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 Bulk Process

by mono in mono/SkiaSharp

Bulk triage and reproduce multiple SkiaSharp GitHub issues in a single command.

MITAuto-check passedDevelopment

Install Issue Bulk Process

skills CLI
$ npx skills add mono/SkiaSharp --skill issue-bulk-process -a claude-code

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

GitHub CLI
$ gh skill install mono/SkiaSharp issue-bulk-process --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/mono/SkiaSharp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/issue-bulk-process .claude/skills/issue-bulk-process && 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-bulk-process
GitHub stars
5.6k
Token cost
~1.6k tokens
SKILL.md length
662 words
Files
1
Skills in repo
23
Repo updated
First seen
Licence
MIT

At a glance

Bulk triage and reproduce multiple SkiaSharp GitHub issues in a single command.

  • Works in 4 steps: Resolve Repository and Issue List → Triage (parallel) → Reproduce (serial) → …
  • Development work in your project
  • SKILL.md covers Input Parsing, Phase 1 — Resolve Repository…, Phase 2 — Triage (parallel) and Phase 3 — Reproduce (serial), plus 2 more sections
  • Calls gh

What it does

Issue Bulk Process is an agent skill from mono/SkiaSharp. Bulk triage and reproduce multiple SkiaSharp GitHub issues in a single command. Orchestrates parallel triage agents then serial reproduction agents, and presents a consolidated summary. Triggers: "bulk process issues", "triage and repro these issues", "process issues 3400 3428 3429", "process the newest 10 issues", "bulk triage", "batch process issues", any request to triage or reproduce multiple issues at once.

Its SKILL.md is about 1.6k 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. The repository describes itself as: SkiaSharp is a cross-platform 2D graphics API for .NET platforms based on Google's Skia Graphics Library. It provides a comprehensive 2D API that can be used across mobile… The licence is MIT.

When your agent uses it

  • Development work in your project

Example prompts

  • “bulk process issues”
  • “triage and repro these issues”
  • “process issues 3400 3428 3429”
  • “/issue-bulk-process”

Workflow steps

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

  1. Resolve Repository and Issue List
  2. Triage (parallel)
  3. Reproduce (serial)
  4. Summary

What it can do on your machine

Read from SKILL.md and the folder at commit a74f7f9. 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:

    • gh

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

  • Network

    No URLs in SKILL.md. Its commands use gh, 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 Bulk Process loads about 1.6k tokens when it runs. Until then it costs about 109 tokens; SKILL.md has 662 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~109
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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 mono/SkiaSharp at commit a74f7f9, republished under its MIT licence (© mono). 662 words, ~1,610 tokens.

Download SKILL.mdSave it as .claude/skills/issue-bulk-process/SKILL.md (or your agent's skills folder).
name
issue-bulk-process
description
Bulk triage and reproduce multiple SkiaSharp GitHub issues in a single command. Orchestrates parallel triage agents then serial reproduction agents, and presents a consolidated summary. Triggers: "bulk process issues", "triage and repro these issues", "process issues 3400 3428 3429", "process the newest 10 issues", "bulk triage", "batch process issues", any request to triage or reproduce multiple issues at once.

Issue Bulk Process

Orchestrate bulk triage and reproduction of multiple SkiaSharp issues by delegating to issue-triage and issue-repro skills via sub-agents.

Input Parsing

Parse the user's message to determine the issue list:

  1. Explicit issue references — numbers preceded by #, or numbers in a space/comma-separated list that the user clearly intends as issue numbers (e.g., #3400 #3428, issues 3400, 3428, 3429, triage 123 456 789). Issue numbers may be 2–5 digits.
  2. "newest N issues" — if the user says "newest", "latest", "recent", or "last N issues", extract the count N and fetch from GitHub (see Phase 1).
  3. Ambiguous numbers — if a number could be an issue number OR a count/quantity (e.g., "process 10 issues starting from 3400"), ask the user to clarify before proceeding. Use the ask_user tool.

Phase 1 — Resolve Repository and Issue List

1. Detect current repository
bash
gh repo view --json owner,name -q '"\(.owner.login)/\(.name)"'

Store the {owner} and {repo} for use in all subsequent phases.

