CtrlK
BlogDocsLog inGet started
Tessl Logo

recipe-front-build

Execute materialized frontend task files in autonomous execution mode

56

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/recipe-front-build/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

73%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 dense but well-sequenced orchestration recipe with concrete agent names, fields, and status branches plus strong validation feedback loops; its main weaknesses are repeated gating/definition language and a single-file structure with no internal reference split.

Suggestions

Consolidate the repeated restricted-pattern definition of the Consumed Task Set into a single statement referenced later, and trim redundant MANDATORY/CRITICAL emphasis.

Extract the large Task Execution Cycle branch table and Post-Implementation Review routing into a one-level-deep reference file to improve progressive disclosure.

Add a brief top-of-file overview or flow diagram summarizing the phase order so the high-level sequence is scannable before the detailed gates.

DimensionReasoningScore

Conciseness

The body is mostly directive and avoids over-explaining concepts Claude knows, but repeats the restricted Consumed Task Set pattern and layers redundant MANDATORY/CRITICAL gating language that could be tightened.

3 / 5

Actionability

It names concrete subagent_types (e.g., "dev-workflows-frontend:task-executor-frontend"), exact fields (diffBase, task_file, qualityCommand, mutationEvidence), and discrete status values to branch on, giving mostly executable guidance with minor prompt-text gaps.

4 / 5

Workflow Clarity

The phases are clearly sequenced (Prerequisites → Materialization → Checklist → 4-step Execution Cycle → Post-Implementation Review → Final Cleanup → Report) with explicit validation checkpoints, approval gates, and feedback loops (needs_revision/stub_detected → return to step 1).

5 / 5

Progressive Disclosure

Content is well-organized under clear section headers and cross-skill references (subagents-orchestration-guide, review-resolution.md) are signaled, but the body is a single dense orchestration file with no own-bundle split, leaving minor organization gaps.

4 / 5

Total

16

/

20

Passed

Description

53%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 the skill's purpose concisely and is reasonably distinct, but it omits any explicit "when to use" trigger guidance and offers only a single action, limiting completeness and trigger coverage.

Suggestions

Add an explicit "Use when..." clause naming the trigger scenarios (e.g., when the user supplies a frontend Work Plan or task files for batch autonomous execution).

Broaden trigger terms with natural synonyms (e.g., "run frontend tasks", "batch-execute frontend tasks", "front-build recipe") beyond the jargon "materialized".

List 1-2 additional concrete actions (e.g., materialize/decompose tasks, verify, commit, clean up) to raise specificity beyond a single action.

DimensionReasoningScore

Specificity

"Execute materialized frontend task files" names the domain (frontend task files) and a concrete action (execute) with a mode qualifier, but lists only one action and is not comprehensive.

3 / 5

Completeness

The description gives a clear "what" (execute materialized frontend task files in autonomous execution mode) but has no "Use when..." clause or equivalent explicit "when" guidance, which caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

"frontend task files" and "autonomous execution" are relevant keywords a user of this system might say, but common variations/synonyms and natural phrasings are missing and "materialized" is jargon.

3 / 5

Distinctiveness Conflict Risk

"Execute materialized frontend task files in autonomous execution mode" carves a fairly distinct niche with specific triggers; only minor overlap risk with a closely related backend/fullstack build recipe.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
shinpr/claude-code-workflows
Reviewed

Table of Contents

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.