Obliteratus
RedWoodOG/Hermes-Desktop
Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails…
Draft a Guardrails PR from its complete final diff and carry out authorized CI and review follow-up, including stacked PRs and takeovers.
Install PR Draft Summary
$ npx skills add openai/openai-guardrails-js --skill pr-draft-summary -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install openai/openai-guardrails-js pr-draft-summary --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/openai/openai-guardrails-js.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/pr-draft-summary .claude/skills/pr-draft-summary && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "pr-draft-summary" agent skill from https://github.com/openai/openai-guardrails-js/tree/main/.agents/skills/pr-draft-summary into .claude/skills/pr-draft-summary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pr-draft-summary", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/openai/openai-guardrails-js/tree/main/.agents/skills/pr-draft-summaryType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add openai/openai-guardrails-js --skill pr-draft-summary -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install openai/openai-guardrails-js pr-draft-summary --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openai/openai-guardrails-js.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/pr-draft-summary .agents/skills/pr-draft-summary && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "pr-draft-summary" agent skill from https://github.com/openai/openai-guardrails-js/tree/main/.agents/skills/pr-draft-summary into .agents/skills/pr-draft-summary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pr-draft-summary", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add openai/openai-guardrails-js --skill pr-draft-summary -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install openai/openai-guardrails-js pr-draft-summary --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openai/openai-guardrails-js.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/pr-draft-summary .cursor/skills/pr-draft-summary && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "pr-draft-summary" agent skill from https://github.com/openai/openai-guardrails-js/tree/main/.agents/skills/pr-draft-summary into .cursor/skills/pr-draft-summary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pr-draft-summary", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/openai/openai-guardrails-js.git --path .agents/skills/pr-draft-summary--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add openai/openai-guardrails-js --skill pr-draft-summary -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install openai/openai-guardrails-js pr-draft-summary --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openai/openai-guardrails-js.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/pr-draft-summary .gemini/skills/pr-draft-summary && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "pr-draft-summary" agent skill from https://github.com/openai/openai-guardrails-js/tree/main/.agents/skills/pr-draft-summary into .gemini/skills/pr-draft-summary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pr-draft-summary", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install openai/openai-guardrails-js pr-draft-summaryInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add openai/openai-guardrails-js --skill pr-draft-summary -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/openai/openai-guardrails-js.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/pr-draft-summary .github/skills/pr-draft-summary && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "pr-draft-summary" agent skill from https://github.com/openai/openai-guardrails-js/tree/main/.agents/skills/pr-draft-summary into .github/skills/pr-draft-summary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pr-draft-summary", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add openai/openai-guardrails-js --skill pr-draft-summary -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install openai/openai-guardrails-js pr-draft-summary --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/openai/openai-guardrails-js.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/pr-draft-summary .opencode/skills/pr-draft-summary && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "pr-draft-summary" agent skill from https://github.com/openai/openai-guardrails-js/tree/main/.agents/skills/pr-draft-summary into .opencode/skills/pr-draft-summary/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pr-draft-summary", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
pr-draft-summary- GitHub stars
- 105
- Token cost
- ~1k tokens
- SKILL.md length
- 566 words
- Files
- 2
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- MIT
At a glance
Draft a Guardrails PR from its complete final diff and carry out authorized CI and review follow-up, including stacked PRs and takeovers.
- Tasks that involve LLM guardrails
- SKILL.md covers Establish the actual PR scope, Draft the title and body and Submit and follow up when…
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
PR Draft Summary is an agent skill from openai/openai-guardrails-js, published by the product's own GitHub organization. Draft a Guardrails PR from its complete final diff and carry out authorized CI and review follow-up, including stacked PRs and takeovers.
Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in AI & LLM Engineering, covering LLM guardrails. The repository describes itself as: OpenAI Guardrails - TypeScript / JavaScript. The licence is MIT.
When your agent uses it
- Tasks that involve LLM guardrails
Example prompts
- “/pr-draft-summary”
What it can do on your machine
Read from SKILL.md and the folder at commit d28dc28. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
PR Draft Summary loads about 1k tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 566 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from openai/openai-guardrails-js at commit d28dc28, republished under its MIT licence (© openai). 566 words, ~1,032 tokens.
