CtrlK
BlogDocsLog inGet started
Tessl Logo

sales-agent-expert

Senior + arquitecto + CTO del módulo sales_agent post redesign 2026-04. Carga §3 protected surfaces, anti-patterns, decisiones cross-fase, checklist pre-commit. NO carga code vivo (paths/LOC/tests cambian). Use cuando user pida cambio/feature/bug en sales_agent: voz de marca, scheduler/payment tools, observabilidad, callback handler, prompt cache, channel registry, semantic router, closer studio, follow_up engine, eval loop, costo agentes. Triggers: 'modifica sales_agent', 'bug en sales_agent', 'agregar tool al agente', 'agente no cierra', 'suena robótico', 'voz de marca', 'agregar canal sales', 'modificar prompt del specialist', 'closer studio', 'follow-up no dispara', 'el agente repite preguntas', 'PII en trazas', 'costo Kimi', 'DeepSeek alias', 'tier pricing 200k', 'eval goldens'.

74

Quality

91%

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

82%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 dense, senior-grade reference with strong sequencing, explicit validation checkpoints and gating, and concrete commands/code. It is mostly lean and well-structured, with only minor verbosity and a few stub code examples that could be tightened.

Suggestions

Tighten stub code snippets (e.g. `estimated_cost_usd=Decimal("...")`) with a concrete illustrative value or a comment noting callers fill the value, to make examples more copy-paste ready.

The Glossary explains some concepts (turn, ratchet, dual-write) that a senior already knows; consider trimming or moving project-specific terms only, to reduce token load.

Some inline detail (e.g. plan-defaults table, MV stale soft-cap) could be pushed into a references file so SKILL.md reads more as an overview pointing to one-level-deep material.

DimensionReasoningScore

Conciseness

Dense and token-efficient with heavy use of tables and bullets, assuming senior competence; a few glossary terms (turn, ratchet, dual-write, Stranger Fig) and some repeated rationale slightly pad the body but remain mostly earned.

4 / 5

Actionability

Concrete executable grep/find commands, real code snippets for BudgetGuard.check and OutboundRateLimiter.check, and exact table/column references; minor gaps are stubbed examples (Decimal('...'), '...') and pointers to external CONTRACT.md rather than fully self-contained guidance.

4 / 5

Workflow Clarity

Sequenced strict ordering ('Antes de codear (orden estricto)'), explicit §3 gating with 'PARAR, preguntar al usuario', an anti-duplication decision tree (EXTEND/LIFT-TO-SHARED/NEW), a 10-item pre-commit checklist, and RED->GREEN test feedback loops for risky/batch operations.

5 / 5

Progressive Disclosure

Well-organized sections with one-level-deep references to a real references/ bundle (4 files present) and clearly signaled Pointers to external docs; the body is somewhat dense with inline detail that could partly live in references, keeping it just short of a fully clean overview-to-detail split.

4 / 5

Total

17

/

20

Passed

Description

100%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 highly specific, comprehensive, and tightly scoped to the sales_agent module, with explicit 'Use cuando' guidance and an extensive natural-language trigger list. It cleanly answers both what the skill does and when to invoke it.

DimensionReasoningScore

Specificity

Names the domain (sales_agent module post redesign) and lists many concrete actions/surfaces: scheduler/payment tools, observability, callback handler, prompt cache, channel registry, semantic router, closer studio, follow_up engine, eval loop, costo agentes — comprehensive coverage.

5 / 5

Completeness

Clearly answers 'what' (senior + arquitecto + CTO role, loads §3 protected surfaces, anti-patterns, cross-phase decisions, pre-commit checklist; does not load live code) AND 'when' via an explicit 'Use cuando' clause plus enumerated 'Triggers' with concrete trigger phrases.

5 / 5

Trigger Term Quality

Provides a long, explicit 'Triggers:' list of natural phrases users would say ('modifica sales_agent', 'agente no cierra', 'suena robotico', 'PII en trazas', 'costo Kimi'), covering many synonyms and concrete symptom phrasings.

5 / 5

Distinctiveness Conflict Risk

Scoped tightly to the sales_agent module post-redesign with module-specific triggers and surfaces, making it clearly distinguishable from copilot or generic skills and unlikely to fire for the wrong skill.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.