recipe-fullstack-build

Execute materialized fullstack task files with layer-aware agent routing

Quality

51%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

66%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 clear, well-sequenced orchestration recipe with strong validation checkpoints and concrete agent-routing instructions. Its main weaknesses are progressive disclosure (monolithic inline content, no local bundle to offload detail) and moderate conciseness redundancy.

Suggestions

Move the routing tables, decision-flow state machine, and post-implementation verification detail into a local references/ file and keep SKILL.md as a concise overview that points to it.

De-duplicate the routing table (it appears in both Execution Protocol and Task Execution Cycle) and drop redundant MANDATORY framing.

Add explicit user-facing trigger guidance near the top of the body so the skill is invokable, since disable-model-invocation is set.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly action-oriented but repeats MANDATORY emphases and re-states routing rules across multiple sections (e.g., the Agent Routing Table appears twice), adding tokens that could be trimmed.	3 / 5
Actionability	It provides concrete, executable guidance: subagent_type values, exact task filename patterns, a 4-step cycle, and a full Completion Report Contract, with only minor gaps (e.g., no literal copy-paste command snippets).	4 / 5
Workflow Clarity	It sequences a clear multi-phase pipeline (prerequisites, materialization, execution cycle, post-implementation verification, cleanup, report) with explicit validation/feedback checkpoints (branch on executor result, quality-fix before commit, Review Resolution convergence) and a pre-execution checklist.	5 / 5
Progressive Disclosure	This is a ~160-line monolithic SKILL.md that inlines substantial procedural detail; its only references (monorepo-flow.md, review-resolution.md) live in the separate subagents-orchestration-guide skill, not in a local bundle, and no references/scripts/assets bundle exists here to split content into.	2 / 5
	Total	14 / 20 Passed

Description

37%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 states a what but omits any when/trigger guidance and leans on internal jargon rather than natural user language. It is reasonably distinct from other skills but not yet actionable as a trigger.

Suggestions

Add an explicit "Use when..." clause naming natural user phrases (e.g., when the user asks to execute or build a fullstack plan's task files).

Replace internal terms ("materialized," "layer-aware agent routing") with user-facing language and concrete actions like "run backend and frontend task files, route them to the right executors."

Mention the triggering artifacts (e.g., docs/plans task files, fullstack work plans) so users can recognize the skill.

Dimension	Reasoning	Score
Specificity	"Execute materialized fullstack task files with layer-aware agent routing" names the domain (fullstack task files) and one concrete action (execute) plus a routing mechanism, but the action is generic and not comprehensive like the 4-5 anchors.	3 / 5
Completeness	There is a vague "what" but no "Use when..." clause or any trigger guidance, which the guidelines cap at 3; combined with the vagueness it sits below the midpoint at 2.	2 / 5
Trigger Term Quality	Terms like "fullstack task files," "layer-aware," and "agent routing" are technical/internal jargon rather than phrases a user would naturally say; no natural user-facing keywords are present.	2 / 5
Distinctiveness Conflict Risk	"recipe-fullstack-build" with "layer-aware agent routing" is a fairly specific niche with minimal overlap risk against other skills, just slightly broad on the word "execute".	4 / 5
	Total	11 / 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-build/SKILL.md
Commit: 83cf695

Reviewed: about 22 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.