dev-team

Developer team router. Toma 1 ticket de 04-tickets.yaml. Decide owner según owner_eligibility (qwen-opencode preferido para BE/FE no-agentic; Opus 4.7 obligatorio para AGENTIC). Para qwen → invoca via Bash con prompt pre-cocido. Para Opus → spawna agent builder-{be,fe,agentic}. Mantiene T-{n}-impl-log.md vivo. TDD obligatorio. Corre /test-{backend,frontend} + Playwright + agentic evals. Push commit. Update ticket state. Activa cuando user dice: '/dev-team', 'tomá ticket T-N', 'implementá T-N', 'arrancá build'.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

70%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 strongly actionable, well-sequenced orchestration skill with real validation checkpoints and feedback loops. Its weak spots are mild verbosity/redundancy and a complete absence of progressive disclosure — everything lives inline in a ~190-line SKILL.md.

Suggestions

Trim the TDD RED/GREEN/REFACTOR explanation (Claude already knows TDD) and de-duplicate the AGENTIC→Opus rule that appears in both 'Reglas hard' and 'Anti-patterns'.

Extract the Step 2A qwen prompt here-doc into a references file (e.g. references/qwen-prompt.md) and link to it, so SKILL.md stays a lean overview.

Replace or document the template placeholders ({n}, {id}, PI-N, SN, T-{n}) with a short note on how to resolve them, moving the commands closer to copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Mostly operational and dense, but includes over-explanation Claude already knows ('RED: escribí tests que fallen primero / GREEN: implementá mínimo para pasar / REFACTOR: limpiar') and redundancy between the 'Reglas hard', 'Anti-patterns', and step bodies that could be tightened.	3 / 5
Actionability	Highly concrete with executable bash (cat, opencode run, git push, realpath), YAML snippets, and an Agent() invocation, but unresolved template placeholders ({n}, {id}, PI-N, SN) keep it just short of copy-paste ready.	4 / 5
Workflow Clarity	Clear sequenced steps (Step 1 → 2A/2B/2C → 3 → 4 → 5) with an explicit validation checklist in Step 4 (acceptance criteria ✅, quality gates verde, commit SHA, push confirmado) and feedback loops ('vuelve a tests-failing', 'itera ≥5x → blocked + escala').	5 / 5
Progressive Disclosure	Well sectioned internally but entirely monolithic — no bundle files and no references to separate files, and inline content such as the ~30-line qwen prompt here-doc in Step 2A is a clear candidate for extraction into a reference file.	3 / 5
	Total	15 / 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.

A dense, well-constructed activation description: it states concrete capabilities across the whole dev pipeline and gives explicit, natural trigger phrases. Its only weakness is heavy reliance on internal jargon (owner_eligibility, builder-agentic, prompt pre-cocido), though that is not directly penalized by these dimensions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the full pipeline — 'Toma 1 ticket', 'Decide owner según owner_eligibility', 'invoca via Bash con prompt pre-cocido', 'spawna agent builder-{be,fe,agentic}', 'Corre /test-{backend,frontend} + Playwright + agentic evals', 'Push commit' — giving comprehensive, non-vague coverage.	5 / 5
Completeness	Clearly answers both 'what' (developer team router that takes a ticket, assigns owner, runs TDD/tests, pushes) and 'when' (concrete 'Activa cuando user dice' trigger clause), matching the anchor for explicit what-and-when with concrete triggers.	5 / 5
Trigger Term Quality	Explicit natural trigger phrases are given — 'Activa cuando user dice: "/dev-team", "tomá ticket T-N", "implementá T-N", "arrancá build"' — including synonym-like variations a user would naturally say.	5 / 5
Distinctiveness Conflict Risk	The niche is highly specific — a ticket-to-model router keyed on owner_eligibility with the distinctive '/dev-team' / 'tomá ticket T-N' triggers — so overlap with other skills is minimal.	5 / 5
	Total	20 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: alpacapurpura/ap_sales_agent
Path: .claude/skills/dev-team/SKILL.md
Commit: d31f7bc

Reviewed: ~18 hours ago

Table of Contents

Discovery Implementation Validation

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.