CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

doubt-driven-review

Revisa afirmacoes e decisoes com duvida sistematica e evidencias. Trigger em: "tem certeza disso", "migration nao vai quebrar", "duvida isso", "decisao de arquitetura antes de eu commitar", "revisa antes de eu commitar", "revisa isso adversarialmente", "isso ta certo mesmo", "questiona essa suposicao", "declarar isso seguro", "refuta essa claim", "decisao", "adversarial review", "doubt driven", "segunda opiniao antes de seguir", "acho que ta certo mas".

Quality

89%

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

88%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.

An exceptionally actionable, well-sequenced behavioral skill: the adversarial prompt template, classification taxonomy, and stop conditions are all copy-paste concrete. The only costs are mild repetition of the skill-11 distinction and a long single-file layout that could offload the rationalizations/red-flags tables to a reference file.

Suggestions

Consolidate the skill-11 distinction into one place (the 'Interação com Outras Skills' section) and drop the repetitions in the intro, the rationalizations table, and red flags to save tokens.

Move the 'Racionalizações Comuns' table and 'Red Flags' list into a references/ file (e.g., references/anti-patterns.md) linked from the body, keeping SKILL.md as a tighter overview.

DimensionReasoningScore

Conciseness

The body is dense and process-specific with almost no explanation of concepts Claude already knows, but there is repeated content: the distinction from skill 11 appears in the intro ('Isso não é a skill 11'), the rationalizations table ('Faço dúvida no final com skill 11'), red flags ('Duvidar só depois de commitar — isso é skill 11'), and interactions ('Skill 11 é veredito pós-hoc'). This fits 'Efficient; minor instances of over-explanation that could be trimmed'; not a 5 because that repetition and some restated rationale sentences ('A skill se aplica a decisão não-trivial, não cada tecla' appears twice) could be consolidated.

4 / 5

Actionability

Fully executable for an instruction-only skill: a copy-paste-ready adversarial reviewer prompt ('Revisão adversarial. Encontre o que está errado neste artefato...'), a copyable CLAIM template, a copyable 5-step checklist, the exact dispatch mechanism ('Agent tool com subagent_type: "dev-team-kit-fv:code-reviewer"'), a concrete 4-class finding taxonomy with precedence order, and numeric stopping conditions (3 ciclos). Nothing remains abstract.

5 / 5

Workflow Clarity

The 5-step process (CLAIM, EXTRACT, DUVIDA, RECONCILIA, PARA) is clearly sequenced with explicit validation checkpoints and feedback loops: findings must be re-read against the artifact text before classification, 'Válido + acionável' triggers a reloop, 'Contrato mal-lido' triggers contract correction and reclassification, and the PARA step defines explicit stop conditions plus user escalation. This matches the top anchor including error-recovery loops and a checklist.

5 / 5

Progressive Disclosure

The single file is well-organized with clear section headers (Quando Usar, Quando Nao Usar, O Processo, Racionalizações, Red Flags, Interação com Outras Skills, Evidencia de Conclusao) and no nested-reference anti-patterns. However, at ~170 lines it exceeds the under-50-line exception for a solo-file 5, and references like 'policies/skills-vs-agents.md' point outside the bundle with no references/ directory present, so it lands on 'Good structure; most content is appropriately placed; minor organization gaps'.

4 / 5

Total

18

/

20

Passed

Description

86%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 with excellent, natural trigger-term coverage and an explicit use-when clause. Its only real weakness is that the capability statement is a single abstract sentence rather than a list of the concrete actions the skill performs.

Suggestions

Expand the opening sentence into 2-3 concrete actions, e.g. 'Nomeia a decisao como CLAIM, despacha um revisor de contexto fresco com prompt adversarial, e classifica os findings (acionavel / trade-off / ruído) antes de seguir.'

Drop or qualify the bare trigger 'decisao' — it is generic enough to fire on nearly any decision-related message; anchor triggers on the doubt/verification phrasings instead.

DimensionReasoningScore

Specificity

The what-clause 'Revisa afirmacoes e decisoes com duvida sistematica e evidencias' names the domain (claims/decisions under doubt) but offers only one generic action verb ('Revisa') — matching 'Names domain and 1-2 concrete actions, but not comprehensive' like 'Processes PDF files and extracts content'. Not a 4 because it does not list several specific actions (e.g., naming the claim, dispatching a fresh-context reviewer, classifying findings), and not a 2 because the domain framing is concrete rather than minimal.

3 / 5

Completeness

Explicitly answers both questions: what ('Revisa afirmacoes e decisoes com duvida sistematica e evidencias') and when ('Trigger em: ...' followed by concrete trigger phrases). The 'when' is maximally explicit with concrete phrases, so the anchor-4 condition ('when' could be more explicit or specific) does not apply; the 'what' is clear and direct, fitting the anchor-5 example pattern.

5 / 5

Trigger Term Quality

Fifteen natural trigger phrases users would actually say, with synonym coverage in both Portuguese and English: 'tem certeza disso', 'migration nao vai quebrar', 'acho que ta certo mas', 'segunda opiniao antes de seguir', 'adversarial review', 'doubt driven', 'refuta essa claim'. This comprehensively covers natural terms and their variations, matching the top anchor; a 4 would require noticeable missing natural phrasings, and none are apparent.

5 / 5

Distinctiveness Conflict Risk

The doubt/refute framing ('duvida sistematica', 'refuta essa claim', 'questiona essa suposicao') carves a mostly distinct niche with minimal conflict risk, fitting 'Mostly distinct; minor overlap risk'. Not a 5 because the bare trigger 'decisao' is very broad and review-flavored triggers ('revisa antes de eu commitar') could overlap with a general code-review skill in the same kit; not a 3 because the majority of triggers are unique to adversarial doubt.

4 / 5

Total

17

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

felvieira/claude-skills-fv

Path

skills/53-doubt-driven-review/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.