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

68%

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 ./src-tauri/experts/skills/writing-plans/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 a strong, self-contained instruction skill: concrete templates with exact commands and expected outputs, an embedded verification checklist, and a clear handoff sequence. The only weaknesses are minor — a few trimmable rationale sentences and schematic rather than fully worked example code.

DimensionReasoningScore

Conciseness

The body is efficient — templates, checklists, and exact paths with no tutorials on concepts Claude already knows. A few rationale sentences ("You reason best about code you can hold in context at once, and your edits are more reliable when files are focused") could be trimmed, so anchor 4 (minor instances of over-explanation) rather than 5.

4 / 5

Actionability

Highly concrete: an exact save path, a full plan-header template, a complete task-structure template with code blocks and exact commands with expected output ("Run: pytest tests/path/test.py::test_name -v / Expected: FAIL with 'function not defined'"), and an explicit placeholder blacklist. Not 5 because the example code is schematic (function(input)/return expected) and only one generic task shape is shown — minor gaps versus covering common cases.

4 / 5

Workflow Clarity

The skill is clearly sequenced (scope check → file structure → task granularity → templates → self-review → execution handoff) with an explicit validation checklist (spec coverage, placeholder scan, type consistency) and a feedback loop ("If you find issues, fix them inline... If you find a spec requirement with no task, add the task"). The task template itself embeds fail/pass verification steps, matching anchor 5's checklists and feedback loops.

5 / 5

Progressive Disclosure

The skill is self-contained with no bundle files: well-organized sections, easy navigation, nothing buried, and no content that warrants splitting out (the templates are the core payload). This fits anchor 5's "content appropriately split; easy navigation" — a single well-sectioned file is the appropriate structure here.

5 / 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 has a clear, explicit trigger clause but completely omits what the skill does — the reader must infer "writes implementation plans" from the name. Trigger terms are decent but miss the most natural synonym ("plan"). Adding a concrete "what" clause and plan-related keywords would move it from weak to strong.

Suggestions

Add an explicit capability clause describing what the skill does, e.g. "Write comprehensive implementation plans that break a spec into bite-sized, test-driven tasks with exact file paths, code, and commands"

Include the natural trigger terms users actually say for this skill: "plan", "implementation plan", "planning", "break this down into tasks", "before coding"

Sharpen distinctiveness by contrasting with adjacent phases, e.g. "...after brainstorming produces a spec and before executing-plans implements it"

DimensionReasoningScore

Specificity

The description names the trigger domain ("spec or requirements for a multi-step task") but states no concrete actions — what the skill does (writing implementation plans) is entirely absent. It sits between anchor 1 (entirely vague) and anchor 2 (domain named, actions minimal); since a domain is clearly named, 2 is the best fit.

2 / 5

Completeness

Only the "when" is present ("Use when you have a spec or requirements for a multi-step task, before touching code"); the "what" is missing entirely, only weakly implied by "before touching code". This is anchor 2's exact pattern (only "when" present without "what"), not 3, where a clear "what" would be stated.

2 / 5

Trigger Term Quality

"spec", "requirements", and "multi-step task" are natural user phrases, but common variations are missing — a user asking to "plan this feature" or "write an implementation plan" would not trigger it. This matches anchor 3 (some relevant keywords, missing common variations) rather than 4, since the skill's own core output term "plan" does not appear.

3 / 5

Distinctiveness Conflict Risk

"Before touching code" pins the pre-implementation phase, but the wording overlaps with adjacent skills in the same family (brainstorming, executing-plans, subagent-driven-development) and with generic task-breakdown/planning skills. Somewhat specific but overlapping — anchor 3.

3 / 5

Total

10

/

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

arwei944/codeg

Path

src-tauri/experts/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.