recipe-fullstack-build

Execute decomposed fullstack tasks with layer-aware agent routing

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with clear, validated multi-step workflows, but it is longer than necessary due to duplicated patterns and tables, and it does not split its substantial detail into separate reference files.

Suggestions

De-duplicate the task-file exclusion patterns by defining them once and referencing that definition in both Work Plan Resolution and the Consumed Task Set.

Consolidate the two routing tables (the list and the Agent Routing Table) into a single canonical table.

Consider extracting the lengthy Work Plan Resolution rules and Post-Implementation Verification details into a reference file to reduce the inline footprint and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	It assumes Claude's competence and avoids explaining known concepts, but the Work Plan Resolution and Consumed Task Set sections repeat the same exclusion patterns verbatim and the routing table appears twice, so it could be tightened.	2 / 3
Actionability	Provides fully executable, copy-paste-ready guidance: exact subagent_type strings, filename patterns, response status fields to branch on, and a literal scope-boundary block to append to subagent prompts.	3 / 3
Workflow Clarity	The 4-step task cycle and post-implementation verification include explicit validation checkpoints, retry/escalation branches, and a 'repeat until all pass or blocked' fix loop.	3 / 3
Progressive Disclosure	Cross-skill references are one level deep and clearly signaled, but the body is a single ~177-line monolithic protocol with no internal offloading; content that could be split is inline.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 concrete and domain-specific but stops short of listing multiple distinct actions and provides no explicit usage trigger, leaving it at the mid-level across all dimensions.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers, e.g. 'Use when the user asks to execute or build a decomposed fullstack plan with separate backend and frontend tasks.'

Enumerate a few concrete actions (e.g. 'route backend/frontend tasks to layer-specific executors, run quality fixers, commit per task') to lift specificity to 3.

Include common natural phrasings users would say ('run my plan', 'execute the decomposed tasks') to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the fullstack domain and concrete actions ("Execute decomposed fullstack tasks", "layer-aware agent routing") but describes a single compound action rather than multiple distinct concrete actions.	2 / 3
Completeness	States what the skill does but lacks any "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	"fullstack tasks" is a natural term, but "layer-aware agent routing" is jargon and common user-facing variations (e.g. "run my plan", "build the backend and frontend tasks") are absent.	2 / 3
Distinctiveness Conflict Risk	The layer-aware routing framing is fairly distinct, but without explicit triggers it could still overlap with general build/orchestration skills.	2 / 3
	Total	8 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: shinpr/claude-code-workflows
Commit: 66e3b29

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.