recipe-front-review
Design Doc compliance and security validation with optional auto-fixes
50
55%
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-review/SKILL.mdQuality
Discovery
32%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 terse and lacks a 'Use when...' clause, making it difficult for Claude to know when to select this skill. While it names a domain (Design Doc) and hints at capabilities (compliance, security validation, auto-fixes), it doesn't specify concrete actions or provide trigger guidance. The description would benefit significantly from explicit trigger terms and a clearer enumeration of what it validates.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks to review, validate, or audit a design document for compliance or security issues.'
List specific concrete actions, e.g., 'Validates design documents against compliance standards, checks for security vulnerabilities, flags missing sections, and optionally applies auto-fixes for common issues.'
Include natural keyword variations users might say, such as 'design document', 'design review', 'security audit', 'compliance check', 'RFC review'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('Design Doc') and two actions ('compliance and security validation' and 'auto-fixes'), but lacks concrete specifics about what validation entails or what auto-fixes are applied. | 2 / 3 |
Completeness | Provides a partial 'what' (compliance and security validation with auto-fixes) but completely lacks a 'when' clause or explicit trigger guidance, which per the rubric caps completeness at 2, and the 'what' itself is also weak enough to warrant a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'Design Doc', 'compliance', 'security validation', and 'auto-fixes', but misses common user variations such as 'design document', 'security review', 'audit', 'lint', or 'check'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'Design Doc' with 'compliance and security validation' is somewhat specific, but 'compliance' and 'security validation' are broad terms that could overlap with other security or compliance-related skills. | 2 / 3 |
Total | 7 / 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-structured orchestration skill with strong actionability and workflow clarity. Each step has concrete subagent invocations with specific parameters, clear decision points, and explicit validation/re-validation loops. The main weaknesses are moderate verbosity for the amount of content inline and the lack of progressive disclosure for a skill of this complexity — splitting report templates or routing logic into separate reference files would improve navigability.
Suggestions
Consider extracting the detailed report templates and routing decision table into a separate reference file (e.g., REPORT_FORMAT.md) to reduce the main skill's length and improve progressive disclosure.
Tighten the Step 4 section by consolidating the internal routing rule and user-facing presentation — the routing table could be defined once and referenced, rather than explained twice in different contexts.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly dense and covers a complex multi-step orchestration workflow. While it avoids explaining basic concepts Claude already knows, there is some redundancy (e.g., the routing table logic is repeated in both the internal rule and the user-facing prompt template). The report templates and step descriptions could be tightened in places, but overall it's reasonably efficient for the complexity it covers. | 2 / 3 |
Actionability | Each step provides concrete, executable guidance: specific bash commands for prerequisite checks, exact subagent invocation parameters (subagent_type, description, prompt), structured output templates, and clear decision tables. The Agent tool invocations include all necessary fields and the report format is copy-paste ready. | 3 / 3 |
Workflow Clarity | The 11-step workflow is clearly sequenced with explicit validation checkpoints (Steps 9-10 re-validate after fixes), a security block gate (Step 4), feedback loops (Step 5d re-evaluates c-routed findings after DD updates), conditional branching (skip paths when all findings are d or s), and cleanup verification. The routing decision table and skip conditions are well-defined. | 3 / 3 |
Progressive Disclosure | The skill references external subagents and skills (e.g., subagents-orchestration-guide, documentation-criteria, code-reviewer, security-reviewer) which provides some progressive disclosure. However, the SKILL.md itself is a monolithic document with all 11 steps inline rather than splitting detailed step content into separate files. For a skill of this length and complexity (~180 lines), the report templates and routing tables could be extracted into referenced files for better navigation. | 2 / 3 |
Total | 10 / 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
68ecb4a
- 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.