Download SKILL.mdSave it as
.claude/skills/pr-draft-summary/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- pr-draft-summary
- description
- Draft a Guardrails PR from its complete final diff and carry out authorized CI and review follow-up, including stacked PRs and takeovers.
PR Draft Summary
Describe the complete final change, including internal tooling and docs PRs. Read AGENTS.md for review, release-note, and remote-action rules. Drafting alone does not authorize submission or messages; retain explicit user authorization already given for the task.
Establish the actual PR scope
Inspect the current branch, target, merge base, all branch commits, staged and unstaged changes, and relevant untracked deliverables. Use the intended target, not a feature branch's tracking configuration. For an explicit stack, compare against the previous PR's branch and list the required predecessor. Check the combined stack separately for integration and scope drift.
Keep a user-selected branch; suggest an unused codex/<topic> name when needed.
Do not include unrelated local notes. If the diff is empty, report that fact
rather than inventing a PR. Reconcile the summary with the final diff after fixes.
Draft the title and body
Lead with the concrete problem or missing capability and resulting behavior. Use a concise imperative title. Include only details needed to review the change:
- What changes and why; relevant compatibility or migration requirements.
- Actual tests/checks run, results, and material coverage limitations.
- Changeset impact when it helps clarify release behavior.
- For takeovers, the source PR and verified attribution; for split takeovers, identify the slice without claiming the entire original PR is complete.
- For stacks, the predecessor and ordered stack position. Explain that the incremental diff is against that predecessor.
Use native GitHub references (#123 or owner/repo#123). Add issue-closing syntax
only when the final change fully resolves that issue and closure is intended.
Keep local paths, reviewer transcripts, internal diagnostics, and app directives
out of the external description. Do not claim a check or approval that did not run.
Show full SKILL.md (288 more words)Show less
Submit and follow up when authorized
Before any push or PR update, complete the repository's final review and applicable verification. Push only the intended branches and create PRs with explicit bases. Do not rewrite another author's branch, merge, or close a source PR merely because a replacement exists.
Monitor CI and CodeQL on the current head of every submitted PR. Both workflows
filter PR targets to main, so higher stack entries may have no automatic runs.
Inspect .github/workflows/ci.yml and .github/workflows/codeql.yml; when
needed, dispatch each workflow on each affected stack branch and verify that
every run's head SHA matches the PR. Require both workflows to pass before
reporting the head as green or requesting review. Missing checks are not passing
checks. Report an unavailable trigger or blocked run rather than weakening CI
or modifying branch protection.
Fix and re-push only failures introduced/worsened by the change or narrowly necessary to its outcome, repeating the required review/checks before updates. Retry evidenced transient failures; report unrelated failures separately. Stop repeated retries when there is no new evidence or progress.
Once current-head CI and CodeQL pass, request review in root #sdk-reviews as
required by AGENTS.md and authorized for the task. For a stack, one message can list all PRs
in dependency order; do not post it as a thread reply. If messaging is unavailable,
report the blocker and provide the prepared request without claiming it was sent.
When addressing feedback, inspect the whole affected diff, push the reviewed fix, then reply to the particular review thread explaining the correction and resolve it. Do not resolve feedback that remains unaddressed. If an earlier stack branch changes, reconcile dependent branches within the authorized scope and revalidate affected PR heads before reporting the stack as green.
© openai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in .agents/skills/pr-draft-summary of openai/openai-guardrails-js.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit d28dc28
Compare with similar skills
PR Draft Summary next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| PR Draft Summary this skillopenai/openai-guardrails-js | 105 | — | ~1k | Automated safety check: Pass | MIT | |
| ObliteratusRedWoodOG/Hermes-Desktop | 177 | 6 repos | ~3.8k | Automated safety check: Pass | MIT | |
| Lemonade Router Builderamd/skills | 398 | — | ~4k | Automated safety check: Pass | MIT | |
| Wp Project Triagegambitph/Stackable | 350 | 4 repos | ~371 | Automated safety check: Pass | GPL-3.0 | |
| Aisafetyhotwuyoscar/AISafetyHot-Hub | 224 | — | ~774 | Automated safety check: Pass | Custom licence | |
| Persona Designkangarooking/system-prompt-skills | 205 | 1 repos | ~956 | Automated safety check: Pass | MIT |
Similar skills
Lemonade Router Builder
amd/skills
Turns a natural-language description of routing intent into a valid Lemonade collection.router policy JSON.
