CtrlK
BlogDocsLog inGet started
Tessl Logo

ux-flow-architect

Interactive cross-feature navigation architect for Nicolify. Audits all routes and sidebar entries, maps user journeys across studios, detects orphaned features and dead-end flows, proposes navigation improvements with ASCII diagrams, generates clickable multi-page HTML prototypes on localhost:8888, and outputs FLOW-SPEC.md plus per-screen UI-SPEC updates for implementation agents. Use when the user asks about navigation coherence, user flows, journey mapping, orphaned features, dead-end screens, sidebar reorganization, cross-studio navigation, or feature discoverability. Triggers: 'flujo de usuario', 'navegación', 'journey', 'user flow', 'sidebar', 'rutas huérfanas', 'orphaned routes', 'dead end', 'flow audit', 'navigation audit', 'ux-flow', 'flow architect', 'cómo llega el usuario', 'discoverability', 'no encuentro', 'dónde está', 'reorganizar navegación', 'cross-feature flow', 'audita la navegación', 'mapa de rutas', 'flujos de la app'.

71

Quality

88%

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

81%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 body is a well-structured, actionable workflow: sequenced phases with gate checkpoints, concrete tool calls and file paths, and bulk detail delegated to real reference files. It loses points mainly on conciseness (length plus a deprecated-skill banner) and minor progressive-disclosure gaps from cross-skill references not present in the bundle.

Suggestions

Collapse the four deprecation banner lines and redundant 'deprecated path' reminders into a single concise note to reclaim tokens.

Either bundle the two ux-disruptivo reference files this skill depends on, or inline the small amount of their content actually used so no reference points outside the bundle.

Tighten the role preamble and Common Mistakes table to the few items that genuinely steer behavior away from common errors.

DimensionReasoningScore

Conciseness

The body largely assumes Claude's competence (no 'what is a sidebar' padding) and delegates bulk detail to reference files, but at ~530 lines it carries repeated deprecation banners, a prose role preamble, and explanatory tables that could be trimmed — efficient with minor instances of over-explanation, fitting anchor 4 rather than the lean anchor 5.

4 / 5

Actionability

Provides concrete, executable guidance — exact Glob/Grep/Read tool calls with real glob patterns, exact file paths (app-sidebar.tsx, globals.css), and runnable bash (mkdir -p, python3 -m http.server 8888) — with only minor gaps where proposal/iteration steps are instructional rather than coded, matching anchor 4 (mostly executable, minor gaps).

4 / 5

Workflow Clarity

Six clearly sequenced phases each end in an explicit 'Gate' validation checkpoint, a mode-detection table routes to the right phases, and Edge Cases/Common Mistakes tables give error-recovery guidance; operations are read-only audit + artifact writing + HTML serving (not destructive/batch), so the ≤3 cap does not apply and the explicit checkpointed sequence matches anchor 5.

5 / 5

Progressive Disclosure

SKILL.md acts as an overview with bulk detail offloaded to four real, one-level-deep reference files loaded per-phase via explicit Read calls, but two referenced paths (ux-disruptivo/references/ascii-mockup-guide.md, ui-spec-template.md) are cross-skill and absent from this bundle and the deprecated banner adds navigational noise, leaving it at anchor 4 rather than the cleanly organized anchor 5.

4 / 5

Total

17

/

20

Passed

Description

96%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 is strong: third-person, concrete, comprehensive in both capabilities and natural trigger terms (bilingual), and explicitly pairs 'what' with 'when'. The only weakness is distinctiveness, since the skill is deprecated in favor of /ux-ui and shares a UX/navigation space with several sibling skills.

Suggestions

If this skill is truly deprecated, narrow its triggers to legacy-context phrases to reduce overlap with the replacement /ux-ui skill.

Clarify the boundary against ux-disruptivo and nicolify-ux-designer inside the description so it is distinguishable on triggers alone, not just in the body.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Audits all routes and sidebar entries', 'maps user journeys across studios', 'detects orphaned features and dead-end flows', 'proposes navigation improvements with ASCII diagrams', 'generates clickable multi-page HTML prototypes on localhost:8888', 'outputs FLOW-SPEC.md plus per-screen UI-SPEC updates' — comprehensive coverage matching the anchor-5 example.

5 / 5

Completeness

Explicitly answers both 'what' (the enumerated concrete actions) and 'when' ('Use when the user asks about navigation coherence, user flows, journey mapping…') with concrete trigger phrases, exactly matching the anchor-5 example.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including the founder's Spanish phrasings ('navegación', 'no encuentro', 'dónde está', 'cómo llega el usuario'), English synonyms ('journey', 'user flow', 'sidebar', 'dead end'), and explicit 'Triggers:' list — matching the anchor-5 standard of synonyms and variations a user would actually say.

5 / 5

Distinctiveness Conflict Risk

Clear niche ('cross-feature navigation architect for Nicolify') with distinct triggers and minimal generic conflict, but the skill body itself declares deprecation/absorption into '/ux-ui' and overlaps with sibling skills (ux-disruptivo, nicolify-ux-designer), giving minor overlap risk with closely related skills rather than the clean niche of anchor 5.

4 / 5

Total

19

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (533 lines); consider splitting into references/ and linking

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

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.