cog-daily-intelligence
Generate personalized verified news briefs with 7-day freshness and 95%+ source accuracy
Datos de origen
- Repositorio
- a5c-ai/babysitter
- Última actividad en el origen
- 1 de junio de 2026 a las 07:46
- Idioma detectado de SKILL.md
- inglés
- Estrellas
- 1813
- Forks
- 111
Opciones de instalación
De forma predeterminada está seleccionado el prompt que primero revisa el origen. Puedes cambiar a un comando directo o descargar una copia local.
Revisa los archivos de origen
Lee SKILL.md y los archivos complementarios que muestra SkillsMP antes de decidir si quieres instalarlo.
Explorador de archivos
2 archivosMostrando SKILL.md
SKILL.md
Instrucciones de origen · Vista previa de solo lectura- name
- cog-daily-intelligence
- description
- Generate personalized verified news briefs with 7-day freshness and 95%+ source accuracy
- allowed-tools
- ["file-read","file-write","web-search","web-fetch","git-commit"]
- graph
- {"domains":["domain:software-engineering"],"skillAreas":["skill-area:agentic-loops","skill-area:orchestration-loop"],"workflows":["workflow:feature-development"],"topics":["topic:developer-experience"],"roles":["role:tech-lead","role:backend-engineer"]}
- Enforce 7-day freshness requirement on all sources
- Apply verification-first methodology: every claim needs a source
- Target 95%+ source accuracy
- Assign confidence levels to all intelligence items
- Cross-reference with existing vault knowledge in 05-knowledge
- Quality-gated brief generation with iterative refinement
## Tool Use Instructions
1. Use `file-read` to load user profile and interests from 00-inbox
2. Use `web-search` to gather relevant intelligence sources
3. Use `web-fetch` to verify and extract content from sources
4. Cross-verify claims across multiple sources
5. Use `file-read` to check existing knowledge in 05-knowledge for context
6. Use `file-write` to create daily brief in 01-daily
7. Use `git-commit` to commit the brief
## Quality Standards
- All sources must be within 7 days
- Every claim must have at least one verifiable source
- Confidence levels: high (3+ corroborating sources), medium (2 sources), low (1 source)
- Target overall accuracy: 95%+
## Examples
```json
{
"vaultPath": "./cog-vault",
"mode": "daily-brief",
"userName": "Alex",
"rolePack": "engineer",
"targetQuality": 80
}
```
Ver en GitHub