recipe-front-build

Execute frontend implementation in autonomous execution mode

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.

This is a tightly written orchestration recipe with excellent actionability and a rigorously sequenced, validated workflow including feedback loops for a batch operation. Its main weakness is structural: the procedure is monolithic and repeats its file-exclusion rules across several sections rather than splitting or factoring them out.

Suggestions

Define the task-file exclusion pattern once in a labeled block and reference it from Work Plan Resolution, Consumed Task Set, verify-generation, and Final Cleanup to remove the repeated pattern lists.

Extract the long per-phase decision and verification detail into a bundled reference file (e.g. references/verification.md) and link to it one level deep, keeping SKILL.md as an overview.

Move the literal subagent prompt scaffolding (scope-boundary block, decomposer prompt) into a references snippet so the main body stays a lean control-flow overview.

Dimension	Reasoning	Score
Conciseness	The body is dense procedural guidance without concept fluff, but the task-file exclusion pattern list is repeated verbatim across Work Plan Resolution, Consumed Task Set, Task Decomposition verify, and Final Cleanup, so it could be tightened by defining once and referencing it.	2 / 3
Actionability	It supplies exact subagent_type values (e.g. 'dev-workflows-frontend:task-executor-frontend'), specific response fields to branch on, concrete git commands like 'git diff --name-only main...HEAD', and precise file patterns — copy-paste ready orchestration guidance.	3 / 3
Workflow Clarity	The mandatory 4-step cycle is explicitly sequenced with validation checkpoints (quality-fixer approval before every commit), feedback loops (return to step 2 on stub_detected/needs_revision, re-run only failed verifiers), escalation branches, and a pre-execution checklist for a batch/destructive operation.	3 / 3
Progressive Disclosure	Sections are well-organized with headers, tables, and checklists, but the full detailed procedure is inline and monolithic with no bundle files (references/scripts/assets absent); detail is offloaded only to external skills, fitting 'some structure but content that should be separate 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 third-person and names the frontend domain, but it is a single bare clause with no trigger guidance and leans on internal jargon ('autonomous execution mode'). It answers 'what' but not 'when', landing at the mid-level across all dimensions.

Suggestions

Add a 'Use when ...' clause stating the trigger conditions (e.g., when the user provides a frontend work plan to execute autonomously).

Replace or demote 'autonomous execution mode' with natural user-facing terms like 'run frontend tasks unattended from a work plan'.

Enumerate concrete actions (e.g., decompose a plan, execute task cycles, run quality checks, commit, verify) to lift specificity above a single broad verb.

Dimension	Reasoning	Score
Specificity	The phrase 'Execute frontend implementation' names a domain and an action, but offers only one broad action rather than multiple specific concrete actions, matching the 'names domain and some actions, but not comprehensive' anchor.	2 / 3
Completeness	It states what the skill does but provides no 'when to use it' trigger; per the guidelines a missing 'Use when...' clause caps completeness at 2.	2 / 3
Trigger Term Quality	'frontend' and 'implementation' are natural terms, but 'autonomous execution mode' is internal jargon and common variations are absent, fitting 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	'frontend implementation' carves out a niche but could still overlap with other frontend recipe skills and lacks distinct triggers, matching 'somewhat specific but could still overlap'.	2 / 3
	Total	8 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.