CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

postman-execution

Comandos e automação para executar operações Postman (conversão OpenAPI, execução de testes, geração de relatórios).

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/documentation/postman-execution/SKILL.md
SKILL.md
Quality
Evals
Security

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.

The body delivers fully executable make-based commands, a validated 5-step workflow with error-feedback loops, and concrete error handling — strong on actionability and workflow. It is held back by triple repetition of each command across the Exemplo and scenario sections and by dead local references in a single 290-line file with no bundle to offload detail to.

Suggestions

Collapse the "Exemplos de Uso pelos Agentes" scenarios into the existing per-command "Exemplo" blocks (or a single short examples file) — each make command currently appears three times, which is the main conciseness drag.

Remove or fix the dead local references (`skills/documentation/postman/SKILL.md`, `core/templates/postman-collection/`) — they point to paths that do not exist in this bundle and mislead navigation.

Add the direct newman/openapi-to-postmanv2 CLI invocations as fallbacks for projects without the Makefile targets, closing the gap between copy-paste make commands and actually executable guidance.

DimensionReasoningScore

Conciseness

The body is mostly task-relevant with no concept explanations, but each make command is repeated three times — in the section's "Comando" line, the "Exemplo" block, and again in "Exemplos de Uso" scenarios with mock outputs — and the "Checklist de Execução" restates "Regras de Execução" almost verbatim. Not 2 because nothing explains what Claude already knows; the padding is duplication rather than teaching.

3 / 5

Actionability

Commands like `make postman-test COLLECTION=postman/api.json ENV=postman/prod.json` are concrete and copy-paste ready, with defaults, prerequisites, and error-handling actions. Not 5 because the underlying `newman` and `openapi-to-postmanv2` CLI invocations are never shown, so the skill fails to instruct when the expected Makefile targets are absent.

4 / 5

Workflow Clarity

The "Workflow recomendado" gives a 5-step sequence with an explicit validation checkpoint ("3. Validar collection → make postman-validate"), test execution reports exit codes ("0 = sucesso, != 0 = falha"), and "Tratamento de Erros" provides feedback loops (analyze report → identify failures → fix) plus a pre-execution checklist. This matches the anchor for clear sequence with explicit validation, feedback loops, and checklists.

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), yet the single file runs ~290 lines with error-handling guides and three mock-output scenario walkthroughs inlined that belong in an examples/reference file. The "Referências" section points to local paths (`skills/documentation/postman/SKILL.md`, `core/templates/postman-collection/`) that do not exist in this bundle, alongside the two real external GitHub links. Not 4 because the dead local references and unsplit inlined content are more than minor organization gaps.

3 / 5

Total

15

/

20

Passed

Description

58%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 states concrete, domain-specific actions in third person, but omits any "when to use" guidance and misses natural trigger terms like "newman", "swagger", and "collection". It is distinct enough not to misfire, yet incomplete as a trigger surface.

Suggestions

Append a "Use when" clause, e.g. "Use quando o usuário pedir para converter OpenAPI/Swagger em collection Postman, rodar testes com Newman, ou gerar relatórios de testes" — this lifts completeness from 3 to 5.

Include the natural trigger words users actually say — "newman", "swagger", "collection", "API tests" — directly in the description text rather than relying on the separate triggers field.

Mention the validation and collection-update operations ("validar collection", "atualizar collection") so the description covers all four capabilities the body documents.

DimensionReasoningScore

Specificity

"conversão OpenAPI, execução de testes, geração de relatórios" lists three concrete actions in a specific domain. Below 5 because the skill's validation and collection-update operations are absent; above 3 because it names multiple actions, not just 1-2.

4 / 5

Completeness

The "what" is clear (convert, test, report), but there is no "Use when..." clause or equivalent explicit trigger guidance — per guidelines this caps completeness at 3. Not 2 because the "what" half is concrete and multi-part.

3 / 5

Trigger Term Quality

Relevant keywords like "Postman" and "OpenAPI" are present, but common variations users would naturally say — "newman", "swagger", "collection", "API tests" — are missing from the description itself. Not 4 because the gap includes the primary tool (newman) and common synonyms, not just a few terms.

3 / 5

Distinctiveness Conflict Risk

"executar operações Postman" carves a clear niche with Postman/OpenAPI-specific triggers, so conflict risk with unrelated skills is low. Not 5 because "conversão OpenAPI" could plausibly match generic OpenAPI-tooling requests that are not Postman-related.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

fernandezbaptiste/cursor-multiagent-system

Path

skills/documentation/postman-execution/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.