only skill: verbatim templates, exact commands with expected outputs, a concrete self-review checklist with feedback loops, and explicit anti-placeholder rules, all delivered tersely. The only weaknesses are a small amount of recap redundancy and the absence of any progressive-disclosure structure in a 145-line single file.

DimensionReasoningScore

Conciseness

The body is lean and directive — no basic-concept explanations (TDD, commits, and file granularity are stated as rules, not taught), and every section issues instructions. It falls short of 5 only through minor redundancy: the 'Remember' section recapitulates the Overview and 'No Placeholders' sections, and 'Bite-Sized Task Granularity' partially repeats the Task Structure template it precedes.

4 / 5

Actionability

Fully concrete guidance throughout: a verbatim plan-header template, a complete task template with exact pytest commands and expected FAIL/PASS output, exact git add/commit commands, an exact save path pattern ('docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md'), an explicit forbidden-placeholder list, and a word-for-word execution-handoff script. As an instruction-only skill this is copy-paste actionable with no material gaps.

5 / 5

Workflow Clarity

The process is clearly sequenced with temporal markers ('Before defining tasks...', 'After writing the complete plan...', 'After saving the plan...') running announce → scope check → file structure → tasks → self-review → save → handoff. Validation is explicit: a three-item self-review checklist (spec coverage, placeholder scan, type consistency) with fix-forward feedback loops ('If you find a spec requirement with no task, add the task'), plus verify-fail/verify-pass checkpoints embedded in the task template itself. Not a destructive/batch skill, so no validation cap applies.

5 / 5

Progressive Disclosure

A single-file skill (no references/, scripts/, or assets/ exist) with clean, well-labeled sections and nothing buried. It exceeds the under-50-line simple-skill threshold (~145 lines) and keeps everything inline with no overview-to-details split, so it does not earn the top anchor; not lower than 4 because nothing here obviously belongs in a separate file and navigation is unambiguous.

4 / 5

Total

18

/

20

Passed

Description

40%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 clause: it pins the 'when' (spec or requirements, multi-step task, before touching code) reasonably well but never states what the skill does, which caps completeness and specificity. It also skips the skill's most natural keyword ('plan') and uses second-person voice.

Suggestions

Add a 'what' statement, e.g. 'Writes comprehensive implementation plans that decompose a spec into bite-sized TDD tasks with exact file paths, complete code, and commit steps.'

Include the core natural trigger terms 'plan', 'implementation plan', and 'planning' — a user asking to 'write an implementation plan' currently matches nothing in the description.

Rephrase to third person or a gerund ('Use when starting a multi-step task from a spec' or 'Use when the user has a spec...') to avoid the second-person 'you have'.

DimensionReasoningScore

Specificity

The description names the domain with concrete nouns ("a spec or requirements for a multi-step task, before touching code") but states zero actions the skill performs — there is no capability verb at all. The second-person phrasing ("you have") also violates the third-person voice guideline, but the score already sits at the anchor-2 floor since no capability actions are named.

2 / 5

Completeness

Only a 'when' is present ("Use when you have a spec or requirements...") with no 'what' — the description never says the skill writes implementation plans. This exactly matches anchor 2 ('only when is present without what'); anchor 3 requires a clear 'what', and per the guidelines we cannot infer the capability from the skill name or body.

2 / 5

Trigger Term Quality

"spec", "requirements", "multi-step task", and "before touching code" are terms users would plausibly say, but the description omits the skill's own core natural terms — "plan", "implementation plan", "planning", "task breakdown". Missing the central synonym for a writing-plans skill is more than the 'a few natural terms missing' of level 4.

3 / 5

Distinctiveness Conflict Risk

The trigger carves a distinct pre-implementation niche (spec in hand, before touching code), which mostly distinguishes it from adjacent brainstorming/execution skills. It falls short of 5 because without a stated 'what', edge cases like a user asking to review or refine a spec could mis-trigger it.

4 / 5

Total

11

/

20

Passed

Validation

100%

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

valeriibeck-star/claude-skills

Path

skills/writing-plans/SKILL.md

Reviewed

Table of Contents

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.