Weavebench Cua Reproduce
AMAP-ML/LongHorizon-Harness
Reproduce CUA-Harness experiments on WeaveBench from a GitHub checkout.
Turn a bug the user describes in DeckWerk into a GitHub issue on vsitzmann/deckwerk.
$ npx skills add vsitzmann/deckwerk --skill bug-report -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install vsitzmann/deckwerk bug-report --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/vsitzmann/deckwerk.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/bug-report .claude/skills/bug-report && 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 "bug-report" agent skill from https://github.com/vsitzmann/deckwerk/tree/main/.claude/skills/bug-report into .claude/skills/bug-report/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bug-report", 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/vsitzmann/deckwerk/tree/main/.claude/skills/bug-reportType 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 vsitzmann/deckwerk --skill bug-report -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install vsitzmann/deckwerk bug-report --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vsitzmann/deckwerk.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/bug-report .agents/skills/bug-report && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "bug-report" agent skill from https://github.com/vsitzmann/deckwerk/tree/main/.claude/skills/bug-report into .agents/skills/bug-report/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bug-report", 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 vsitzmann/deckwerk --skill bug-report -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install vsitzmann/deckwerk bug-report --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vsitzmann/deckwerk.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/bug-report .cursor/skills/bug-report && 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 "bug-report" agent skill from https://github.com/vsitzmann/deckwerk/tree/main/.claude/skills/bug-report into .cursor/skills/bug-report/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bug-report", 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/vsitzmann/deckwerk.git --path .claude/skills/bug-report--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 vsitzmann/deckwerk --skill bug-report -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install vsitzmann/deckwerk bug-report --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vsitzmann/deckwerk.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/bug-report .gemini/skills/bug-report && 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 "bug-report" agent skill from https://github.com/vsitzmann/deckwerk/tree/main/.claude/skills/bug-report into .gemini/skills/bug-report/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bug-report", 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 vsitzmann/deckwerk bug-reportInstalls 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 vsitzmann/deckwerk --skill bug-report -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/vsitzmann/deckwerk.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/bug-report .github/skills/bug-report && 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 "bug-report" agent skill from https://github.com/vsitzmann/deckwerk/tree/main/.claude/skills/bug-report into .github/skills/bug-report/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bug-report", 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 vsitzmann/deckwerk --skill bug-report -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install vsitzmann/deckwerk bug-report --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/vsitzmann/deckwerk.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/bug-report .opencode/skills/bug-report && 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 "bug-report" agent skill from https://github.com/vsitzmann/deckwerk/tree/main/.claude/skills/bug-report into .opencode/skills/bug-report/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bug-report", 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.
bug-reportTurn a bug the user describes in DeckWerk into a GitHub issue on vsitzmann/deckwerk.
Bug Report is an agent skill from vsitzmann/deckwerk. Turn a bug the user describes in DeckWerk into a GitHub issue on vsitzmann/deckwerk. Use when the user reports that the editor, presenter, agent CLI, importer, exporter, or web export misbehaves, crashes, hangs, loses work, or renders wrongly — "this is broken", "I found a bug", "it crashed when I…", "file a bug", "write a bug report", "open an issue". Also use when a bug surfaces during other work and is worth recording. Covers verifying, searching for duplicates, drafting, and filing with gh.
Its SKILL.md is about 1.4k 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 Testing & QA, covering QA and bug reports. It works with GitHub. The licence is MIT.
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 2e3fddd. 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:
gitghnodenpmnpxFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use git, gh, npm and npx, 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.
Bug Report loads about 1.4k tokens when it runs. Until then it costs about 128 tokens; SKILL.md has 684 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 vsitzmann/deckwerk at commit 2e3fddd, republished under its MIT licence (© vsitzmann). 684 words, ~1,400 tokens.
.claude/skills/bug-report/SKILL.md (or your agent's skills folder).The goal is an issue a maintainer can act on without asking a follow-up question: what happened, what should have happened, how to make it happen again, and where it was running. Never file anything without the user's explicit yes on the exact text.
Get the facts before drafting. Ask only what you cannot find out yourself.
decks/demo-deck"). If the user only has it in their own deck,
try to reproduce on decks/demo-deck or a fresh deck first; user decks
are private data and must not be attached or quoted in an issue.npm run dev), packaged app, or the
web/collab client. Collect the environment yourself (see §2).slide-agent command and its output.If the repo is at hand and the bug is cheap to confirm, confirm it: run the
focused test that covers the area (npx vitest run test/<name>.test.ts),
call the CLI, or read the code path. Say clearly in the issue what you
verified versus what the user reported. Do not fix the bug as part
of reporting it unless the user asks; a report and a fix are separate tasks.
Not everything is a bug. A feature request or a "should it work like this?" belongs in a Discussion or a conversation, not an issue; say so and offer the text anyway.
Run from the deckwerk checkout and put the results in the issue:
git rev-parse --short HEAD && git branch --show-current && git status --short | head
node -e 'const p=require("./package.json");console.log("deckwerk",p.version,"electron",p.devDependencies.electron)'
node --version
sw_vers 2>/dev/null || uname -srmFor a packaged app, ask the user for the version from the About panel instead of the checkout version. Note any uncommitted changes, because a bug on a dirty tree may be the user's own.
A duplicate costs more maintainer time than no report.
gh issue list --repo vsitzmann/deckwerk --state all --search "<distinctive words>"Search on the symptom and the component (e.g. "paste image collab", "pptx import fonts"), not on your draft title. Include closed issues: a bug that was closed as fixed and reproduces again is a regression, and saying so is the most useful report of all.
