recipe-fullstack-build
Execute decomposed fullstack tasks with layer-aware agent routing
44
31%
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-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 'when to use' guidance. It reads more like an internal architecture label than a user-facing skill description, making it nearly impossible for Claude to correctly select this skill from a pool of alternatives.
Suggestions
Replace abstract jargon with concrete actions, e.g., 'Builds frontend components, creates API endpoints, configures database models, and connects layers in fullstack web applications.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to build a web app, create a full stack feature, connect frontend to backend, or scaffold a new project.'
Clarify the specific niche this skill covers to distinguish it from general coding skills — specify frameworks, languages, or architectural patterns if applicable.
| 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 UI components', or 'configure database schemas'. | 1 / 3 |
Completeness | The 'what' is vague ('execute decomposed fullstack tasks') and there is no 'when' clause or explicit trigger guidance whatsoever. Both components are very weak or missing. | 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', none of which appear here. | 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 this from other development-related skills. | 1 / 3 |
Total | 4 / 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, explicit decision trees, and proper escalation paths. Its main weaknesses are moderate redundancy (duplicate routing tables, repeated emphasis markers) and a gap between procedural descriptions and fully executable examples — the Agent tool invocations describe what to do but don't show complete, copy-paste-ready invocation patterns with expected response schemas.
Suggestions
Remove the duplicate agent routing table — define it once and reference it, or consolidate the Execution Protocol section with the Task Execution Cycle section
Add concrete JSON examples for the structured responses expected from sub-agents (e.g., what an escalation_needed response looks like vs a readyForQualityCheck response) to make response handling fully actionable
Consider moving the Task Decomposition Phase and Security Review sections to separate reference files, keeping only a brief summary and link in the main skill body
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes some redundancy — the routing table appears twice (once in Execution Protocol and once in Agent Routing Table section), and some instructions like the orchestrator identity statement and repeated emphasis on 'MANDATORY'/'CRITICAL' add bulk without proportional value. However, it mostly avoids explaining concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides concrete bash commands for verification steps and structured agent invocation patterns with specific subagent_type values and prompt templates. However, much of the guidance is procedural/abstract rather than fully executable — the Agent tool invocations are described but not shown as complete executable examples, and the structured response handling lacks concrete JSON schemas for the expected responses. | 2 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced with explicit phases (pre-execution prerequisites → task decomposition → pre-execution checklist → 4-step execution cycle → security review → output). It includes validation checkpoints (verify task file generation, check executor response status, quality-fixer approval before commit), escalation paths for blocked/failed states, and a decision flow table for handling different initial states. | 3 / 3 |
Progressive Disclosure | The skill references external files (monorepo-flow.md, subagents-orchestration-guide) appropriately, but the main content itself is quite long and could benefit from splitting detailed sections (like the task decomposition phase or security review) into separate reference files. The references are one-level deep which is good, but the inline content is dense enough to warrant better separation. | 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
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.