New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Contribute Publish

by jeremylongshore in jeremylongshore/tons-of-skills-marketplace

Publish one prepared OSS contribution action to GitHub after a fresh human approval boundary.

MITAuto-check passedDevelopment

Install Contribute Publish

skills CLI
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill contribute-publish -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jeremylongshore/tons-of-skills-marketplace contribute-publish --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/.curated/contribute-publish .claude/skills/contribute-publish && rm -rf skills-src

Use ~/.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/

Facts

Skill name
contribute-publish
GitHub stars
2.8k
Token cost
~1.2k tokens
SKILL.md length
489 words
Files
2 (incl. references)
Skills in repo
3,342
Repo updated
First seen
Licence
MIT

At a glance

Publish one prepared OSS contribution action to GitHub after a fresh human approval boundary.

  • Works in 6 steps: GitHub repository and issue or… → Exact action and command category (issue… → Complete content that will be posted, or… → …
  • Local preparation is complete and the user explicitly asks to post a claim
  • SKILL.md covers Overview, Prerequisites, Mandatory approval boundary and Instructions, plus 5 more sections
  • Calls gh and git

What it does

Contribute Publish is an agent skill from jeremylongshore/tons-of-skills-marketplace. Publish one prepared OSS contribution action to GitHub after a fresh human approval boundary. Shows the exact target, content, command, commit, and test evidence before any mutation. Use when local preparation is complete and the user explicitly asks to post a claim, create a Design Issue, comment, push a branch, or open a pull request. Trigger with "/contribute-publish" or "publish this prepared contribution".

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/approval-contract.md`). Compatibility notes: Model-agnostic; requires git and an authenticated GitHub CLI with permission for the approved action

It sits in Development, covering Pull requests. It works with GitHub. The repository describes itself as: Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com. The licence is MIT.

When your agent uses it

  • Local preparation is complete and the user explicitly asks to post a claim
  • Create a Design Issue
  • Open a pull request
  • With /contribute-publish

Example prompts

  • “/contribute-publish”
  • “publish this prepared contribution”
  • “/contribute-publish”

Requirements

  • Compatibility (from SKILL.md): Model-agnostic; requires git and an authenticated GitHub CLI with permission for the approved action
  • Pre-approved tools (allowed-tools): Read, Bash(gh:*), Bash(git:*)

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. GitHub repository and issue or pull-request target.
  2. Exact action and command category (issue comment, issue create, pr create,
  3. Complete content that will be posted, or the exact branch/ref that will be
  4. Exact prepared commit SHA and changed-file list when code is involved.
  5. Test and lint evidence.
  6. Any warnings, overrides, AI-use disclosure, CLA, or DCO requirement.

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Bash(gh:*)
    • Bash(git:*)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • cli.github.com

    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.

  • Compatibility

    Model-agnostic; requires git and an authenticated GitHub CLI with permission for the approved action

    From compatibility in the SKILL.md frontmatter.

Context cost

Contribute Publish loads about 1.2k tokens when it runs, and up to ~1.3k if it reads all its reference files. Until then it costs about 108 tokens; SKILL.md has 489 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~108
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.3k

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 jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 489 words, ~1,208 tokens.

Download SKILL.mdSave it as .claude/skills/contribute-publish/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
contribute-publish
description
Publish one prepared OSS contribution action to GitHub after a fresh human approval boundary. Shows the exact target, content, command, commit, and test evidence before any mutation. Use when local preparation is complete and the user explicitly asks to post a claim, create a Design Issue, comment, push a branch, or open a pull request. Trigger with "/contribute-publish" or "publish this prepared contribution".
allowed-tools
Read, Bash(gh:*), Bash(git:*)
compatibility
Model-agnostic; requires git and an authenticated GitHub CLI with permission for the approved action
version
0.9.0
author
Jeremy Longshore <jeremy@intentsolutions.io>
license
MIT
tags
oss, contributions, github, publishing, human-approval
argument-hint
[prepared-review-packet]
model
inherit
effort
high

Contribute Publish

Overview

Perform exactly one approved GitHub mutation from a completed local preparation packet. This skill has no authority to discover unrelated work, create persistent state, install dependencies, or expand the approved scope.