Wp Project Triage
gambitph/Stackable
A skill your agent uses when you need a deterministic inspection of a WordPress repository (plugin/theme/block theme/WP core/Gutenberg/full site) including tooling/tests/version hints, and a…
Aisafetyhot
wuyoscar/AISafetyHot-Hub
Read AI Safety HOT daily digests, search recent AI safety research and incidents, and follow current hot topics.
Persona Design
kangarooking/system-prompt-skills
当需要为 AI 产品定义核心身份、角色声明和能力边界时调用此 skill。典型场景包括：设计新 AI 产品的 system prompt 首段、为不同场景创建差异化角色（如教学助手 vs 编程代理）、重新定义 AI 与用户的关系框架。
Execution Guardrails
mrtooher/fable-mode
Always-on operational guardrails, model-independent. An agent skill from mrtooher/fable-mode.
More from openai/openai-guardrails-js
- Official
Code Change Verification
openai/openai-guardrails-js
Select and run Guardrails verification for code, dependency, test, tooling, documentation, or repository-workflow changes.
- Official
Implementation Final Review
openai/openai-guardrails-js
Prepare independent review of a complete Guardrails change before pushing or updating a PR, using the repository adversarial-review procedure.
- Official
Implementation Kickoff
openai/openai-guardrails-js
Start or resume a requested Guardrails implementation or PR takeover in the selected linked worktree with bounded scope and verification.
- Official
Implementation Strategy
openai/openai-guardrails-js
Choose bounded implementation scope and existing owning modules before Guardrails runtime, configuration, client, resource, streaming, Agents, or SDK compatibility changes and feedback fixes.
Related
Categories
Questions about PR Draft Summary
What does PR Draft Summary do?
Draft a Guardrails PR from its complete final diff and carry out authorized CI and review follow-up, including stacked PRs and takeovers. PR Draft Summary is an agent skill from openai/openai-guardrails-js, published by the product's own GitHub organization. Draft a Guardrails PR from its complete final diff and carry out authorized CI and review follow-up, including stacked PRs and takeovers.
When should I use PR Draft Summary?
PR Draft Summary fits situations like: tasks that involve LLM guardrails.
How do I install PR Draft Summary in Claude Code?
Run `npx skills add openai/openai-guardrails-js --skill pr-draft-summary -a claude-code`. Or copy the skill folder (.agents/skills/pr-draft-summary in openai/openai-guardrails-js) into .claude/skills/pr-draft-summary in your project. Claude Code loads it when a task matches its description.
How do I install PR Draft Summary in Codex?
Run `npx skills add openai/openai-guardrails-js --skill pr-draft-summary -a codex`. Or copy the skill folder (.agents/skills/pr-draft-summary in openai/openai-guardrails-js) into .agents/skills/pr-draft-summary in your project. Codex loads it when a task matches its description.
Can I use PR Draft Summary in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add openai/openai-guardrails-js --skill pr-draft-summary -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pr-draft-summary, .gemini/skills/pr-draft-summary, .github/skills/pr-draft-summary and .opencode/skills/pr-draft-summary in your project.
What does PR Draft Summary need to run?
SKILL.md names no scripts, command-line tools or credentials: PR Draft Summary is instructions for the agent only.
Does PR Draft Summary access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is PR Draft Summary safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does PR Draft Summary use?
PR Draft Summary is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does PR Draft Summary use?
About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to PR Draft Summary?
Skills that share tags, products or a category with PR Draft Summary: Obliteratus (RedWoodOG/Hermes-Desktop, 177 stars), Lemonade Router Builder (amd/skills, 398 stars), Wp Project Triage (gambitph/Stackable, 350 stars) and Aisafetyhot (wuyoscar/AISafetyHot-Hub, 224 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains PR Draft Summary?
openai (a GitHub organization, an official publisher) maintains it in openai/openai-guardrails-js, which has 105 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 8, 2026.
Source: openai/openai-guardrails-js on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.