recipe-fullstack-implement

Orchestrate full-cycle implementation across backend and frontend layers

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

62%

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

The body is a well-structured orchestrator protocol with strong workflow clarity and validation feedback loops, and it provides many concrete routing/actionability details. Its main gaps are heavy deferral of step-by-step detail to external references and some emphatic redundancy.

Suggestions

Inline a concise summary of the monorepo-flow scale/step structure (or a trimmed step table) so the orchestrator is not wholly dependent on an external reference for the core sequence.

Consolidate repeated "MANDATORY"/"CRITICAL" emphasis and the pre-execution checklist to reduce redundancy without losing the stop-point guarantees.

Add a brief navigation map at the top listing the external references and what each is consulted for, improving discovery given the absence of local bundle files.

Dimension	Reasoning	Score
Conciseness	The body is dense and task-focused with little concept re-explanation, but repeated emphatic markers ("MANDATORY", "CRITICAL", "MANDATORY" checklists) and some checklist/protocol duplication could be tightened.	2 / 3
Actionability	It gives concrete specifics (exact subagent_type strings, filename routing patterns, `git diff --name-only main...HEAD`, pass/fail status thresholds), but the core design-through-planning steps are deferred to "Follow monorepo-flow.md" rather than given inline.	2 / 3
Workflow Clarity	Multi-step orchestration is clearly sequenced with explicit stop points, a quality-fixer feedback loop (stub_detected/blocked/approved), and a post-implementation verification cycle that re-runs only failed verifiers until all pass or escalate.	3 / 3
Progressive Disclosure	Sections are well-organized and references to external skills (monorepo-flow.md, subagents-orchestration-guide) are clearly signaled at one level, but no local bundle files exist and navigation depends on other skills' structures.	2 / 3
	Total	9 / 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 third-person and identifies a clear fullstack orchestration niche, but it is high-level and lacks any explicit "when to use" trigger. It reads as a capability summary rather than activation guidance.

Suggestions

Append a "Use when..." clause with natural triggers, e.g. "Use when the user requests a full-stack feature spanning backend and frontend, or asks to build/ship a web feature end-to-end."

Replace jargon ("orchestrate full-cycle") with concrete user-facing verbs and terms ("build, plan, and ship full-stack features across backend and frontend").

List a couple of concrete actions to lift specificity, e.g. "...analyzes requirements, designs backend + frontend layers, plans tasks, and runs quality checks."

Dimension	Reasoning	Score
Specificity	"Orchestrate full-cycle implementation across backend and frontend layers" names the domain (fullstack/backend/frontend) and an action (orchestrate) but stays high-level rather than listing multiple concrete actions.	2 / 3
Completeness	The description states what the skill does but provides no "Use when..." clause or equivalent trigger guidance, capping completeness at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	"implementation", "backend", and "frontend" are relevant, but "orchestrate full-cycle" is jargon and the phrasing omits natural user variations like "fullstack", "build a feature", or "web app".	2 / 3
Distinctiveness Conflict Risk	"full-cycle implementation across backend and frontend" carves a recognizable fullstack niche but could still overlap with general dev-workflow or implementation 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.