Prerequisites

  • A completed contribute-prepare review packet with final content, target, commit SHA, changed files, and passing evidence.
  • GitHub CLI authenticated through the user's existing credential store.
  • A clean understanding of the upstream's contribution, disclosure, CLA/DCO, branch, and review policies.

Mandatory approval boundary

Before any external action, show all of the following:

  1. GitHub repository and issue or pull-request target.
  2. Exact action and command category (issue comment, issue create, pr create, pr comment, or git push).
  3. Complete content that will be posted, or the exact branch/ref that will be pushed.
  4. Exact prepared commit SHA and changed-file list when code is involved.
  5. Test and lint evidence.
  6. Any warnings, overrides, AI-use disclosure, CLA, or DCO requirement.

Then ask for explicit approval for that exact action. Approval must appear in the current conversation after the review packet. Earlier blanket permission, installation, authentication, repository ownership, or approval of a different target does not count.

Instructions

  1. Use Read only to inspect the final prepared packet and approved body file.
  2. Present the mandatory approval boundary below.
  3. Wait for fresh approval for the exact action.
  4. Execute once, read back the resulting GitHub object, and stop.
  • Execute only the approved action and target.
  • Use the user's existing gh authentication; never request, read, or print a token.
  • Do not merge, force-push, approve reviews, bypass repository rules, close an issue, or delete a branch unless that exact operation received its own review packet and explicit approval.
  • If content or the target changes after approval, present the revised packet and ask again.
  • After execution, read back the resulting GitHub object and report its URL and authoritative state.
  • On failure, report the error and stop. Do not broaden permissions or retry with a more powerful command.
Show full SKILL.md (163 more words)Show less

Supported actions

bash
gh issue comment "$ISSUE_NUMBER" --repo "$REPOSITORY" --body-file "$APPROVED_FILE"
gh issue create --repo "$REPOSITORY" --title "$APPROVED_TITLE" --body-file "$APPROVED_FILE"
git -C "$APPROVED_WORKTREE" push "$APPROVED_REMOTE" "$APPROVED_REFSPEC"
gh pr create --repo "$REPOSITORY" --head "$APPROVED_HEAD" --base "$APPROVED_BASE" \
  --title "$APPROVED_TITLE" --body-file "$APPROVED_FILE"

These are examples, not permission to run them. Never combine multiple mutations under one approval unless the review packet explicitly lists each one.

Examples

  • publish this approved claim comment — show the final comment and target, obtain fresh approval, post once, then read back the issue comment URL.
  • open the prepared pull request — verify the prepared SHA and checks, show the exact base/head/title/body, obtain fresh approval, create once, and read back the pull request state.
  • push this prepared branch — show the exact worktree, remote, commit, and refspec; approval applies only to that push.

Output

Return the action performed, repository and target, resulting URL, resulting state read back from GitHub, and any remaining local-only follow-up.

Error handling

ConditionResponse
No fresh explicit approvalStop without mutation
Packet lacks tests, SHA, target, or final contentReturn to contribute-prepare
GitHub rejects the actionReport the error; do not bypass controls
Target/content changedInvalidate approval and present a new packet

Resources

© jeremylongshore, 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 (references) in skills/.curated/contribute-publish of jeremylongshore/tons-of-skills-marketplace.

  • SKILL.md
  • references/approval-contract.md

Open the folder on GitHubat commit cfae287

Compare with similar skills

Contribute Publish 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.

Contribute Publish compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Contribute Publish this skilljeremylongshore/tons-of-skills-marketplace2.8k—~1.2kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Check PRonyx-dot-app/onyx32k2 repos~2.3kAutomated safety check: PassMIT
Contributor-First PR MergeHKUDS/OpenHarness16k1 repos~847Automated safety check: PassMIT
Create Pull Requestcline/cline70k1 repos~1.6kAutomated safety check: PassApache-2.0
Pull Request Title and Body Writeropeninterpreter/openinterpreter69k2 repos~1.1kAutomated safety check: PassApache-2.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed

  • Check PR

    onyx-dot-app/onyx

    Checks a GitHub, GitLab, or Perforce (p4) pull request (or merge request, or shelved changelist) for unresolved review comments, failing status checks, and incomplete PR descriptions.

