github.com/openai/symphony
| Skill | Added | Review |
|---|---|---|
push .codex/skills/push/SKILL.md Push current branch changes to origin and create or update the corresponding pull request; use when asked to push, publish updates, or create pull request. | 77 77 2.05x Agent success vs baseline Impact 80% 2.05xAverage score across 2 eval scenarios Securityby Low Low-risk findings worth noting Reviewed: Version: 8001b52 | |
pull .codex/skills/pull/SKILL.md Pull latest origin/main into the current local branch and resolve merge conflicts (aka update-branch). Use when Codex needs to sync a feature branch with origin, perform a merge-based update (not rebase), and guide conflict resolution best practices. | 66 66 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 8001b52 | |
linear .codex/skills/linear/SKILL.md Use Symphony's `linear_graphql` client tool for raw Linear GraphQL operations such as comment editing and upload flows. | 76 76 1.58x Agent success vs baseline Impact 84% 1.58xAverage score across 3 eval scenarios Securityby High Do not use without reviewing Reviewed: Version: 8001b52 | |
land .codex/skills/land/SKILL.md Land a PR by monitoring conflicts, resolving them, waiting for checks, and squash-merging when green; use when asked to land, merge, or shepherd a PR to completion. | 83 83 1.90x Agent success vs baseline Impact 95% 1.90xAverage score across 3 eval scenarios Securityby Low Low-risk findings worth noting Reviewed: Version: 8001b52 | |
debug .codex/skills/debug/SKILL.md Investigate stuck runs and execution failures by tracing Symphony and Codex logs with issue/session identifiers; use when runs stall, retry repeatedly, or fail unexpectedly. | 83 83 1.00x No change in agent success vs baseline Impact 83% 1.00xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: 8001b52 | |
commit .codex/skills/commit/SKILL.md Create a well-formed git commit from current changes using session history for rationale and summary; use when asked to commit, prepare a commit message, or finalize staged work. | 77 77 1.00x No change in agent success vs baseline Impact 56% 1.00xAverage score across 3 eval scenarios Securityby Passed No findings from the security scan Reviewed: Version: 8001b52 |