recipe-front-plan
Create frontend work plan from design document and obtain plan approval
45
47%
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-plan/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 conveys a basic idea of the skill's purpose—creating frontend work plans from design documents—but lacks the depth and explicit trigger guidance needed for reliable skill selection. It is missing a 'Use when...' clause, has limited trigger term coverage, and provides only a surface-level view of its capabilities.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user has a design document, mockup, or spec and needs to break it into frontend implementation tasks or get a plan reviewed/approved.'
Include more natural trigger terms and variations such as 'implementation plan', 'task breakdown', 'UI development', 'mockup', 'spec', 'Figma', 'sprint plan'.
Expand the 'what' portion with more specific actions, e.g., 'Parses design documents to generate a structured frontend implementation plan with task estimates, component breakdowns, and dependency mapping, then facilitates plan approval.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (frontend work planning) and two actions (create plan, obtain approval), but lacks detail about what the plan contains or what a 'design document' entails. Not comprehensive enough for a 3. | 2 / 3 |
Completeness | Describes what it does (create a frontend work plan and obtain approval) but has no explicit 'Use when...' clause or equivalent trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also fairly thin, placing this at 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant terms like 'frontend', 'work plan', 'design document', and 'plan approval', but misses common variations users might say such as 'implementation plan', 'UI plan', 'mockup', 'spec', 'task breakdown', or 'sprint planning'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'frontend', 'design document', and 'plan approval' provides some specificity, but it could overlap with general project planning or task management skills. The niche is somewhat defined but not sharply distinct. | 2 / 3 |
Total | 7 / 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 is a well-structured orchestration skill with clear workflow sequencing and good conditional logic for different scenarios. Its main weaknesses are moderate verbosity in prompt construction details and reliance on external skills whose content isn't available for verification. The actionability is decent for an orchestration-style skill but leans more toward procedural description than concrete executable guidance.
Suggestions
Tighten the prompt construction section in Step 3 by using a concise template or table format instead of nested bullet points with conditional logic prose.
Consider providing a concrete example of a complete Agent tool invocation (with all parameters filled in) to make the guidance more immediately actionable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some redundancy—e.g., restating orchestrator identity and referencing external guides multiple times. The prompt construction details for work-planner are thorough but could be tightened. Some sections like 'Scope Boundaries' add modest value but border on unnecessary given the execution process already implies scope. | 2 / 3 |
Actionability | The skill provides concrete steps with specific tool invocation parameters (subagent_type, description, prompt templates), which is good. However, it relies heavily on external skills (subagents-orchestration-guide, acceptance-test-generator, work-planner) without providing their content, and the guidance is more procedural description than executable code. The ls command in Step 1 is concrete, but most other steps are orchestration instructions rather than copy-paste-ready commands. | 2 / 3 |
Workflow Clarity | The three-step process is clearly sequenced with explicit decision points (user confirmation in Step 2, conditional branching based on test generation, user review/approval in Step 3). There are feedback loops for plan revision ('If user requests changes, re-invoke work-planner') and validation checkpoints (highlighting unclear scope, obtaining approval before completion). The workflow handles conditional paths well. | 3 / 3 |
Progressive Disclosure | The skill references external skills (subagents-orchestration-guide, acceptance-test-generator, work-planner) appropriately, but no bundle files are provided to verify these references exist. The content is reasonably structured with clear sections, but the inline detail about prompt construction for the work-planner invocation is quite dense and could potentially be split out. References are one-level deep, which is good. | 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
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.