New: 97,000+ 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

Issue Fixer

by openinary in openinary/openinary

Implement GitHub issues collaboratively in open-source repositories with explicit approval gates, incremental delivery, atomic commits, and PR-ready validation.

AGPL-3.0Auto-check passedDevelopment

Install Issue Fixer

skills CLI
$ npx skills add openinary/openinary --skill issue-fixer -a claude-code

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

GitHub CLI
$ gh skill install openinary/openinary issue-fixer --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/openinary/openinary.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/issue-fixer .claude/skills/issue-fixer && 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
issue-fixer
GitHub stars
412
Token cost
~1.2k tokens
SKILL.md length
567 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Implement GitHub issues collaboratively in open-source repositories with explicit approval gates, incremental delivery, atomic commits, and PR-ready validation.

  • Works in 10 steps: Repository Sync → Issue Analysis (No Coding) → Solution Proposal (No Coding) → …
  • Working issue-by-issue with a human operator who decides scope and product direction
  • SKILL.md covers Outcome, When to Use, Collaboration Contract and Required Inputs, plus 3 more sections
  • Calls git

What it does

Issue Fixer is an agent skill from openinary/openinary. Implement GitHub issues collaboratively in open-source repositories with explicit approval gates, incremental delivery, atomic commits, and PR-ready validation. Use when working issue-by-issue with a human operator who decides scope and product direction.

Its SKILL.md is about 1.2k 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. It works with GitHub and Git. The repository describes itself as: The self-hostable alternative to Cloudinary. The licence is AGPL-3.0.

When your agent uses it

  • Working issue-by-issue with a human operator who decides scope and product direction

Example prompts

  • “/issue-fixer”

Workflow steps

10 steps, taken from the step headings in SKILL.md.

  1. Repository Sync
  2. Issue Analysis (No Coding)
  3. Solution Proposal (No Coding)
  4. Branch Creation
  5. Implementation Loop (Incremental)
  6. Atomic Commits
  7. Validation Before PR
  8. Sync Before Push
  9. Pull Request Preparation
  10. Post-Merge Cleanup

What it can do on your machine

Read from SKILL.md and the folder at commit 1f05325. 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

    Shell commands in SKILL.md call:

    • git

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

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Issue Fixer loads about 1.2k tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 567 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~67
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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 openinary/openinary at commit 1f05325, republished under its AGPL-3.0 licence (© openinary). 567 words, ~1,199 tokens.

Download SKILL.mdSave it as .claude/skills/issue-fixer/SKILL.md (or your agent's skills folder).
name
issue-fixer
description
Implement GitHub issues collaboratively in open-source repositories with explicit approval gates, incremental delivery, atomic commits, and PR-ready validation. Use when working issue-by-issue with a human operator who decides scope and product direction.
argument-hint
Issue URL or description, target branch policy, and any non-negotiable constraints
user-invocable
true
disable-model-invocation
false

Open Source Issue Implementation

Outcome

Produce a production-ready issue implementation with:

  • Shared understanding of scope and constraints
  • Operator-approved technical approach before coding
  • Incremental, reviewable changes
  • Clean commit history
  • Verified build/lint/type/tests status
  • PR-ready summary linked to the issue

When to Use

Use this skill when:

  • Working on a single GitHub issue in an open-source repository
  • A human operator must validate decisions before implementation advances
  • Scope control and traceable collaboration matter more than speed

Do not use this skill when:

  • Doing broad discovery without a concrete issue
  • Running large autonomous refactors without operator checkpoints

Collaboration Contract

At all times:

  • Propose -> operator decides -> implement
  • Do not make product decisions alone
  • Do not expand scope without explicit approval
  • Prefer clarity over speed
  • Ask concise clarification questions when ambiguous

Required Inputs

Collect or confirm:

  • Issue link or full issue text
  • Target base branch and contribution conventions
  • Definition of done (tests, lint/type, docs, screenshots, changelog)
  • Constraints (backward compatibility, performance, API stability)

Procedure

1. Repository Sync

Run and report results:

  1. git checkout main
  2. git pull origin main
  3. git fetch --all
  4. git status

Validation checks:

  • Working tree is clean (or operator explicitly approves proceeding with local changes)
  • main is current
  • No unresolved conflicts

If validation fails:

  • Stop and ask the operator how to proceed before editing code
2. Issue Analysis (No Coding)

Deliver a concise analysis containing:

  • 2-3 sentence summary
  • Goal
  • In-scope items
  • Out-of-scope items
  • Constraints
  • Edge cases
  • Open questions

Decision gate:

  • Wait for operator validation before moving forward
3. Solution Proposal (No Coding)

Propose implementation details:

  • Technical approach
  • Impacted files/modules
  • Data flow (if relevant)
  • Risks and trade-offs
  • Test strategy

Decision gate:

  • Wait for explicit operator approval before coding
4. Branch Creation

Create a branch only after proposal approval:

  1. Choose one prefix: feat/, fix/, refactor/, or chore/
  2. Create branch: git checkout -b <prefix><short-description>
5. Implementation Loop (Incremental)

For each iteration:

  1. Explain the next small step
  2. Implement that step
  3. Report what changed and why
  4. Ask for operator validation

Suggested iteration order:

  • Setup/refactor prerequisites
  • Core functionality
  • Edge cases and error handling
  • Cleanup and documentation

Rules:

