CtrlK
BlogDocsLog inGet started
Tessl Logo

teach-impeccable

One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.

86

2.32x
Quality

80%

Does it follow best practices?

Impact

100%

2.32x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./archived/legacy-companion/.agents/skills/teach-impeccable/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

100%Weight 40%Scale 1-3

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 tight, well-structured instruction workflow with concrete tool usage, specific questions, and a ready-to-use template. It respects Claude's competence and needs no external references for its scope.

DimensionReasoningScore

Conciseness

Lean and efficient with no padding or explanations of concepts Claude already knows; the scan checklists and question lists are the actual working content, not fluff.

3 / 3

Actionability

Concrete, executable guidance throughout — an explicit tool call ("call the AskUserQuestionTool"), specific scan targets, exact questions to ask, and a copy-paste markdown template for the Design Context section.

3 / 3

Workflow Clarity

A clearly sequenced Step 1 → Step 2 → Step 3 process with an explicit verification checkpoint ("Confirm completion and summarize the key design principles"); this is not a destructive or batch operation, so no feedback-loop cap applies.

3 / 3

Progressive Disclosure

Under 50 lines with no need for external references, organized into well-labeled sections and subsections; per the simple-skills note this earns full marks without bundle files.

3 / 3

Total

12

/

12

Passed

Description

60%Weight 40%Scale 1-3

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 concrete actions and the target artifact (AI config file), but lacks an explicit invocation trigger and has only partial coverage of natural user phrasing. Adding a "Use when..." clause and broader trigger terms would lift the weaker dimensions.

Suggestions

Add an explicit trigger clause, e.g. "Use when setting up persistent design guidelines for a project, or when the user asks to establish a design context / brand style."

Broaden natural trigger terms to include phrasings users actually say: branding, design system, UI style guide, visual direction.

Sharpen the action verbs (e.g. "interviews the user for design preferences and writes them to CLAUDE.md") to further reduce overlap with generic setup skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "gathers design context", "saves it to your AI config file", "establish persistent design guidelines" — rather than vague abstractions.

3 / 3

Completeness

The "what" is clear, but the "when" is only implied by the directive "Run once to establish persistent design guidelines"; no explicit "Use when..." trigger, which caps completeness at 2.

2 / 3

Trigger Term Quality

Some natural terms appear ("design context", "design guidelines"), but common variations a user would say (branding, design system, UI style) are missing.

2 / 3

Distinctiveness Conflict Risk

The design-context onboarding niche is recognizable, but the skill could overlap with general project-setup or config-writing skills given the weak triggers.

2 / 3

Total

9

/

12

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
The-Vibe-Company/companion
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.