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.

Quality

41%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.cursor/skills/teach-impeccable/SKILL.md

Quality

Discovery

25%

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 too vague about what it actually does—it doesn't specify what 'design context' means, what information is gathered, or what the output looks like. It lacks natural trigger terms users would use and has no explicit 'Use when...' clause. The one-time setup framing provides some distinctiveness but isn't enough to compensate for the lack of specificity.

Suggestions

Specify what 'design context' means concretely—e.g., 'Collects brand colors, typography, spacing, and component styles from your project and saves them as design guidelines in your AI config file.'

Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user wants to set up design guidelines, initialize a style guide, configure brand standards, or establish design tokens for their project.'

Use third-person voice and replace 'your project' / 'your AI config file' with neutral phrasing like 'the project' to avoid second-person penalties and improve clarity.

Dimension	Reasoning	Score
Specificity	The description uses vague language like 'gathers design context' and 'persistent design guidelines' without specifying concrete actions. It doesn't explain what kind of design context, what format, or what specific operations are performed.	1 / 3
Completeness	It partially answers 'what' (gathers design context and saves to config) and implies 'when' (one-time setup, run once), but lacks an explicit 'Use when...' clause with trigger conditions. The when guidance is about frequency rather than triggering scenarios.	2 / 3
Trigger Term Quality	The description lacks natural keywords a user would say. Terms like 'design context', 'AI config file', and 'persistent design guidelines' are abstract and unlikely to match user queries. Missing terms like 'brand colors', 'typography', 'style guide', 'design system', or 'theme setup'.	1 / 3
Distinctiveness Conflict Risk	The mention of 'one-time setup' and 'AI config file' provides some distinctiveness, but 'design context' and 'design guidelines' are broad enough to overlap with other design-related skills. The setup/initialization framing helps somewhat.	2 / 3
	Total	6 / 12 Passed

Implementation

57%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a reasonably well-structured skill for a one-time setup task, with clear steps and a useful output template. However, it lacks validation checkpoints (e.g., confirming the synthesized context with the user before writing), has a confusing sentence fragment in Step 3, and could be more actionable by specifying tool usage and providing a concrete example of completed output.

Suggestions

Add an explicit validation step after synthesizing the Design Context: 'Present the draft to the user for review before writing to file.'

Fix the confusing sentence in Step 3 that starts with 'Then ask the user directly to clarify what you cannot infer. whether they'd also like...' — this appears to be a copy-paste error mixing Step 2 language with the .cursorrules question.

Add a concrete example of a completed Design Context section to show what good output looks like, rather than just the template skeleton.

Specify the tool to use for file operations (e.g., write_file or similar) to make the file-writing step more actionable.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient but includes some unnecessary verbosity, such as listing every possible question to ask the user rather than summarizing categories. The parenthetical examples in aesthetic preferences and the repeated 'ask the user directly' phrasing add minor bloat.	2 / 3
Actionability	The skill provides a clear process and a concrete output template (the markdown section), but lacks executable code or commands. The guidance for writing to `.impeccable.md` is vague—no specific tool usage (e.g., write_file) is mentioned, and there's no example of a completed Design Context section to show what good output looks like.	2 / 3
Workflow Clarity	The three steps are clearly sequenced, but there are no validation checkpoints. After writing to `.impeccable.md`, there's no step to verify the file was written correctly or to confirm the content with the user before finalizing. The instruction about `.cursorrules` is awkwardly placed mid-paragraph in Step 3 rather than as a clear sub-step, and there's a dangling/confusing sentence fragment ('Then ask the user directly to clarify what you cannot infer. whether they'd also like...').	2 / 3
Progressive Disclosure	For a skill of this size and scope (single-purpose, under 80 lines), the content is well-organized into clear sections with headers and sub-headers. No external references are needed, and the structure is easy to scan and follow.	3 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: pbakaus/impeccable
Commit: db1add7

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.