Core commands
Skill Tiao553/sdd-harness-copilot/.github/skills/core-commands
AI-powered assistant for Harness-based software delivery, helping automate CI/CD, testing, deployments, and pipeline optimization with faster, safer, and more reliable workflows.
npx -y skills add Tiao553/sdd-harness-copilot --skill core-commandsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
AgentSpec commands for core. Use /core-commands + intent. Reads .github/config/grounding.md before executing. Commands: /meeting, /memory, /readme-maker, /status, /sync-context
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
2.5 KB, as published. Nobody here has run it
Core Commands
Invoke:
/core-commands+ descrição da tarefa
Regras Globais Obrigatórias
Estas regras valem para todos os comandos desta skill.
Grounding e Roteamento
- Antes de executar qualquer comando, leia
.github/config/grounding.md. - Leia
.github/config/routing.jsone selecione o agente pelo comando solicitado. - Leia o arquivo do agente selecionado em
.github/agents/. - Toda resposta operacional deve iniciar com o bloco
[GROUNDING]exigido por.github/config/grounding.md.
Caminhos Canônicos
| Tipo | Caminho correto |
|---|---|
| Storage persistente | .github/storage/ |
| Memória do projeto | .github/storage/memory/ |
| Status do projeto | _meta/STATUS.md |
| Contexto do projeto | _meta/CONTEXT.md |
| Instruções Copilot | .github/copilot-instructions.md |
| Agentes | .github/agents/{category}/{name}.agent.md |
| KB domains | .github/kb/{domain}/ |
Regras de Caminho
- Nunca use caminhos
.claude/**,.agents/**ouGEMINI.md. - Storage local usa
.github/storage/, não a raiz do repositório. - Artefatos de documentação (README, docs/) seguem convenções do repositório.
Constraints
- Não inicie fases SDD a partir desta skill.
- Não use sintaxe
#skill:ouskill:. - Se o comando exigir um agente que não existe, pare e reporte ao invés de inventar.
Comandos Disponíveis
| Comando | Descrição | Arquivo | Agente |
|---|---|---|---|
/meeting | Análise de transcrições de reunião | commands/meeting.md | meeting-analyst |
/memory | Gestão de memória e contexto do projeto | commands/memory.md | codebase-explorer |
/readme-maker | Geração e atualização de README | commands/readme-maker.md | codebase-explorer |
/status | Status e saúde do projeto | commands/status.md | codebase-explorer |
/sync-context | Sincronização de contexto entre sessões | commands/sync-context.md | codebase-explorer |
Execução
Para cada comando, leia o arquivo correspondente em commands/ e siga as instruções detalhadas contidas nele. O arquivo do comando é a fonte autoritativa de lógica, passos e formato de saída.