    32k GitHub starsUsed in 2 repos~2.3k tokens
    DevelopmentAuto-check passed

  • 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.

    16k GitHub starsUsed in 1 repo~847 tokens
    DevelopmentAuto-check passed

  • Create Pull Request

    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.

    70k GitHub starsUsed in 1 repo~1.6k tokens
    DevelopmentAuto-check passed

  • Pull Request Title and Body Writer

    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.

    69k GitHub starsUsed in 2 repos~1.1k tokens
    DevelopmentAuto-check passed

  • GitHub Review Iteration

    prisma/orm

    Official

    Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.

    48k GitHub stars~2.2k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from jeremylongshore/tons-of-skills-marketplace

All 3,342 skills in this repo

  • Performing Security Code Review

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to conduct a security-focused code review using the security-agent plugin.

    2.8k GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check: notes

  • Adapting Transfer Learning Models

    jeremylongshore/tons-of-skills-marketplace

    Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Agent Context Loader

    jeremylongshore/tons-of-skills-marketplace

    Execute proactive auto-loading: automatically detects and loads agents.md files.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Aggregating Performance Metrics

    jeremylongshore/tons-of-skills-marketplace

    Aggregate and centralize performance metrics from applications, systems, databases, caches, and services.

    2.8k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Analyzing Capacity Planning

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to analyze capacity requirements and plan for future growth.

    2.8k GitHub stars~947 tokensUpdated today
    Auto-check passed

  • Analyzing Database Indexes

    jeremylongshore/tons-of-skills-marketplace

    Process use when you need to work with database indexing. An agent skill from jeremylongshore/tons-of-skills-marketplace.

    2.8k GitHub stars~2k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Contribute Publish

What does Contribute Publish do?

Publish one prepared OSS contribution action to GitHub after a fresh human approval boundary. Contribute Publish is an agent skill from jeremylongshore/tons-of-skills-marketplace. Publish one prepared OSS contribution action to GitHub after a fresh human approval boundary.

When should I use Contribute Publish?

Contribute Publish fits situations like: local preparation is complete and the user explicitly asks to post a claim; create a Design Issue; open a pull request; with /contribute-publish.

How do I install Contribute Publish in Claude Code?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill contribute-publish -a claude-code`. Or copy the skill folder (skills/.curated/contribute-publish in jeremylongshore/tons-of-skills-marketplace) into .claude/skills/contribute-publish in your project. Claude Code loads it when a task matches its description.

How do I install Contribute Publish in Codex?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill contribute-publish -a codex`. Or copy the skill folder (skills/.curated/contribute-publish in jeremylongshore/tons-of-skills-marketplace) into .agents/skills/contribute-publish in your project. Codex loads it when a task matches its description.

Can I use Contribute Publish 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 jeremylongshore/tons-of-skills-marketplace --skill contribute-publish -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/contribute-publish, .gemini/skills/contribute-publish, .github/skills/contribute-publish and .opencode/skills/contribute-publish in your project.

What does Contribute Publish need to run?

Going by SKILL.md and its folder, Contribute Publish needs the command-line tools its instructions call (gh and git). Its frontmatter pre-approves these tools: Read, Bash(gh:*), Bash(git:*). Compatibility (from SKILL.md): Model-agnostic; requires git and an authenticated GitHub CLI with permission for the approved action.

Does Contribute Publish access the network?

SKILL.md names 1 domain. As links in the text: cli.github.com. This is read from the text; nothing was executed.

Is Contribute Publish 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 Contribute Publish use?

Contribute Publish is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Contribute Publish use?

About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 135 tokens, read only when the agent opens those files.

What are the alternatives to Contribute Publish?

Skills that share tags, products or a category with Contribute Publish: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Check PR (onyx-dot-app/onyx, 32k stars), Contributor-First PR Merge (HKUDS/OpenHarness, 16k stars) and Create Pull Request (cline/cline, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Contribute Publish?

jeremylongshore (a GitHub user) maintains it in jeremylongshore/tons-of-skills-marketplace, which has 2,827 GitHub stars. The repository holds 3,342 skills in this directory. The repository was last updated on October 10, 2026.

Source: jeremylongshore/tons-of-skills-marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.