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.
52
41%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./source/skills/teach-impeccable/SKILL.mdQuality
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 mentions 'design context' and 'design guidelines' without specifying concrete actions or outputs. It uses second person ('your project', 'your AI config file') which violates voice guidelines. The one-time setup framing provides some distinctiveness but the lack of specific trigger terms and explicit 'Use when' guidance significantly weakens its utility for skill selection.
Suggestions
Add specific concrete actions: e.g., 'Collects brand colors, typography choices, spacing rules, and component patterns from the user and writes them to the 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, configure brand styles, initialize a design system, or establish project theming for the first time.'
Switch to third person voice: replace 'your project' and 'your AI config file' with 'the project' and 'the AI config file', e.g., 'Gathers design context for a project and saves it to the AI config file.'
| 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 (colors, typography, spacing?) or what the config file contains. | 1 / 3 |
Completeness | It partially answers 'what' (gathers design context and saves to config) and 'when' (one-time setup, run once), but the 'when' is about frequency rather than explicit trigger conditions. There is no 'Use when...' clause with trigger 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 not what users would naturally request. Missing terms like 'brand colors', 'style guide', 'design tokens', 'theme setup'. | 1 / 3 |
Distinctiveness Conflict Risk | The 'one-time setup' and 'AI config file' framing provides some distinctiveness, but 'design context' and 'design guidelines' are broad enough to overlap with other design-related skills. The setup/initialization angle 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 onboarding/setup skill with clear steps and a useful output template. Its main weaknesses are moderate verbosity in the question lists (Claude could generate contextual UX questions without exhaustive prompting), lack of concrete commands for codebase exploration, and missing validation after file writes. The template variables without explanation reduce immediate actionability.
Suggestions
Add a validation step after writing to .impeccable.md — e.g., 'Read back the written section and confirm with the user that the design context accurately captures their intent before proceeding.'
Trim the question lists in Step 2 to just the category headers with 1-2 key questions each; Claude can generate contextually appropriate follow-ups without exhaustive enumeration.
Add concrete commands for codebase exploration in Step 1 (e.g., 'Check for tailwind.config.*, globals.css, or design-tokens.* files') to make the exploration step more actionable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary elaboration. The question lists in Step 2 are somewhat verbose with parenthetical examples that Claude could generate on its own. The bullet lists in Step 1 could be tighter. | 2 / 3 |
Actionability | The skill provides a clear process and a concrete markdown template for output, but relies on template variables ({{ask_instruction}}, {{config_file}}) without explaining their resolution. The codebase exploration step lists what to look for but doesn't provide specific commands or code to discover these artifacts. | 2 / 3 |
Workflow Clarity | The three steps are clearly sequenced (explore → ask → write), but there's no validation checkpoint. After writing to .impeccable.md, there's no step to verify the file was written correctly or to review the output with the user before finalizing. For a file-writing operation, a review/confirmation step before writing would strengthen the workflow. | 2 / 3 |
Progressive Disclosure | For a skill of this size and scope (~60 lines, single-purpose setup task), the content is well-organized into clear sections with logical progression. No external references are needed, and the structure is easy to scan and follow. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- pbakaus/impeccable
- Commit
3a4fc70
- 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.