recipe-fullstack-build
Execute decomposed fullstack tasks with layer-aware agent routing
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-fullstack-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 heavily jargon-laden and lacks any concrete actions, natural trigger terms, or explicit usage guidance. It reads more like an internal architecture label than a skill description that would help Claude select the right skill. It would be nearly impossible for Claude to reliably choose this skill over others based on this description alone.
Suggestions
Replace abstract jargon with concrete actions, e.g., 'Builds full-stack web features by generating frontend components, API endpoints, database schemas, and connecting them together.'
Add an explicit 'Use when...' clause with natural trigger terms like 'build a web app', 'full-stack feature', 'frontend and backend', 'create an API with a UI'.
Clarify what 'layer-aware agent routing' means in practical terms—e.g., 'Routes subtasks to appropriate layers (UI, API, database) for coordinated implementation' so Claude understands the distinct niche.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses abstract, jargon-heavy language ('decomposed fullstack tasks', 'layer-aware agent routing') without listing any concrete actions. There are no specific capabilities like 'create API endpoints', 'build React components', etc. | 1 / 3 |
Completeness | The 'what' is vague ('execute decomposed fullstack tasks') and there is no 'when' clause or any explicit trigger guidance. Both components are very weak. | 1 / 3 |
Trigger Term Quality | The terms 'decomposed fullstack tasks' and 'layer-aware agent routing' are technical jargon that no user would naturally say. Users would say things like 'build a web app', 'create frontend and backend', or 'full-stack development'. | 1 / 3 |
Distinctiveness Conflict Risk | 'Fullstack tasks' is extremely broad and could overlap with virtually any web development, frontend, backend, database, or DevOps skill. There are no distinct triggers to differentiate it from other development-related skills. | 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 thorough orchestration workflow with excellent sequencing and validation checkpoints, but suffers significantly from verbosity — the Consumed Task Set filtering logic is repeated three times, and many sections could be compressed without losing clarity. The actionability is moderate: decision tables and routing patterns are concrete, but the skill depends heavily on external references that aren't bundled, and actual tool invocations lack complete executable examples.
Suggestions
Extract the Consumed Task Set computation into a single definition and reference it by name in subsequent sections instead of restating the filtering rules three times.
Compress the Implementation Readiness Check and Task Generation Decision Flow into tighter decision tables — the current prose around each table adds little value for Claude.
Bundle the referenced monorepo-flow.md and subagents-orchestration-guide files, or inline the critical routing/cycle definitions so the skill is self-contained.
Move the detailed Pre-execution Prerequisites and Post-Implementation Verification sections into separate reference files, keeping only summaries in the main SKILL.md.
| 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 patterns (Consumed Task Set definition is restated multiple times), and the Implementation Readiness Check table, Task Generation Decision Flow table, and Pre-execution Checklist contain information that could be condensed. The skill also explains orchestration concepts that could be assumed. | 1 / 3 |
Actionability | The skill provides concrete agent routing tables, specific file patterns, and structured decision flows with clear branching logic. However, it relies heavily on external references (monorepo-flow.md, subagents-orchestration-guide) without including their content, and the actual Agent tool invocations are described rather than shown with complete executable examples. The subagent invocation in the Task Decomposition section is the closest to concrete but uses placeholder values. | 2 / 3 |
Workflow Clarity | The multi-step workflow is exceptionally well-sequenced with explicit validation checkpoints at every stage: Implementation Readiness Check gates execution, the 4-step (actually 6-step) task cycle has clear escalation/retry branches for each status response, post-implementation verification includes a fix-and-rerun loop, and final cleanup has error handling. Feedback loops are present for quality-fixer rejections, stub detection, and test review failures. | 3 / 3 |
Progressive Disclosure | The skill references external files (monorepo-flow.md, subagents-orchestration-guide) for detailed routing and orchestration patterns, which is good progressive disclosure. However, no bundle files are provided to verify these references exist, and the skill itself is monolithic — the lengthy Pre-execution Prerequisites, Consumed Task Set computation, and Task Generation Decision Flow sections could be split into separate reference files rather than inlined in the main SKILL.md. | 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
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.