o2-loop
o2-loop is a Multi-stage workflow orchestration skill for AI agents, published by openobserve in the openobserve repository on GitHub. Skillspace rates o2-loop D (68/100) and it passed the safety scan; the rating is based on static analysis only.
Plan, implement, and review a change with separated roles. The main session discusses the plan with the user and writes a spec; an o2-coder subagent implements it and runs the gates; an independent reviewer process (Codex CLI, or a sandboxed claude -p when Codex is unavailable) reviews each round's WIP commit; the coder fixes or disputes every finding; up to 5 rounds, then the user is asked. The main session only orchestrates, watches, and relays progress. Use when the user says "start the loop", "o2-loop", "start the review loop", or when a confirmed plan is ready to be implemented and reviewed before the user looks at it. Makes local WIP commits, never pushes.
- Grade
- D
- Quality
- 68 / 100
- Safety
- Passed
- GitHub stars
- 21,772
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
- 100 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
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.