CtrlK
BlogDocsLog inGet started
Tessl Logo

writing-plans

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

48

Quality

51%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/writing-plans/SKILL.md

The canonical home for this skill is writing-plans in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 well-structured, actionable planning skill with concrete templates and an explicit TDD validation loop. It is slightly held back by minor padding and a weak closing When-to-Use section, and gains nothing from progressive disclosure since no bundle files accompany it.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete templates, but includes minor padding: 'questionable taste', a duplicated assumption sentence, and a low-value 'When to Use' section ('applicable to execute the workflow or actions described in the overview') that could be trimmed.

3 / 5

Actionability

It provides copy-paste-ready templates (plan header, task structure with pytest/git commands and expected output) and exact path/commit patterns; minor gaps are the placeholder fields ([Feature Name], [Component Name]) and reliance on the spec for actual content.

4 / 5

Workflow Clarity

The TDD task loop has explicit validation checkpoints ('Expected: FAIL' then 'Expected: PASS' before commit) and the plan-then-handoff sequence is clear; the top-level plan-writing workflow itself lacks an explicit validation/feedback checkpoint, keeping it just below 5.

4 / 5

Progressive Disclosure

No bundle files exist, but the single SKILL.md is well-organized into clearly signaled sections (Overview, Granularity, Header, Task Structure, Remember, Execution Handoff) and points to sub-skills via explicit 'REQUIRED SUB-SKILL' markers; minor organization gaps (e.g. the filler When-to-Use section) keep it at 4.

4 / 5

Total

15

/

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 functions almost entirely as a trigger clause with a clear 'when' but no statement of what the skill does, leaving its capabilities implicit. Keywords are relevant but lack common synonyms, and the niche overlaps with sibling planning skills.

Suggestions

Add an explicit 'what' clause stating the concrete action, e.g. 'Write comprehensive implementation plans that break a spec into bite-sized, TDD-style tasks.'

Broaden trigger terms with natural synonyms users say, such as 'implementation plan', 'break down a feature', or 'plan the work before coding'.

Sharpen distinctiveness by scoping the trigger to planning-from-spec specifically (e.g. 'before writing any code, to produce a saved plan document'), reducing overlap with executing-plans and brainstorming.

DimensionReasoningScore

Specificity

The phrase 'spec or requirements for a multi-step task' names the domain, but the description lists no concrete actions (e.g. 'write implementation plans', 'break specs into bite-sized tasks') — actions are minimal/generic.

2 / 5

Completeness

It gives a clear 'when' ('Use when you have a spec or requirements for a multi-step task, before touching code') but omits the 'what' — it never states that the skill writes implementation plans, matching the 'only when is present without what' anchor.

2 / 5

Trigger Term Quality

It includes relevant keywords like 'spec', 'requirements', 'multi-step task', and 'before touching code', but misses common variations a user might say such as 'plan', 'implementation plan', or 'break down a feature'.

3 / 5

Distinctiveness Conflict Risk

The trigger is reasonably specific to pre-code planning, but it overlaps with the related planning skill family (brainstorming, executing-plans, subagent-driven-development) referenced in the body, so it could still trigger for sibling skills.

3 / 5

Total

10

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.