recipe-front-build
Execute frontend implementation in autonomous execution mode
30
23%
Does it follow best practices?
Impact
—
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 uses vague, jargon-heavy language ('autonomous execution mode') without specifying concrete actions, natural trigger terms, or when the skill should be selected. It would be nearly impossible for Claude to reliably distinguish this skill from other frontend or coding-related skills.
Suggestions
Replace vague language with specific concrete actions, e.g., 'Builds React components, implements responsive layouts, writes CSS/HTML, and integrates frontend APIs'.
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 React/HTML/CSS'.
Remove internal jargon like 'autonomous execution mode' and instead describe the operational behavior concretely if relevant, or omit it if it doesn't help with skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description is vague — 'frontend implementation' and 'autonomous execution mode' are abstract phrases that don't describe concrete actions like 'build components', 'style pages', or 'write React code'. | 1 / 3 |
Completeness | The 'what' is extremely vague ('frontend implementation') and there is no 'when' clause or explicit trigger guidance at all. | 1 / 3 |
Trigger Term Quality | 'Frontend implementation' is somewhat relevant but overly broad, and 'autonomous execution mode' is internal jargon that no user would naturally say. Missing natural terms like 'React', 'CSS', 'HTML', 'UI', 'web page', etc. | 1 / 3 |
Distinctiveness Conflict Risk | 'Frontend implementation' is extremely broad and could overlap with any skill related to web development, UI design, CSS, JavaScript frameworks, or general coding tasks. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
47%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 comprehensive orchestration workflow with strong workflow clarity — clear sequencing, validation checkpoints, escalation paths, and feedback loops. However, it is excessively verbose, repeating the same task-file filtering patterns multiple times and including procedural detail that could be significantly compressed. The lack of bundle files means all content is crammed into one monolithic document, and the actionability suffers from abstract procedural descriptions rather than concrete executable examples.
Suggestions
Reduce verbosity by extracting the Consumed Task Set filtering rules into a single definition and referencing it by name instead of restating the exclusion patterns in multiple sections.
Add concrete, copy-paste-ready examples of Agent tool invocations with exact parameter structures and example response JSON showing the status fields to parse.
Split detailed reference content (e.g., task file pattern rules, verification criteria tables, cleanup procedures) into separate bundle files and reference them from the main SKILL.md to improve progressive disclosure.
Remove redundant explanatory text — e.g., the parenthetical '(computed in the Consumed Task Set section above)' and repeated cross-references that add tokens without adding clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~200+ lines with extensive procedural detail that could be significantly compressed. Many sections repeat the same filtering/exclusion patterns (Consumed Task Set criteria are restated multiple times), and the Implementation Readiness Check table and Task Generation Decision Flow table contain information that could be condensed. The skill explains orchestration concepts and decision flows at length rather than trusting Claude to follow concise instructions. | 1 / 3 |
Actionability | The skill provides concrete subagent invocation patterns with specific subagent_type strings, status field checks, and branching logic, which is good. However, there are no executable code examples — the guidance is procedural prose with tables and checklists rather than copy-paste-ready commands. Key details like the exact Agent tool invocation syntax and response parsing are described abstractly rather than shown concretely. | 2 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced with explicit phases (Pre-execution → Task Decomposition → Execution Cycle → Post-Implementation Verification → Final Cleanup → Completion Report). The 4-step task cycle includes explicit validation checkpoints, escalation branches, and feedback loops (e.g., stub_detected → return to step 2, quality-fixer must approve before commit). Error recovery paths are well-defined throughout. | 3 / 3 |
Progressive Disclosure | The skill references external subagents and skills (e.g., 'see subagents-orchestration-guide skill') but has no bundle files to support progressive disclosure. The content is monolithic — all orchestration logic, decision tables, cleanup rules, and verification steps are inline in a single long document. Content like the Consumed Task Set filtering rules or the Post-Implementation Verification fix cycle could be split into referenced files. | 2 / 3 |
Total | 8 / 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
adf2e4d
- 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.