recipe-front-build
Execute frontend implementation in autonomous execution mode
44
31%
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 ./skills/recipe-front-build/SKILL.mdQuality
Discovery
0%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 description is critically weak across all dimensions. It provides no concrete actions, no trigger terms users would naturally use, no 'when to use' guidance, and is too generic to distinguish from other development-related skills. The phrase 'autonomous execution mode' is internal jargon that adds no value for skill selection.
Suggestions
List specific concrete actions the skill performs, e.g., 'Builds React components, writes HTML/CSS layouts, implements responsive designs, adds interactivity with JavaScript'.
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to build a web page, create UI components, implement a frontend feature, or work with HTML, CSS, JavaScript, React, or Vue.'
Remove the jargon 'autonomous execution mode' and replace with a clear description of the skill's operational approach, such as 'Independently scaffolds and iterates on frontend code without step-by-step confirmation'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'frontend implementation' and 'autonomous execution mode' without listing any concrete actions. It doesn't specify what kind of frontend work (e.g., building components, styling, writing HTML/CSS/JS). | 1 / 3 |
Completeness | The 'what' is extremely vague ('frontend implementation') and there is no 'when' clause at all. There are no explicit triggers or guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | 'Frontend implementation' is somewhat relevant but overly broad, and 'autonomous execution mode' is technical jargon that users would never naturally say. Missing natural terms like 'React', 'CSS', 'HTML', 'UI', 'web page', 'component', etc. | 1 / 3 |
Distinctiveness Conflict Risk | 'Frontend implementation' is very broad and could overlap with any web development, UI design, or coding skill. 'Autonomous execution mode' adds no meaningful differentiation for skill selection purposes. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a well-structured orchestration workflow with clear sequencing, decision flows, and escalation paths for frontend implementation. Its main weaknesses are moderate verbosity with some repeated concepts, and actionability that leans toward describing what to do rather than providing fully executable examples. The workflow clarity is strong with explicit validation gates and error recovery paths.
Suggestions
Provide a complete, copy-paste-ready Agent tool invocation example with all fields filled in, rather than just listing field names and partial examples.
Reduce redundancy by consolidating the repeated mentions of the 4-step cycle and CRITICAL warnings into a single prominent callout.
Extract the structured response JSON schemas and sub-agent invocation constraints into a referenced file (e.g., SUBAGENT-SPECS.md) to improve progressive disclosure and reduce inline bulk.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes some redundancy (e.g., repeating 'CRITICAL' warnings, restating the 4-step cycle multiple times) and explanatory text that could be tightened. The decision flow table and structured response specs are useful but some surrounding prose is unnecessary. | 2 / 3 |
Actionability | Provides concrete sub-agent invocation patterns with specific field names and structured response formats, but much of the guidance is semi-abstract orchestration instructions rather than fully executable code. The bash snippets are minimal checks, and the actual Agent tool invocations are described rather than shown as complete, copy-paste-ready examples. | 2 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced with explicit phases (pre-execution check → task decomposition → execution cycle → security review), includes validation checkpoints at each step, escalation/error handling paths, and a feedback loop (quality-fixer before every commit, re-invoke on failure). The decision flow table for task generation is well-structured. | 3 / 3 |
Progressive Disclosure | References external skills (subagents-orchestration-guide) and external files (task files, plans), but the skill itself is fairly long and monolithic. Some sections like the structured response specification and sub-agent invocation constraints could be split into referenced files. The cross-references that exist are not clearly signaled with navigation links. | 2 / 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
- shinpr/claude-code-workflows
- Commit
2e719be
- 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.