Contributor-First PR Merge
HKUDS/OpenHarness
Merges external GitHub pull requests while keeping the original author credited, and fixes conflicts after the merge instead of rewriting the contribution.
Prepare focused commits, push branches, and create or update GitHub pull requests when requested.
$ npx skills add converge-ai-labs/agent-foundation --skill commit-push-pr -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install converge-ai-labs/agent-foundation commit-push-pr --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/converge-ai-labs/agent-foundation.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/commit-push-pr .claude/skills/commit-push-pr && 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 "commit-push-pr" agent skill from https://github.com/converge-ai-labs/agent-foundation/tree/main/.agents/skills/commit-push-pr into .claude/skills/commit-push-pr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "commit-push-pr", 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/converge-ai-labs/agent-foundation/tree/main/.agents/skills/commit-push-prType 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 converge-ai-labs/agent-foundation --skill commit-push-pr -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install converge-ai-labs/agent-foundation commit-push-pr --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/converge-ai-labs/agent-foundation.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/commit-push-pr .agents/skills/commit-push-pr && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "commit-push-pr" agent skill from https://github.com/converge-ai-labs/agent-foundation/tree/main/.agents/skills/commit-push-pr into .agents/skills/commit-push-pr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "commit-push-pr", 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 converge-ai-labs/agent-foundation --skill commit-push-pr -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install converge-ai-labs/agent-foundation commit-push-pr --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/converge-ai-labs/agent-foundation.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/commit-push-pr .cursor/skills/commit-push-pr && 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 "commit-push-pr" agent skill from https://github.com/converge-ai-labs/agent-foundation/tree/main/.agents/skills/commit-push-pr into .cursor/skills/commit-push-pr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "commit-push-pr", 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/converge-ai-labs/agent-foundation.git --path .agents/skills/commit-push-pr--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 converge-ai-labs/agent-foundation --skill commit-push-pr -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install converge-ai-labs/agent-foundation commit-push-pr --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/converge-ai-labs/agent-foundation.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/commit-push-pr .gemini/skills/commit-push-pr && 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 "commit-push-pr" agent skill from https://github.com/converge-ai-labs/agent-foundation/tree/main/.agents/skills/commit-push-pr into .gemini/skills/commit-push-pr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "commit-push-pr", 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 converge-ai-labs/agent-foundation commit-push-prInstalls 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 converge-ai-labs/agent-foundation --skill commit-push-pr -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/converge-ai-labs/agent-foundation.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/commit-push-pr .github/skills/commit-push-pr && 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 "commit-push-pr" agent skill from https://github.com/converge-ai-labs/agent-foundation/tree/main/.agents/skills/commit-push-pr into .github/skills/commit-push-pr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "commit-push-pr", 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 converge-ai-labs/agent-foundation --skill commit-push-pr -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install converge-ai-labs/agent-foundation commit-push-pr --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/converge-ai-labs/agent-foundation.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/commit-push-pr .opencode/skills/commit-push-pr && 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 "commit-push-pr" agent skill from https://github.com/converge-ai-labs/agent-foundation/tree/main/.agents/skills/commit-push-pr into .opencode/skills/commit-push-pr/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "commit-push-pr", 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.
commit-push-prPrepare focused commits, push branches, and create or update GitHub pull requests when requested.
Commit Push PR is an agent skill from converge-ai-labs/agent-foundation. Prepare focused commits, push branches, and create or update GitHub pull requests when requested. Perform only the stages authorized by the user; a commit-only request does not include pushing or opening a PR.
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development, covering Pull requests. It works with GitHub and Git. The repository describes itself as: a13n - An open-source library and self-hosted platform for building and running your own agent systems—with managed agents, memory, sandboxes, computer use, and durable… The licence is Apache-2.0.
Read from SKILL.md and the folder at commit 03de0fe. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
ghgitFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use gh and git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Commit Push PR loads about 2.2k tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 1,165 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.
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.
The full file from converge-ai-labs/agent-foundation at commit 03de0fe, republished under its Apache-2.0 licence (© converge-ai-labs). 1,165 words, ~2,204 tokens.