  • Keep diffs focused and reviewable
  • Avoid unrelated file churn
  • Halt when requirements become ambiguous
Show full SKILL.md (208 more words)Show less
6. Atomic Commits

Commit each logical unit separately using conventional commits, for example:

  • feat: add overlay support
  • fix: handle empty queue payload

Commit quality checks:

  • One logical change per commit
  • Message reflects actual change
  • No debug artifacts
7. Validation Before PR

Run or confirm:

  • Build succeeds
  • Lint/type checks pass
  • Tests pass (or clearly state missing tests and rationale)
  • No debug code, temporary logging, or dead code remains

If checks fail:

  • Fix failures or escalate with a concise blocker report
8. Sync Before Push

Before opening PR:

  1. git fetch origin
  2. git rebase origin/main

If conflicts appear:

  • Resolve cleanly
  • Re-run validation checks
  • Summarize conflict decisions for operator visibility
9. Pull Request Preparation

Create a structured PR description containing:

  • Problem summary
  • Solution summary
  • Key implementation details
  • Validation evidence (build/lint/type/tests)
  • Visuals/screenshots when relevant
  • Linked issue
10. Post-Merge Cleanup

After merge confirmation:

  1. git branch -d <branch>
  2. git push origin --delete <branch>

Completion Criteria

This skill is complete when:

  • Issue scope is implemented as approved
  • Operator accepted each decision gate
  • Validation checks are green (or exceptions documented and accepted)
  • PR is ready or merged with cleanup completed

For each operator-facing update, use:

  1. Intent
  2. Action taken
  3. Result
  4. Decision needed

Keep updates concise and structured.

© openinary, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .github/skills/issue-fixer of openinary/openinary.

Open the folder on GitHubat commit 1f05325

Compare with similar skills

Issue Fixer 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.

Issue Fixer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Issue Fixer this skillopeninary/openinary412—~1.2kAutomated safety check: PassAGPL-3.0
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
Draft Release Notesjamiepine/voicebox57k—~941Automated safety check: PassMIT
PR Review State Fetchprisma/orm48k—~767Automated safety check: PassApache-2.0

Similar skills

  • 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

  • Draft Release Notes

    jamiepine/voicebox

    Writes or refreshes the Unreleased section of CHANGELOG.md as a themed narrative built from the commits, PRs and diff since the last version tag.

    57k GitHub stars~941 tokensUpdated today
    DevelopmentAuto-check passed

  • PR Review State Fetch

    prisma/orm

    Official

    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.

    48k GitHub stars~767 tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Mole Release Notes Publisher

    tw93/Mole

    Publishes curated, bilingual release notes for an existing Mole version tag with gh release edit, including contributor thanks and reactions, after the release workflow finishes.

    69k GitHub stars~1.9k tokensUpdated today
    DevelopmentAuto-check passed

More from openinary/openinary

  • Loops API

    openinary/openinary

    A skill your agent uses whenever the user wants to integrate Loops from application code, backend services, webhook handlers, or server-side automation.

    412 GitHub stars~1.1k tokensUpdated 2 days ago
    Auto-check passed

  • Loops CLI

    openinary/openinary

    A skill your agent uses whenever the user wants to work with the Loops CLI from the terminal.

    412 GitHub stars~782 tokensUpdated 2 days ago
    Auto-check passed

  • Loops Email Sending Best Practices

    openinary/openinary

    A skill your agent uses when the user wants to review, audit, improve, or plan email sending best practices.

    412 GitHub stars~943 tokensUpdated 2 days ago
    Auto-check passed

Works with

Categories

Questions about Issue Fixer

What does Issue Fixer do?

Implement GitHub issues collaboratively in open-source repositories with explicit approval gates, incremental delivery, atomic commits, and PR-ready validation. Issue Fixer is an agent skill from openinary/openinary. Implement GitHub issues collaboratively in open-source repositories with explicit approval gates, incremental delivery, atomic commits, and PR-ready validation.

When should I use Issue Fixer?

Issue Fixer fits situations like: working issue-by-issue with a human operator who decides scope and product direction.

How do I install Issue Fixer in Claude Code?

Run `npx skills add openinary/openinary --skill issue-fixer -a claude-code`. Or copy the skill folder (.github/skills/issue-fixer in openinary/openinary) into .claude/skills/issue-fixer in your project. Claude Code loads it when a task matches its description.

How do I install Issue Fixer in Codex?

Run `npx skills add openinary/openinary --skill issue-fixer -a codex`. Or copy the skill folder (.github/skills/issue-fixer in openinary/openinary) into .agents/skills/issue-fixer in your project. Codex loads it when a task matches its description.

Can I use Issue Fixer 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 openinary/openinary --skill issue-fixer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/issue-fixer, .gemini/skills/issue-fixer, .github/skills/issue-fixer and .opencode/skills/issue-fixer in your project.

What does Issue Fixer need to run?

Going by SKILL.md and its folder, Issue Fixer needs the command-line tools its instructions call (git).

Does Issue Fixer access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Issue Fixer 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 Issue Fixer use?

Issue Fixer is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Issue Fixer 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.

What are the alternatives to Issue Fixer?

Skills that share tags, products or a category with Issue Fixer: 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 Draft Release Notes (jamiepine/voicebox, 57k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Issue Fixer?

openinary (a GitHub organization) maintains it in openinary/openinary, which has 412 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 4, 2026.

Source: openinary/openinary on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.