recipe-fullstack-implement
Orchestrate full-cycle implementation across backend and frontend layers
39
25%
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-fullstack-implement/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 overly abstract and buzzword-heavy, providing no concrete actions, no trigger terms users would naturally use, and no guidance on when Claude should select this skill. It reads more like a resume bullet point than a functional skill description, making it nearly impossible to distinguish from other development-related skills.
Suggestions
Replace vague language with specific concrete actions, e.g., 'Creates API endpoints, database models, frontend components, and connects them end-to-end for new features'.
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to build a new feature, implement a full-stack change, or add functionality spanning API and UI layers'.
Narrow the scope to a distinct niche or specify the technology stack (e.g., React + Node.js, Django + Vue) to reduce conflict risk with other coding skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language like 'orchestrate full-cycle implementation' and 'backend and frontend layers' without naming any concrete actions. No specific tasks (e.g., create APIs, build UI components, write tests) are mentioned. | 1 / 3 |
Completeness | The description weakly addresses 'what' with vague language and completely lacks any 'when' guidance. There is no 'Use when...' clause or equivalent trigger guidance. | 1 / 3 |
Trigger Term Quality | The terms 'orchestrate', 'full-cycle implementation', and 'backend and frontend layers' are abstract jargon that users would rarely naturally say. Users are more likely to say things like 'build a feature', 'create an API endpoint', or 'add a new page'. | 1 / 3 |
Distinctiveness Conflict Risk | This description is extremely generic — 'backend and frontend' covers virtually all web development tasks and would conflict with nearly any coding-related skill. There is no clear niche or distinct trigger. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a moderately well-structured orchestration skill that provides useful concrete patterns (agent routing by filename, mandatory prompt suffixes, stop points) but relies heavily on external references without providing enough standalone context. The workflow is discernible but has gaps due to delegation to external documents, and there is some redundancy in repeated compliance reminders. The skill would benefit from tighter organization and clearer inline summaries of what the referenced documents contain.
Suggestions
Provide a brief inline summary of the key steps from monorepo-flow.md so the skill is more self-contained and actionable without requiring the external reference to understand the basic flow.
Consolidate the repeated compliance reminders (e.g., 'follow monorepo-flow.md' appears in multiple sections) into a single authoritative section to improve conciseness.
Add explicit validation checkpoints to the Execution Decision Flow table (Section 1) — currently it routes to next actions but doesn't specify how to verify the routing decision was correct.
Use proper markdown links for all external references (e.g., [monorepo-flow.md](references/monorepo-flow.md)) consistently to improve progressive disclosure and navigation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is moderately efficient but includes some redundancy—repeated reminders to follow monorepo-flow.md and subagents-orchestration-guide, and the pre-execution checklist partially duplicates earlier instructions. Some sections could be tightened, but it mostly avoids explaining concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides concrete agent routing patterns, specific subagent_type strings, and structured decision tables, which is good. However, most of the actual execution logic is delegated to external references (monorepo-flow.md, subagents-orchestration-guide) without inline specifics, making this skill incomplete on its own. The filename-pattern routing and prompt suffix are concrete and actionable. | 2 / 3 |
Workflow Clarity | The workflow has a clear high-level sequence (assessment → UI spec → design → planning → task execution → security review) with some explicit stop points and validation steps (quality-fixer after each executor, security review after all tasks). However, the heavy reliance on external references for the actual step definitions means the workflow within this document has gaps, and the decision flow table in section 1 lacks explicit validation checkpoints. | 2 / 3 |
Progressive Disclosure | The skill references external files (monorepo-flow.md, subagents-orchestration-guide) appropriately and keeps the overview at a manageable level. However, the references are not always clearly signaled with links, and the relationship between this skill and its dependencies could be better organized—some sections mix overview content with detailed execution rules that might belong in 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
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.