CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

review-report

Resumir `.bob/report.md` no corpo do PR. Use ao escrever ou atualizar um pull request depois de `bob check`.

Quality

85%

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.

A highly actionable, well-sequenced skill: the PR-body template and per-step completion criteria leave no ambiguity about what to execute. The main cost is duplicated exit-4/invalid-usage text that could be consolidated, and minor organization looseness in the exit-code catalog placement.

Suggestions

Consolidate the exit-4/invalid-usage detection criteria into one place: they currently appear both in the CLI section and again almost verbatim in step 1 of Passos.

Delete the verbatim duplicate of the exit-4 meaning ("O `4` é erro de configuração ou ferramenta ausente..." restates the list entry two lines above).

Trim the inline exit-code catalog to the codes the skill acts on (0 and 4) and keep the full catalog in the already-referenced `docs/exit-codes.md`.

DimensionReasoningScore

Conciseness

The body is dense and operational with no concept-explainer padding, but the exit-4/invalid-usage detection criteria are stated twice nearly verbatim ("`4` erro de configuração ou ferramenta ausente" followed by "O `4` é erro de configuração ou ferramenta ausente...", and the "stderr começa com `usage: bob`... Não é o exit `2`" clause repeated in step 1). This matches 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than level 2, since the redundancy is localized and the rest earns its tokens.

3 / 5

Actionability

The skill provides a copy-paste-ready PR body template, exact commands (`bob check --format both`), concrete exit-code meanings, file paths, and explicit per-section placement rules, fully covering the common case. It matches 'fully executable; copy-paste ready code or commands'.

5 / 5

Workflow Clarity

Four clearly sequenced steps, each with an explicit 'Feito quando...' completion checkpoint, plus an error-recovery branch (exit-4 invalid usage detected via stderr heuristics redirects to the `bob-check` skill and forbids re-running the same argv). This matches the top anchor: clear sequence, explicit validation, feedback loop for error recovery.

5 / 5

Progressive Disclosure

The single-file skill is well-sectioned (Quando, Interface da CLI, Passos, Formato do relatório, Molde do corpo do PR) with clearly signaled external references ("Fonte do formato: `docs/SPEC.md`", "Catálogo em `docs/exit-codes.md#exit-4`"). It is not level 5 because the inline exit-code catalog partially duplicates the referenced `docs/exit-codes.md`, and stray floating lines ("⏭️ permanece ⏭️, com o motivo") sit outside any section.

4 / 5

Total

17

/

20

Passed

Description

82%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 concise, well-targeted description that clearly states both what it does and when to use it, anchored to tool-specific triggers. Its only weakness is that it names a single capability (summarizing the report) rather than listing the fuller set of actions the skill performs.

Suggestions

List one or two more concrete capabilities in the description (e.g., structuring the body as Summary/Evidence/Merge Danger, or comparing the last failed vs passing `bob check` run) rather than only 'Resumir'.

Add natural trigger synonyms such as 'abrir/criar pull request' or 'descrição do PR' to broaden the natural-phrases a user might say.

Optionally mention the before/after evidence comparison in the 'what' clause so the scope of the summary work is clearer at a glance.

DimensionReasoningScore

Specificity

"Resumir `.bob/report.md` no corpo do PR" names the domain and one concrete action with a specific file and destination, matching the 'names domain and 1-2 concrete actions' anchor. It does not list several specific actions, so it falls short of level 4, while the single action is far too concrete for level 2.

3 / 5

Completeness

It explicitly answers what ("Resumir `.bob/report.md` no corpo do PR") and when ("Use ao escrever ou atualizar um pull request depois de `bob check`") with concrete trigger phrases, matching the top anchor. The 'when' clause is already specific and conditional, so level 4's 'could be more explicit' does not apply.

5 / 5

Trigger Term Quality

Natural trigger phrases like "pull request", "PR", "escrever ou atualizar" are present and map well to what a user would say. Common synonyms (e.g., "abrir/criar pull request", "descrição do PR") are missing, keeping it just below the comprehensive level 5.

4 / 5

Distinctiveness Conflict Risk

Triggers are anchored to tool-specific artifacts (`.bob/report.md`, `bob check`, PR body), giving the skill a clear niche with minimal overlap risk against generic PR-writing or review skills.

5 / 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

fazedordecodigo/bob

Path

skills/review-report/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.