CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

html-plan

Direct-invocation specialist for clear, self-contained HTML plans that preserve source material while improving hierarchy, sequence, ownership, dependencies, and reviewability. Use when the user explicitly invokes html-plan or the broad html skill routes a plan request here. Do not activate independently from a general request.

Quality

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 lean, well-structured, and assumes Claude's competence, with concrete build and verification directives and clean one-level-deep referencing. The only gaps are a missing worked structural example and an explicit fix-and-retry feedback loop in the verify step.

Suggestions

Add a short worked structural skeleton (e.g. a minimal <main>/<section>/<table> outline) so the build directive has a copy-paste-ready starting point.

Make the verify step an explicit feedback loop: 'if a check fails, fix the HTML and re-inspect before returning the path.'

DimensionReasoningScore

Conciseness

Lean ~40-line body that assumes Claude's competence — it never explains what HTML/CSS/landmarks are — and every section earns its place with no padding; only mildly florid phrasing ('quiet, workmanlike direction') keeps it from being perfectly spare but does not rise to a penalty.

5 / 5

Actionability

Gives concrete, specific directives ('Use semantic headings, lists, tables, and landmarks. Keep essential CSS and JavaScript inline... make any navigation or disclosure keyboard-operable') and a concrete verification checklist, but provides no worked structural example or template, a minor gap for an instruction-only skill.

4 / 5

Workflow Clarity

A clear sequence (shape the document → preserve traceability → build and verify) with an explicit verification checklist ('Inspect the result at wide and narrow widths. Check that no commitment disappeared...'), but it lacks an explicit fix-and-retry feedback loop, capping it just below 5.

4 / 5

Progressive Disclosure

A sub-50-line skill with no bundle files and well-organized sections; the single external reference ([design-artifact](../design-artifact/SKILL.md)) is clearly signaled and one level deep, satisfying the simple-skill exception for progressive disclosure.

5 / 5

Total

18

/

20

Passed

Description

80%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 clearly states both what the skill does and when to use it, with strong distinctiveness and boundary guidance. Trigger term coverage is the weakest dimension, relying on invocation routing rather than natural user phrasing.

Suggestions

Broaden trigger terms to include natural phrases a user might say unprompted (e.g. 'project plan', 'roadmap', 'implementation plan') rather than only 'html-plan' and 'plan request'.

Consider rephrasing the improvement dimensions as discrete concrete actions so specificity reaches full coverage.

DimensionReasoningScore

Specificity

Names the domain ('self-contained HTML plans') and several specific improvement actions ('preserve source material', 'improving hierarchy, sequence, ownership, dependencies, and reviewability'), but the actions are improvement qualities rather than discrete concrete operations like 'extract', 'fill', 'merge', leaving a minor gap versus full coverage.

4 / 5

Completeness

Explicitly answers both what ('specialist for clear, self-contained HTML plans that preserve source material while improving...') and when ('Use when the user explicitly invokes html-plan or the broad html skill routes a plan request here') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes relevant trigger terms ('html-plan', 'plan request') but these are narrow invocation-routing phrases; common natural variations a user might say (e.g. 'plan', 'project plan', 'roadmap') are missing.

3 / 5

Distinctiveness Conflict Risk

Clear niche with distinct triggers and an explicit boundary ('Do not activate independently from a general request'; differentiated from the broad html skill), giving minimal conflict risk.

5 / 5

Total

17

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

plannotator/effective-html

Path

skills/html-plan/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.