harness
harness is a Multi-stage workflow orchestration skill for AI agents, published by gutomec in the nirvana-os-engine repository on GitHub. Skillspace rates harness C (73/100) and it passed the safety scan; the rating is based on static analysis only.
Top-level agentic orchestrator — this IS the Nirvana-OS. The model carrying this skill is the maestro of the whole system and can mobilize MANY businesses AND/OR MANY squads simultaneously (injecting mind-clones) to fulfil one brief. Reads the brief, researches the web if needed, consults all three registries (businesses + squads + mind-clones) and dispatches the best combination. MANDATORY entry point for any production brief (livro, vídeo, PDF, post, copy, design, código, marca, relatório, análise, ilustração, página, app, qualquer artefato) AND whenever the user invokes the system by name: 'use o nirvana-os', 'via nirvana', 'pelo nirvana', 'orquestre via nirvana', 'manda o nirvana', 'use minhas empresas/squads', 'o que o nirvana pode fazer'. Agentic by default; a `fast` BM25/keyword routing mode is available for zero-token, deterministic routing.
- Grade
- C
- Quality
- 73 / 100
- Safety
- Passed
- GitHub stars
- 38
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 93 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- Low-risk patterns
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- mentions secrets in text
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.