CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

architect-fe

Sub-architect Frontend. Invocado por /architect orchestrator. Lee 01-spec.md + 02-design-ui.md + story YAML. Produce 03-arch-fe.md con: routes, components FSD-Lite, hooks React Query, Zod schemas, types TS, tests Vitest+Playwright, server-first boundaries. Activa cuando /architect spawna o user dice: '/architect-fe', 'arq frontend', 'diseña FE'.

68

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

A lean, highly prescriptive skill body that gives a frontend sub-architect exact commands, structure templates, and hard rules. It falls short of top marks on placeholder-laden code snippets, minor duplication between inline rules and the anti-pattern list, and a missing output-validation step.

Suggestions

Add a final validation step in the workflow (e.g. verify the generated 03-arch-fe.md covers every section of the template and passes the arch test constraints) before the hand-off in Step 3.

Deduplicate the Anti-patterns list against inline rules — keep the inline NEVERs where they are contextual and reserve the anti-patterns section for rules not already stated, or vice versa.

Complete the code templates (e.g. a real mutationFn example and a concrete grep keyword) or explicitly note that placeholders are per-module substitutions, so examples read as executable rather than pseudocode.

DimensionReasoningScore

Conciseness

The body is dense, rule-driven, and assumes Claude's competence with zero concept explanations, but the Anti-patterns section duplicates ~5 rules already stated inline (e.g. 'useEffect para data fetching', 'toLocaleDateString()', hardcoded 'USD'), which could be trimmed.

4 / 5

Actionability

Provides concrete grep/find commands with real paths, an exact FSD-Lite file tree, test file paths, telemetry event names, and the output path, but code templates contain unresolved placeholders ('mutationFn: ...', '<keyword>', '{m}') without explicitly justifying that flexibility.

4 / 5

Workflow Clarity

Clear three-step sequence (audit → design → hand off) with an explicit reuse decision checkpoint in Step 1 and an exact output destination; the gap is the absence of any validation step confirming the produced 03-arch-fe.md is complete before hand-off.

4 / 5

Progressive Disclosure

Well-organized single-file skill with clear sections and no nested or buried references, but at ~130 lines it inlines substantial detail (accessibility rules, telemetry spec, full anti-pattern catalog) that could split into bundle files, and its only external pointer is a project path rather than a clearly signaled reference.

4 / 5

Total

16

/

20

Passed

Description

92%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.

A strong description: it names the role, inputs, exact output artifact with a comprehensive list of concrete deliverables, and explicit activation triggers in third person. The only weakness is slightly narrow trigger-term coverage missing common synonyms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and outputs — 'Lee 01-spec.md + 02-design-ui.md + story YAML' and 'routes, components FSD-Lite, hooks React Query, Zod schemas, types TS, tests Vitest+Playwright, server-first boundaries' — comprehensively covering the skill's deliverables with no vague filler.

5 / 5

Completeness

Explicitly answers both 'what' ('Produce 03-arch-fe.md con: routes, components FSD-Lite, hooks React Query...') and 'when' ('Activa cuando /architect spawna o user dice: /architect-fe, arq frontend, diseña FE') with concrete trigger phrases in third-person voice.

5 / 5

Trigger Term Quality

Includes the natural trigger phrases '/architect-fe', 'arq frontend', 'diseña FE' plus orchestrator invocation, which users of this Spanish-language project would actually say; however common synonyms and variations (e.g. 'frontend architecture', 'diseño frontend') are missing.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche ('Sub-architect Frontend. Invocado por /architect orchestrator') with a distinctive slash-command trigger ('/architect-fe') unlikely to fire for any other skill.

5 / 5

Total

19

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository

alpacapurpura/ap_sales_agent

Path

.claude/skills/architect-fe/SKILL.md

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.