conductor
conductor is an Execution & autonomous loops skill for AI agents, published by crbnos in the carbon repository on GitHub. Skillspace rates conductor D (66/100) and it passed the safety scan; the rating is based on static analysis only.
Autonomous loop conductor — drive a single work item (a bug, a usability tweak, a small feature) through a doer→gate→judge→keep-or-revert→ledger cycle to a gated PR, unattended. Use when asked to "conduct", "loop on", or build/fix one tightly-scoped item with explicit acceptance criteria, and as the inner loop the outer-loop orchestrator dispatches headless. Backed by @carbon/harness and the @carbon/checks gates. Autonomous means: never call /grill or block on human input mid-loop; the gated PR is the supervision point — never auto-merged. For multi-phase features with human design gates prefer /feature.
- Grade
- D
- Quality
- 66 / 100
- Safety
- Passed
- GitHub stars
- 2,401
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 96 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
Not checked yet
- Category is a classifier prediction; no model has read this skill 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.