## Summary
- add `skills/.experimental/wrapped`
- include skill definition, agent config, and scripts for wrapped
reports
## Testing
- not run (file import only)
Co-authored-by: Ed Bayes <@openai.com>
## Summary
Fix Playwright CLI skill to reference the correct npm package.
## Changes
- Use `@playwright/cli` in the wrapper script instead of
`@playwright/mcp`.
- Update skill install guidance to match the correct package.
## Why
The Playwright CLI binary is provided by `@playwright/cli`. The skill
currently points at `@playwright/mcp`, which does not install
`playwright-cli`, causing installs to succeed but the CLI to be missing.
## Testing
- Installed the updated skill locally.
- Opened Google and performed a search via `playwright-cli` in headed
mode.
**Summary**
- aligned the Cloudflare, Netlify, and Render deploy skills with the
prereqs and escalation guidance from the Vercel skill
- documented requirement to rerun deployments with
`sandbox_permissions=require_escalated` when sandboxing blocks
networking and reminded that deployments may take several minutes
- added a Troubleshooting section that describes when to request
escalated network access and sample messaging for Cloudflare, Netlify,
and Render
**Testing**
- Not run (not requested)
## Summary
- add small and large icons for the develop-web-game skill
- add matching assets for the jupyter-notebook skill
- add icons and assets for the transcribe skill so every curated
openai.yaml has imagery
## Testing
- Not run (not requested)
Summary
- add MCP configs for both Notion skills mirroring existing structure
with small and large icon references
- add exported Notion assets, small SVG supporting currentColor and PNG
large icon for each skill
Testing
- Not run (not requested)
Summary
- create an openai.yaml manifest for the Linear skill with ownership,
interface, and MCP tooling details matching render-deploy guidance
- add the required small and large asset files (linear-small.svg with
currentColor path and linear.png icon)
Testing
- Not run (not requested)
## Summary
- Add curated skills from internal: `atlas`, `develop-web-game`,
`figma-implement-design`, `jupyter-notebook`, `openai-docs`,
`playwright`, `sentry`, and `transcribe`
- Normalize repo-root script paths to `skills/.curated/...` within the
copied skill docs
- Remove `dependencies.tools` blocks from all new `agents/openai.yaml`
files (matching the cleanup approach from PR #64)
## Notes
- Atlas validation succeeds via `uv run --python 3.12`
- Develop web game/playwright scripts require local Playwright
dependencies to run
Summary
- tighten up the `yeet` skill instructions by trimming extra whitespace
and reformatting the workflow steps into consistent Markdown bullets
- clarify that the branch creation step only applies when starting from
main/master/default
Testing
- Not run (not requested)
## Summary:
- add experimental gitlab-address-comments skill docs and workflow steps
- include a fetch_comments.py helper to pull MR discussions via glab api
- add Apache 2.0 license for the new skill bundle
## Testing:
- manually QA'd
## Overview
This PR adds two Codex readiness skills that evaluate repository
guidance quality
and end‑to‑end agentic execution. The unit test focuses on deterministic
checks + in‑session LLM evaluation of AGENTS.md/PLANS.md quality, while
the
integration test runs a full agentic loop and scores real code changes
and
build/test outcomes.
## 1) codex-readiness-unit-test (LLM Codex Readiness Unit Test)
### Goal
Validate that AGENTS.md and PLANS.md provide sufficient, usable guidance
using
deterministic checks plus in‑session LLM evaluation, and generate a
scored
JSON + HTML report.
### How it works
This skill builds a report from two pipelines: deterministic filesystem
checks
and in‑session LLM evaluation of AGENTS.md/PLANS.md guidance. It writes
a
timestamped run directory with evidence, LLM results, and a scored
JSON/HTML
report; in optional execute mode it runs a user‑approved plan and
includes
execution logs in scoring. JSON outputs are strictly validated with a
retry +
json‑fix loop.
## 2) codex-readiness-integration-test (LLM Codex Readiness Integration
Test)
### Goal
Validate real agentic execution quality by running Codex CLI against the
repo,
executing an approved change prompt, and scoring results with evidence +
LLM
evaluation.
### How it works
This skill runs an end‑to‑end agentic execution against the repo using
Codex
CLI, then executes a build/test plan and scores the run from evidence
plus LLM
evaluation. It spins up the Codex session by launching the CLI as a
subprocess
with HOME/XDG_CACHE_HOME pointed at the repo‑local .codex-home, using
the
approved prompt.json (change prompt + agentic_loop settings) so the CLI
reads
AGENTS.md and operates in the repo. It requires a repo‑local login,
always
runs in execute mode, and writes results to a timestamped run directory
with
agentic logs, LLM results, and a summary.
## Summary
This PR corrects the path to the CLA document referenced in the GitHub
Actions workflow. The CLA document is located at the root of the
repository, not in a docs/ subdirectory.
The CLA and CLA workflow were copied verbatim from the openai/codex
repo. The contributing guidelines are a stripped-down version of that in
the openai/codex repo.
---------
Co-authored-by: Josh McKinney <joshka@openai.com>
Rewrites `plan` skill as `create-plan` and removes all lifecycle
management skills. Moved to a new `.experimental` bucket for evaluation
and to get feedback on use.
This PR removes references to oai_gh from the curated GitHub skills and
replaces them with standard GitHub CLI auth guidance (gh auth login).
The goal is to avoid assuming internal tooling in a public repo.
That said, I'm not sure whether oai_gh is actually a built-in Codex
helper. If it is, feel free to close this PR.
I also did a sweep of .curated for other internal-only helpers and
didn't find any additional ones.
Thomas MustierandGitHub
Andi RadulescuandGitHub
Dominik KundelandGitHub
Andrew QuandGitHub
Vaibhav SrivastavandGitHub
Andrew AmbrosinoandGitHub
Gav VermaandGitHub
pranavdeshandGitHub
LukeandGitHub
Eric TrautandGitHub
ErayandGitHub
Josh McKinneyandGitHub
xl-openaiandGitHub
Christian Bager Bach HoumannandGitHub