.claude/skills/commit-push-pr/SKILL.md (or your agent's skills folder).Complete the requested Git/GitHub handoff under AGENTS.md and CONTRIBUTING.md. Preserve existing authorization across follow-ups. Do not add Issue creation, reviewer requests, PR merges, releases, or deployments unless authorized. Do not start a separate code review or review subagent unless the user requests it.
git status --short --branch, the diff, untracked files, and relevant remotes. Separate intended changes from unrelated work, secrets, local configuration, caches, and generated artifacts.feat/harness-capability-runtime or fix/session-cancellation. Do not push directly to a protected base.gh; local Git work does not require it. On first use for a target, determine the host/repository from the remote and check gh auth status --hostname <host> and gh repo view --json nameWithOwner,url,defaultBranchRef. Reuse that verification unless the target or authentication context changes, or an operation indicates it is no longer valid.gh is unavailable or unauthenticated, finish independent authorized local preparation and report the missing prerequisite and applicable login command. Do not silently substitute browser automation, raw APIs, or another hosting CLI.Unresolved material design questions follow the contribution workflow; this skill does not settle them or authorize an Issue post.
Follow CONTRIBUTING.md for validation. Reuse successful results whose relevant inputs remain unchanged and rerun affected checks after fixes. Committing or updating a PR does not itself invalidate prior results. Report failures and unavailable checks accurately; never bypass hooks.
Before staging, run git diff --check. Stage explicit intended paths and review both the staged diff and git diff --cached --stat.
Use an English Conventional Commit subject with lowercase type and required scope:
type(scope): imperative summaryKeep the subject concise without a trailing period. Describe material completed behavior or boundary changes in the body when needed; do not pad it with routine staging/formatting steps or require a fixed bullet count.
Do not create empty or duplicate commits, add agent co-author trailers, or invent attribution. If hooks rewrite files, inspect and stage only intended changes before committing again. Rewrite existing history only when that operation is explicitly authorized.
Confirm the destination remote and branch, then push with upstream tracking where needed; for a confirmed origin destination:
git push -u origin HEADDo not force-push by default. Use --force-with-lease only when the concrete history rewrite is explicitly authorized. After an uncertain push result, inspect remote state before retrying.
When local checkout synchronization is part of the user's workflow, inspect that checkout before changing it. Synchronize only a clean checkout with a verified fast-forward; explain the impact and obtain missing authorization if local work, reset, rebase, or merge would be involved. Do not delete branches or worktrees merely to tidy up.
Check for an existing open PR for the confirmed head/base so updates do not create duplicates:
gh pr view --json number,url,state,isDraft,titleIf no open PR exists, create one with the intended head/base. Preserve an existing PR's draft state; create a ready PR unless the user requests a draft. Drafts skip code CI; marking a draft ready starts the applicable checks. Do not toggle readiness just to refresh automatic labels.
Use the scoped Conventional Commit format for the PR title, describing the resulting change rather than editing or review activity. Write it for the component's users or integrators, not just someone familiar with the implementation:
type(scope)!: and retain only the summary.Examples (use only when supported by the diff):
| Too vague or implementation-led | Outcome-led summary |
|---|---|
| refine media previews | preview linked images, audio, and video in conversations |
| simplify proxy handling | allow proxied Web requests without local destination DNS |
| enable self-healing by default | repair supported model history rejections by default |
The PR Labels workflow automatically classifies PRs on opening and readiness; ordinary PRs need no manual labels or notes file. Mark incompatible changes with ! and explain impact and migration in the body. Existing type labels are preserved, so when an update changes the PR's classification, inspect its labels and adjust only the relevant ones with gh pr edit; preserve unrelated labels. Do not classify user-visible changes as chore. Label corrections are part of the authorized PR handoff, not permission to change repository settings or publish a release.
Read the repository PR template, preferring the base-branch version. Preserve required headings and checklist items, remove placeholders such as Closes #, link a relevant Issue when one exists, and mark only verified conditions. Human-review items require evidence from the human author.
Follow Writing Issues and Pull Requests for the opening explanation, choice of visuals, and concise validation evidence. Keep the body and diagrams aligned with the final diff when the PR scope changes. Explain material compatibility implications; use GitHub checks for CI status rather than repeating routine check results in the body. If no template exists, a short summary and validation section suffice. Pass multiline content with --body-file using a temporary file outside the repository. Do not claim a missing check passed or omit a known blocker.
Inspect gh pr checks once after creating or updating the PR. Report CI as pending, passing, or failed; wait or monitor only when requested. Before retrying an uncertain PR creation, query existing PRs again.
