recipe-fullstack-implement

Orchestrate full-cycle implementation across backend and frontend layers

Quality

46%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/recipe-fullstack-implement/SKILL.md

Quality

Content

63%Weight 40%Scale 1-5

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

The content is a tightly structured orchestration recipe with concrete agent routings, validation gates, and feedback loops, which makes it highly actionable for a complex workflow. Its main weaknesses are some repetitive emphasis padding and detailed rules inlined rather than split into local reference files.

Suggestions

Collapse repeated 'MANDATORY'/'CRITICAL' emphasis and redundant 'follow monorepo-flow.md / subagents-orchestration-guide' reminders into a single consolidated compliance statement to recover tokens.

Extract the multi-branch Task Execution Quality Cycle into a local reference file (e.g. references/task-cycle.md) and link to it from a concise summary in SKILL.md.

Surface the external-skill references (monorepo-flow.md, review-resolution.md) as a short 'Required references' list with one-line purposes so navigation is immediately clear.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and dense with concrete orchestration rules, but repeats emphasis markers ('MANDATORY', 'CRITICAL') and re-issues reminders to follow monorepo-flow.md / subagents-orchestration-guide that could be tightened.	3 / 5
Actionability	It gives concrete routings (subagent_type values), a filename-pattern routing table, specific field names (mutationEvidence, requiresTestReview), and branch dispositions; minor gaps come from deferring detail to external references.	4 / 5
Workflow Clarity	A clear numbered sequence with explicit validation checkpoints and feedback loops (stub_detected/blocked/verification_incomplete/approved branches, Review Resolution Gate) is present; some checkpoints are delegated to external references rather than stated inline.	4 / 5
Progressive Disclosure	Sections are organized and references are one level deep, but they point to other skills' references rather than local bundle files, and sizable rule blocks (the Task Execution Quality Cycle) are inlined that could live in a dedicated reference.	3 / 5
	Total	14 / 20 Passed

Description

28%Weight 40%Scale 1-5

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 a terse domain label rather than a capability statement: it gestures at fullstack orchestration but lists no concrete actions and gives no usage triggers. It is distinguishable from generic skills but risks overlap with related orchestration skills.

Suggestions

Replace generic verbs with concrete actions the skill performs, e.g. 'Analyzes requirements, generates per-layer Design Docs, plans vertical slices, and runs per-task implementation/QA cycles across backend and frontend.'

Add an explicit 'Use when...' clause with natural trigger phrases users would say, e.g. 'Use when implementing a fullstack feature that spans backend and frontend, or when the user asks to run the full implementation cycle end to end.'

Add natural synonyms/extensions (e.g. 'fullstack', 'monorepo', '.md plan files') to improve trigger matching and reduce conflict with sibling orchestration skills.

Dimension	Reasoning	Score
Specificity	Names the fullstack domain ('backend and frontend layers') but the only action verb is the generic 'Orchestrate full-cycle implementation', with no concrete actions enumerated.	2 / 5
Completeness	It states a vague 'what' (orchestrate full-cycle implementation) but provides no 'when'/'Use when...' trigger guidance at all, so it does not reach the explicit-when threshold.	2 / 5
Trigger Term Quality	Terms like 'full-cycle implementation' and 'backend and frontend' are present but read as technical phrasing rather than natural user language, and lack synonyms or file extensions users would actually say.	2 / 5
Distinctiveness Conflict Risk	The fullstack scope is somewhat specific, but 'orchestrate implementation' overlaps materially with sibling orchestration skills (e.g. subagents-orchestration-guide) and could trigger for the wrong one.	3 / 5
	Total	9 / 20 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: 2 missing	Warning

	Total	15 / 16 Passed

Repository: shinpr/claude-code-workflows
Path: skills/recipe-fullstack-implement/SKILL.md
Commit: 83cf695

Reviewed: about 23 hours 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.