firstrun
First-time setup for uSpec. Prompts for MCP provider and environment (Cursor, Claude Code, Codex), syncs skills to the chosen platform, then configures your Figma template library. Use when the user mentions "firstrun", "first run", "setup", "setup library", "configure templates", or "link templates".
92
88%
Does it follow best practices?
Impact
100%
1.88xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that clearly communicates what the skill does (first-time uSpec setup involving MCP provider selection, skill syncing, and Figma template configuration) and when to use it (with an explicit 'Use when...' clause listing multiple natural trigger terms). It is specific, complete, and distinctive with minimal risk of conflicting with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: prompts for MCP provider and environment, syncs skills to the chosen platform, and configures Figma template library. These are clear, actionable steps. | 3 / 3 |
Completeness | Clearly answers both 'what' (first-time setup: prompts for MCP provider/environment, syncs skills, configures Figma template library) and 'when' (explicit 'Use when...' clause with specific trigger phrases). | 3 / 3 |
Trigger Term Quality | Includes a strong set of natural trigger terms users would say: 'firstrun', 'first run', 'setup', 'setup library', 'configure templates', 'link templates'. These cover common variations of how a user would invoke this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — it targets a very specific niche (first-time uSpec setup) with unique trigger terms like 'firstrun' and 'setup library'. Unlikely to conflict with other skills due to the product-specific context and setup-oriented triggers. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted setup skill with excellent actionability and workflow clarity — every step has concrete commands, tool calls, error handling, and conditional logic for different providers. The main weaknesses are moderate verbosity (some explanatory text could be trimmed) and the monolithic structure that could benefit from splitting provider-specific details into separate references. Overall it's a strong, production-ready skill.
Suggestions
Trim the introductory paragraph and inline explanations (e.g., 'catching a broken connection early avoids wasting time') — Claude doesn't need rationale for why steps exist.
Consider extracting provider-specific logic (figma-console vs figma-mcp call patterns) into a separate reference file to reduce the main skill's length.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long but most content is necessary given the multi-step, multi-provider workflow. However, some sections have unnecessary elaboration (e.g., explaining why MCP verification is done, the 'skip' flow explanation) and the checklist duplication adds tokens. The introductory paragraph restates what the title and description already convey. | 2 / 3 |
Actionability | Provides fully concrete, executable guidance throughout: specific MCP tool calls with parameters, exact bash commands for syncing, JavaScript code for font detection, a complete JSON schema for the config output, and specific error messages to display. Every step tells Claude exactly what to do. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with a progress checklist, clear sequencing, explicit validation at Step 1b (MCP connection verification), error handling with user-facing messages at multiple steps (sync failure, missing templates, missing library URL), and conditional branching clearly documented for each MCP provider. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headings and numbered steps, but it's a monolithic document (~200 lines) with no references to external files. The JavaScript code block and the detailed per-provider branching logic could potentially be split into reference files, though for a setup skill this level of inline detail is somewhat justified. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%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
- redongreen/uSpec
- Commit
4eae941
- 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.