Report only the completed/requested stages: branch and commit, push result, PR link/title, validation and current CI state, plus concrete blockers. Apply reviewer routing from MAINTAINERS.md when requesting reviewers is authorized.
© converge-ai-labs, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .agents/skills/commit-push-pr of converge-ai-labs/agent-foundation.
Open the folder on GitHubat commit 03de0fe
Commit Push PR 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 |
|---|---|---|---|---|---|---|
| Commit Push PR this skillconverge-ai-labs/agent-foundation | 171 | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| Contributor-First PR MergeHKUDS/OpenHarness | 16k | 1 repos | ~847 | Automated safety check: Pass | MIT | |
| Create Pull Requestcline/cline | 70k | 1 repos | ~1.6k | Automated safety check: Pass | Apache-2.0 | |
| Pull Request Title and Body Writeropeninterpreter/openinterpreter | 69k | 2 repos | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| PR Review State Fetchprisma/orm | 48k | — | ~767 | Automated safety check: Pass | Apache-2.0 | |
| Create Pull Request with Work Item IDmakeplane/plane | 61k | — | ~824 | Automated safety check: Pass | AGPL-3.0 |
HKUDS/OpenHarness
Merges external GitHub pull requests while keeping the original author credited, and fixes conflicts after the merge instead of rewriting the contribution.
cline/cline
Opens a GitHub pull request from your current branch with the gh CLI, after reviewing the commits and diff and gathering the details the PR needs.
openinterpreter/openinterpreter
Rewrites the title and body of one or more pull requests with gh, leading with why the change was made, then what changed, and describing only the net result.
prisma/orm
Fetches a pull request's canonical review state as JSON, validates it, and renders markdown, a text summary and triage target files from it using bundled scripts.
makeplane/plane
Opens a pull request for the current branch using the repo's template, a work item ID in the title and a description filled in from the actual diff.
redis/jedis
Generate a clear, concise GitHub PR title and description from the diff between two local git branches, and save it to prDescription.md in the repo root.
converge-ai-labs/agent-foundation
Author, review, or reorganize accepted technical contracts under spec/, including domain models, lifecycles, APIs, protocols, ownership, security, and compatibility.
converge-ai-labs/agent-foundation
Audit a repository or revision range for spec-code gaps, inconsistent shared concepts, semantic duplication, and removable code.
converge-ai-labs/agent-foundation
Start a task in a Git worktree under .worktrees/ from freshly fetched origin/main, implement and validate it, then use commit-push-pr to open or update a PR.
converge-ai-labs/agent-foundation
Build and refine frontend pages and interactions with strong visual taste, proactive polish, and lightweight iteration.
Categories
Prepare focused commits, push branches, and create or update GitHub pull requests when requested. Commit Push PR is an agent skill from converge-ai-labs/agent-foundation. Prepare focused commits, push branches, and create or update GitHub pull requests when requested.
Commit Push PR fits situations like: tasks that involve Pull requests.
Run `npx skills add converge-ai-labs/agent-foundation --skill commit-push-pr -a claude-code`. Or copy the skill folder (.agents/skills/commit-push-pr in converge-ai-labs/agent-foundation) into .claude/skills/commit-push-pr in your project. Claude Code loads it when a task matches its description.
Run `npx skills add converge-ai-labs/agent-foundation --skill commit-push-pr -a codex`. Or copy the skill folder (.agents/skills/commit-push-pr in converge-ai-labs/agent-foundation) into .agents/skills/commit-push-pr in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add converge-ai-labs/agent-foundation --skill commit-push-pr -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/commit-push-pr, .gemini/skills/commit-push-pr, .github/skills/commit-push-pr and .opencode/skills/commit-push-pr in your project.
Going by SKILL.md and its folder, Commit Push PR needs the command-line tools its instructions call (gh and git).
SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
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.
Commit Push PR is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.2k tokens (SKILL.md is roughly 8.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Commit Push PR: Contributor-First PR Merge (HKUDS/OpenHarness, 16k stars), Create Pull Request (cline/cline, 70k stars), Pull Request Title and Body Writer (openinterpreter/openinterpreter, 69k stars) and PR Review State Fetch (prisma/orm, 48k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
converge-ai-labs (a GitHub organization) maintains it in converge-ai-labs/agent-foundation, which has 171 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 10, 2026.
Source: converge-ai-labs/agent-foundation on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.