2. Resolve issue list

Use the gh CLI for all issue lookups. It handles pagination automatically via the -L (limit) flag — no manual page iteration needed.

If explicit numbers given: Use them directly — they refer to the current repository.

If "newest N issues" or similar:

bash
gh issue list --state open -L {N} --json number,title -q '.[] | "\(.number)\t\(.title)"'

If search query (e.g., "all blazor issues", "issues about WASM", "label:area/foo"):

bash
gh issue list -S "{search terms}" --state open -L 500 --json number,title -q '.[] | "\(.number)\t\(.title)"'

For label-based queries, use --label instead of -S:

bash
gh issue list --label "area/SkiaSharp.Views" --state open -L 500 --json number,title -q '.[] | "\(.number)\t\(.title)"'

Note: -L 500 is a generous upper bound. gh fetches exactly as many pages as needed and stops when results are exhausted, so over-specifying the limit is fine.

Extract issue numbers from the output. Present the list to the user and confirm before proceeding.

3. Skip already-processed issues

Before launching triage/repro agents, check for existing result files:

bash
# Check for existing triage results
ls .data-cache/repos/{owner}-{repo}/ai-triage/{number}.json 2>/dev/null

# Check for existing repro results
ls .data-cache/repos/{owner}-{repo}/ai-repro/{number}.json 2>/dev/null
  • Default behavior: Skip issues that already have a triage JSON file. Skip reproduction for issues that already have a repro JSON file. Report skipped issues in the summary with a ⏩ icon.
  • Force re-processing: If the user explicitly says "force", "re-triage", "re-process", "redo", or "again", process all issues regardless of existing results.
  • Present skip info: Before proceeding, show the user how many will be skipped vs processed:
    Found 33 issues. 15 already triaged, 12 already reproduced.
Will triage: 18 | Will reproduce: 21
Show full SKILL.md (325 more words)Show less

Phase 2 — Triage (parallel)

Triage is read-only — safe to parallelize.

Launch one general-purpose background agent per issue. Each agent's prompt is exactly:

triage issue {number}

This triggers the issue-triage skill in each agent.

Steps:

  1. Launch all agents with mode: "background" via the task tool. Collect all returned agent_id values.
  2. Call read_agent for each agent_id with wait: true, timeout: 300. You can call multiple read_agent in parallel.
  3. If any agent is still running after 300s, call read_agent again with another 300s timeout (600s total max).
  4. From each agent's response, extract the Type, Severity, and suggested Action from the triage summary. Look for patterns like Type: type/bug (0.95), Severity: high, Action: needs-investigation in the response text.
  5. If an agent's response does not mention issue-triage or ai-triage, it failed to invoke the skill — report it.

Batch size limit: Launch at most 12 agents at once. If more issues, wait for the current batch to complete before launching the next.

Phase 3 — Reproduce (serial)

Reproduction may build projects, create files, open simulators — must run in series.

Launch one general-purpose sync agent per issue, sequentially. Each agent's prompt is exactly:

reproduce issue #{number}

This triggers the issue-repro skill in each agent.

Steps:

  1. For each issue in order, launch a task agent with mode: "sync". The call blocks until the agent completes.
  2. From the agent's response, extract the Conclusion (one of: reproduced, not-reproduced, needs-platform, needs-hardware, inconclusive, partial). Look for Conclusion: in the response text.
  3. Continue to the next issue regardless of the previous result.

Phase 4 — Summary

Present a consolidated summary table using data extracted from the agent responses in Phases 2 and 3:

## Bulk Process Results

| # | Issue | Type | Severity | Triage Action | Repro Conclusion |
|---|-------|------|----------|---------------|------------------|
| 1 | #3400 | Bug | medium | needs-investigation | ⏭️ needs-platform |
| 2 | #3472 | Bug | medium | needs-investigation | ❌ reproduced |
...

### Stats
- Triaged: {N}
- Reproduced: {reproduced}
- Not reproduced: {not_reproduced}
- Blocked (needs-platform/hardware): {blocked}
- Inconclusive: {inconclusive}

Conclusion icons: ❌ reproduced · ✅ not-reproduced · ⏭️ needs-platform/hardware · ❓ inconclusive · ⏱️ timeout · ⏩ skipped (already processed)

Error Handling

SituationAction
Agent times out after 600s totalRecord as ⏱️ timeout in the summary and continue
Agent response doesn't mention the skillRecord as failed in the summary and continue
GitHub API fails for "newest N"Ask user to provide explicit issue numbers

© mono, MIT. 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 .agents/skills/issue-bulk-process of mono/SkiaSharp.

