test-engineer
Skill3 starsChanged 43 days agoMITView on GitHub
Reviewer de testes do CHECK: aplica testing-patterns.md sobre a suite da thread, confere que a suite verde foi ganha e nao afrouxada, e reporta cobertura com origem declarada.
22 other projects use a version of this.
Adopted by
Most recently taken up by
- bentoms-dev/skillstheir own version, first seen Nov 8, 2026
- raphaeltm/simple-agent-managertheir own version, first seen Nov 7, 2026
- Vinix24/vnx-orchestrationtheir own version, first seen Nov 6, 2026
- fhgomes/my-awesome-agents-skillstheir own version, first seen Oct 13, 2026
- 0King0P/Claude-Skillstheir own version, first seen Oct 13, 2026
- alphazede/bearing-litetheir own version, first seen Oct 8, 2026
Used with
Projects with it also use system-architect, documentation-writer and 1 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
nahisahoSkillsystem-architect
Copilot agent that assists with architecture design, C4 model diagrams, ADR creation, and tradeoff analysis
Also in 4 projects that use this
GitHubSkilldocumentation-writer
Diátaxis Documentation Expert. An expert technical writer specializing in creating high-quality software documentation, guided by the principles and structure of the Diátaxis technical documentation authoring framework.
Also in 4 projects that use this
JeffallanSkillsecurity-reviewer
Identifies security vulnerabilities, generates structured audit reports with severity ratings, and provides actionable remediation guidance. Use when conducting security audits, reviewing code for vulnerabilities, or analyzing infrastructure security. Invoke for SAST scans, penetration testing, DevSecOps practices, cloud security reviews, dependency audits, secrets scanning, or compliance checks. Produces vulnerability reports, prioritized recommendations, and compliance checklists.
Also in 3 projects that use this
Other versions22 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 22
- nahisaho/MUSUBI★ 74same name
- raphaeltm/simple-agent-manager★ 69same name
- Vinix24/vnx-orchestration★ 63same name
- fhgomes/my-awesome-agents-skills★ 5same name
- LeilaoMi/operit-coding-skills★ 4same name
- alphazede/bearing-lite★ 3same name
- Aizaz-Noor/Agent-Startup-Skills★ 2same name
- batterfried-philosophy172/Agent-Startup-Skills★ 2same name
- JohnJBoren/claude-skills-ecosystem★ 2same name
- Recusive/Skills★ 2same name
12 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- onboardingSkill
- orchestration-experience-pt-brSkill
- orchestration-experienceSkill
- orkastery-bootstrapSkill
- thread-stateSkill
- decision-triageSkill
- narrative-guardianSkill
- roadmap-keeperSkill
- scope-check-capability-mapSkill
- thread-tracingSkill
- check-qualitySkill
- goal-definitionSkill
- go-implementationSkill
- master-metricsSkill
- plan-specificationSkill
- security-remediationSkill
- ship-releaseSkill
- code-reviewerSkill
- security-auditorSkill
- web-performance-auditorSkill
The file
Files
Test Engineer
O que esta skill e
Um roteador fino que aplica testing-patterns.md a suite da thread. Ele nao escreve o teste que falta: ele mostra qual falta e por que, e isso vira tarefa de GO. Suite verde precisa ser ganha, nao declarada.
Como rotear
ork verify <thread> --baseline # gravada ANTES do GO
ork verify <thread> # reexecucao no HEAD real, comparada com a baseline
git diff <base>...HEAD -- '*test*' # o que aconteceu com os testes no caminhoEscopo e conduta
- Comparar contra a baseline. Sem baseline, falha nao distingue regressao de divida pre-existente, e o relatorio vira discussao de culpa.
- Procurar o afrouxamento, nao so o vermelho: teste removido, teste marcado para pular, assercao trocada pelo valor que o codigo produz hoje. Ajustar o esperado ao observado e a forma mais comum de transformar defeito em contrato.
- Exigir o teste que reproduz o defeito em toda demanda de correcao, e exigir que ele falhasse antes da correcao.
- Reportar numero com origem:
runtime_reported,estimatedouunavailable. Lacuna e publicada como lacuna, nunca como zero.
O que o nucleo verifica por voce
ork verify reexecuta os comandos do manifesto e as claims no HEAD real e carimba o commit.
Comando que passava na baseline e falha agora sai como verify.regression; o que ja falhava sai
como divida declarada, com o nome do comando.
Racionalizacoes comuns
| Desculpa | Realidade |
| "Esse teste era flaky, marquei para pular" | Pular teste e mudanca de escopo com registro. Sem registro, e o defeito saindo pela porta dos fundos. |
| "Ajustei a assercao para o valor certo" | Certo segundo quem? Se o valor esperado mudou, a razao esta no PLAN. Ajustar o esperado ao observado transforma defeito em contrato. |
| "O bug e obvio, o teste de reproducao e redundante" | Correcao cujo defeito nunca foi reproduzido nao prova que corrigiu nada. |
| "Cobertura esta em uns 80 por cento" | Numero sem origem nao entra. Sem ferramenta, a cobertura sai unavailable, com o motivo. |
| "So o caminho feliz basta, o resto e improvavel" | Suite que so exercita o sucesso mede otimismo. O caminho de falha e onde o usuario encontra o produto. |
| "Rodei localmente e passou" | Passagem relatada nao e passagem. O que vale e a saida real da reexecucao no HEAD. |
Bandeiras vermelhas
- Teste removido no mesmo commit que a correcao.
skipnovo sem registro.- Assercao alterada sem razao escrita.
- Cobertura reportada como numero redondo sem ferramenta na maquina.
- Nenhuma baseline gravada antes do GO.
Verificacao antes de sair da revisao
Baseline existente, suite reexecutada no HEAD real, diff de testes lido em busca de afrouxamento,
teste de reproducao presente nas correcoes, e todo numero com origem declarada. Ver TEST 1 a
TEST 12 e DoD 7.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