If a match exists, read it with gh issue view <n> --repo vsitzmann/deckwerk --comments. Add a comment only if you bring something new: a different
reproduction, a narrower trigger, a stack trace, the commit where it
regressed. "Happens to me too" is noise; tell the user and file nothing.
Use this shape. Keep it short; the reproduction steps are what matter.
## What happened
…
## What I expected
…
## Steps to reproduce
1. …
2. …
## Environment
- deckwerk <version> @ <sha> on <branch> (clean / dirty: …)
- Electron <version>, Node <version>
- <OS and version>
- Running as: dev checkout / packaged app / web client
## Evidence
<console or terminal output in a fenced block; screenshot path if any>
## Notes
<what was verified vs. reported; suspected code path if known, e.g. `src/main/pptxImport.ts`>
Filed by <model name> via <agent harness>.Title: component first, then the symptom, under ~70 characters.
Collab: pasted image lands on the wrong slide, not Bug with paste.
The signature line is required so a reader knows the text was machine-authored. Use your real model and harness names; if unsure, say so rather than inventing a version string.
Show the user the full title and body and wait for an explicit yes. Apply any edits they ask for and show it again if the change is material.
Only after the yes, and only if the machine can:
gh auth statusIf gh is missing or not authenticated, do not install or log in. Hand the
user the finished text and the URL
https://github.com/vsitzmann/deckwerk/issues/new to submit themselves.
Otherwise write the body to a temp file and create the issue:
gh issue create --repo vsitzmann/deckwerk --title "<title>" --body-file <path> --label bugIf the bug label does not exist, retry without --label. gh cannot
attach images; give the user the screenshot path to drag into the issue on
the web afterwards. Report the resulting URL.
decks/ other than demo-deck and
deckwerk_intro.© vsitzmann, MIT. 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 .claude/skills/bug-report of vsitzmann/deckwerk.
Open the folder on GitHubat commit 2e3fddd
Bug Report 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 |
|---|---|---|---|---|---|---|
| Bug Report this skillvsitzmann/deckwerk | 129 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Weavebench Cua ReproduceAMAP-ML/LongHorizon-Harness | 1.7k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Evidence-Driven Testingmichaelshimeles/skills | 1.3k | 1 repos | ~3.9k | Automated safety check: Pass | None | |
| Create GitHub IssueNVIDIA/OpenShell | 15k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| Triage IssuesClickHouse/clickhouse-java | 1.6k | — | ~904 | Automated safety check: Pass | Apache-2.0 | |
| Gentle AI Issue CreationGentleman-Programming/gentle-shell | 1.2k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 |
AMAP-ML/LongHorizon-Harness
Reproduce CUA-Harness experiments on WeaveBench from a GitHub checkout.
michaelshimeles/skills
Records an annotated screen recording of the agent testing an app hands-on, then posts the video and a results summary to the PR and tracker issue.
NVIDIA/OpenShell
Create GitHub issues using the gh CLI. An agent skill from NVIDIA/OpenShell.
ClickHouse/clickhouse-java
Analyzes a single GitHub issue at a time. An agent skill from ClickHouse/clickhouse-java.
Gentleman-Programming/gentle-shell
Create and triage GitHub issues from repository evidence. An agent skill from Gentleman-Programming/gentle-shell.
termio-sh/termio
Diagnose a termio hang, beachball, crash, or 'it froze again' from the evidence macOS and termio actually leave behind — live process samples, crash and CPU-burn reports, the unified log, the…
Works with
Categories
Turn a bug the user describes in DeckWerk into a GitHub issue on vsitzmann/deckwerk. Bug Report is an agent skill from vsitzmann/deckwerk. Turn a bug the user describes in DeckWerk into a GitHub issue on vsitzmann/deckwerk.
Bug Report fits situations like: the user reports that the editor; web export misbehaves; renders wrongly — this is broken; it crashed when I….
Run `npx skills add vsitzmann/deckwerk --skill bug-report -a claude-code`. Or copy the skill folder (.claude/skills/bug-report in vsitzmann/deckwerk) into .claude/skills/bug-report in your project. Claude Code loads it when a task matches its description.
Run `npx skills add vsitzmann/deckwerk --skill bug-report -a codex`. Or copy the skill folder (.claude/skills/bug-report in vsitzmann/deckwerk) into .agents/skills/bug-report 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 vsitzmann/deckwerk --skill bug-report -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bug-report, .gemini/skills/bug-report, .github/skills/bug-report and .opencode/skills/bug-report in your project.
Going by SKILL.md and its folder, Bug Report needs the command-line tools its instructions call (git, gh, node, npm and npx). Our summary lists: Node.js.
SKILL.md contains no URLs. Its commands use git, gh, npm and npx, 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.
Bug Report is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.4k tokens (SKILL.md is roughly 5.6k 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 Bug Report: Weavebench Cua Reproduce (AMAP-ML/LongHorizon-Harness, 1.7k stars), Evidence-Driven Testing (michaelshimeles/skills, 1.3k stars), Create GitHub Issue (NVIDIA/OpenShell, 15k stars) and Triage Issues (ClickHouse/clickhouse-java, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
vsitzmann (a GitHub user) maintains it in vsitzmann/deckwerk, which has 129 GitHub stars. The repository was last updated on October 6, 2026.
Source: vsitzmann/deckwerk on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.