Open the folder on GitHubat commit a74f7f9

Compare with similar skills

Issue Bulk Process 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 Bulk Process compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Issue Bulk Process this skillmono/SkiaSharp5.6k—~1.6kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Greplooponyx-dot-app/onyx32k4 repos~3.3kAutomated safety check: PassMIT
Check PRonyx-dot-app/onyx32k2 repos~2.3kAutomated safety check: PassMIT
Setup Matt Pocock Skillsbestofjs/bestofjs3.1k20 repos~1.7kAutomated safety check: PassMIT
Contributor-First PR MergeHKUDS/OpenHarness16k1 repos~847Automated safety check: PassMIT

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

  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k 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

  • Setup Matt Pocock Skills

    bestofjs/bestofjs

    Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout.

    3.1k GitHub starsUsed in 20 repos~1.7k 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

More from mono/SkiaSharp

All 23 skills in this repo

  • Issue Fix

    mono/SkiaSharp

    Fix bugs in SkiaSharp C bindings. An agent skill from mono/SkiaSharp.

    5.6k GitHub stars~5.1k tokensUpdated today
    Auto-check passed

  • Issue Repro

    mono/SkiaSharp

    Reproduce a SkiaSharp issue systematically and capture structured reproduction results.

    5.6k GitHub stars~4.7k tokensUpdated today
    Auto-check passed

  • Issue Triage

    mono/SkiaSharp

    Triage a SkiaSharp GitHub issue or PR into structured JSON with classification (type, area, platform, severity), suggested response, automatable actions, and companion Markdown/HTML reports.

    5.6k GitHub stars~3.4k tokensUpdated today
    Auto-check passed

  • Native Dependency Update

    mono/SkiaSharp

    Update native dependencies (libpng, libexpat, zlib, libwebp, harfbuzz, freetype, libjpeg-turbo, etc.) in SkiaSharp's Skia fork.

    5.6k GitHub stars~4.1k tokensUpdated today
    Auto-check passed

  • Review Skia Update

    mono/SkiaSharp

    Review a Skia upstream merge PR in mono/skia. An agent skill from mono/SkiaSharp.

    5.6k GitHub stars~1.6k tokensUpdated today
    Auto-check passed

  • Sample Scout

    mono/SkiaSharp

    Scout Skia GM (golden master) samples in the externals/skia submodule to find demos worth porting to the SkiaSharp Gallery.

    5.6k GitHub stars~1.5k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Issue Bulk Process

What does Issue Bulk Process do?

Bulk triage and reproduce multiple SkiaSharp GitHub issues in a single command. Issue Bulk Process is an agent skill from mono/SkiaSharp. Bulk triage and reproduce multiple SkiaSharp GitHub issues in a single command.

When should I use Issue Bulk Process?

Issue Bulk Process fits situations like: development work in your project.

How do I install Issue Bulk Process in Claude Code?

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

How do I install Issue Bulk Process in Codex?

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

Can I use Issue Bulk Process 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 mono/SkiaSharp --skill issue-bulk-process -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-bulk-process, .gemini/skills/issue-bulk-process, .github/skills/issue-bulk-process and .opencode/skills/issue-bulk-process in your project.

What does Issue Bulk Process need to run?

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

Does Issue Bulk Process access the network?

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

Is Issue Bulk Process 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 Bulk Process use?

Issue Bulk Process 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 Issue Bulk Process use?

About 1.6k tokens (SKILL.md is roughly 6.4k 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 Bulk Process?

Skills that share tags, products or a category with Issue Bulk Process: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Greploop (onyx-dot-app/onyx, 32k stars), Check PR (onyx-dot-app/onyx, 32k stars) and Setup Matt Pocock Skills (bestofjs/bestofjs, 3.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Issue Bulk Process?

mono (a GitHub organization) maintains it in mono/SkiaSharp, which has 5,585 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on October 7, 2026.

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