CtrlK
BlogDocsLog inGet started
Tessl Logo

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'.

66

Quality

80%

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

68%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.

Lean, highly actionable, and well-structured, but the workflow lacks an explicit validation/verification checkpoint before handing off the design artifact, which is the main weakness.

Suggestions

Add an explicit verification step before the Step-3 handoff, e.g. 'Validate 03-arch-fe.md against story acceptance criteria and the 03-arch-template checklist; only hand off when all sections are covered.'

De-duplicate directives that appear in both Step 2 and Anti-patterns (e.g. NEVER useEffect, server/client boundary) — keep the rule in one place and cross-reference it to trim tokens.

Replace a few template placeholders with one concrete worked example (a real feature module name) so the FSD-Lite scaffold and hooks are copy-paste ready.

DimensionReasoningScore

Conciseness

The body is terse and directive (tables, code blocks, anti-pattern list) with no concept padding, but minor redundancy such as "NEVER useEffect" appearing in both Step 2 and Anti-patterns could be trimmed.

4 / 5

Actionability

It gives concrete `grep`/`find` commands, a route table, a file-tree scaffold, and executable `useMutation`/Zod snippets, though template placeholders like `{m}` and `{X}` leave minor gaps.

4 / 5

Workflow Clarity

Three sequenced steps with a Step-1 reuse gate ("Si pattern existe... reutilizar") and a HARD-GATE skill-load check are present, but there is no explicit verification that the output artifact is complete before the Step-3 handoff.

3 / 5

Progressive Disclosure

Well-organized single-file sections (Skills cargados, Workflow, Anti-patterns, Output format) with a clearly signaled external template path; no bundle files exist to navigate, so structure alone carries it just shy of ideal.

4 / 5

Total

15

/

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: concrete actions, explicit activation triggers, and a clear niche. The only weak spot is trigger-term breadth, which is Spanish-only and command-oriented rather than covering natural phrasings.

DimensionReasoningScore

Specificity

"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" lists multiple concrete actions with comprehensive coverage of the skill's output.

5 / 5

Completeness

It explicitly answers "what" ("Lee... Produce 03-arch-fe.md con...") and "when" ("Activa cuando /architect spawna o user dice:...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

"'/architect-fe', 'arq frontend', 'diseña FE'" cover the slash command plus Spanish synonyms a user might say, but the set is narrow and technical, missing common English/natural variations.

4 / 5

Distinctiveness Conflict Risk

The frontend sub-architect niche with distinct command triggers ("/architect-fe", "arq frontend") is clearly separated from sibling architect skills, giving minimal conflict risk.

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.

Validation15 / 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
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.