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

Repro

by ucsandman in ucsandman/DashClaw

Turn a bug symptom into a structured, reproducible bug report — summary, environment, exact repro steps, actual vs expected, and evidence (logs, error text, failing route/test) — and then optionally…

MITAuto-check passedTesting & QA

Install Repro

skills CLI
$ npx skills add ucsandman/DashClaw --skill repro -a claude-code

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

GitHub CLI
$ gh skill install ucsandman/DashClaw repro --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/ucsandman/DashClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/repro .claude/skills/repro && 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
repro
GitHub stars
310
Token cost
~1.5k tokens
SKILL.md length
651 words
Files
1
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

Turn a bug symptom into a structured, reproducible bug report — summary, environment, exact repro steps, actual vs expected, and evidence (logs, error text, failing route/test) — and then optionally…

  • Why is this failing
  • SKILL.md covers The report format — use this…, Fill the fields cheaply —…, Then offer the regression test and What this skill does not do
  • Calls git, node and npm
  • Regression test for a bug

What it does

Repro is an agent skill from ucsandman/DashClaw. Turn a bug symptom into a structured, reproducible bug report — summary, environment, exact repro steps, actual vs expected, and evidence (logs, error text, failing route/test) — and then optionally scaffold a failing regression test that pins it. Use this the moment a bug, defect, crash, 500, wrong count, broken page, or "this used to work" is reported and you're about to start fixing it, even if the user just pastes an error or says "X is broken". A structured report makes a far better fix prompt than a raw…

Its SKILL.md is about 1.5k 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 and Building AI agents. It works with Model Context Protocol. The repository describes itself as: Remote approvals, policy checks, and execution evidence for unattended AI agents. The licence is MIT.

When your agent uses it

  • Why is this failing
  • Regression test for a bug
  • Write up this bug

Example prompts

  • “this used to work”
  • “X is broken”
  • “getting a 500”
  • “/repro”

Requirements

  • Node.js

What it can do on your machine

Read from SKILL.md and the folder at commit 704824d. 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
    • node
    • npm
    • npx

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

  • Network

    No URLs in SKILL.md. Its commands use git, 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.

  • 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

Repro loads about 1.5k tokens when it runs. Until then it costs about 187 tokens; SKILL.md has 651 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~187
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

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 ucsandman/DashClaw at commit 704824d, republished under its MIT licence (© ucsandman). 651 words, ~1,469 tokens.

Download SKILL.mdSave it as .claude/skills/repro/SKILL.md (or your agent's skills folder).
name
repro
description
Turn a bug symptom into a structured, reproducible bug report — summary, environment, exact repro steps, actual vs expected, and evidence (logs, error text, failing route/test) — and then optionally scaffold a failing regression test that pins it. Use this the moment a bug, defect, crash, 500, wrong count, broken page, or "this used to work" is reported and you're about to start fixing it, even if the user just pastes an error or says "X is broken". A structured report makes a far better fix prompt than a raw symptom and becomes the regression test that stops the bug coming back. Trigger on: repro, reproduce, bug report, file a bug, "X is broken", "getting a 500", "why is this failing", regression test for a bug, write up this bug.

repro — symptom in, structured bug report out

A raw symptom ("the decisions page is blank") is a weak fix prompt: it forces whoever fixes it to re-derive the environment, the steps, and the expected behavior from scratch, and it leaves nothing behind to prove the bug stays fixed. A structured bug report front-loads that work once, turns into a sharp fix prompt, and — its highest-value output — becomes a failing regression test that pins the defect forever.

This skill produces that report, then offers to scaffold the test. It does not fix the bug — capturing it cleanly is the whole job; hand the report to the fix (or to /systematic-debugging) afterward.

The report format — use this exact structure

Emit the report as one contiguous, pasteable block (no leading > quote markers, no mid-sentence line breaks — Wes pastes these into prompts and issues):

## BUG: <one-line summary — the observable failure, not the guessed cause>

**Severity:** <blocker | major | minor — blocker = data loss/security/prod down>
**Surface:** <page + click path, or route, or CLI command, or SDK method>

**Environment**
- Commit: <short sha> (<branch>)
- Node: <version>  ·  Platform: <os>
- Package/SDK version: <if relevant>
- Browser: <only if a UI bug>

**Steps to reproduce**
1. <exact, replayable step — real values, not "do the thing">
2. ...
3. ...

**Actual**
<what happens — verbatim error, status code, stack line, screenshot ref>

**Expected**
<what should happen, and why you believe that — cite the spec/route/test>

**Evidence**
- <log snippet, failing assertion, network response, file:line>

**First suspicion (optional)**
<one sentence — a lead, explicitly marked as unverified so it doesn't anchor>

Two rules that keep the report honest:

  • Summary = the symptom, never the guessed cause. "Decisions page renders blank" is reproducible and verifiable; "DecisionsLedgerInner crashes on null agent" is a theory that may be wrong and will mislead the fixer. Keep the theory in First suspicion, clearly fenced off.
  • Steps must be replayable by someone with none of your context. If a step reads "with the right filter set," it's not a step — name the filter and the value.

Fill the fields cheaply — don't interrogate the user

Auto-populate the boring fields before asking the user anything. From C:\Projects\DashClaw:

  • Commit + branch: git rev-parse --short HEAD and git branch --show-current
  • Node + platform: node -v; platform is win32 (this repo's dev box)
  • Version: read package.json version when the bug touches the platform or an SDK surface
  • Evidence for API bugs: reproduce the call and capture the real response — curl/the SDK against the local dev server (npm run dev, port 3000) beats quoting from memory
  • Evidence for UI bugs: the frontend-verify skill already captures console errors + failed requests to disk — pull the failing route's entry rather than clicking by hand

Only ask the user for what you genuinely can't observe: the intended behavior when it isn't written down anywhere, or repro steps for a flow you can't reach. State your assumptions and proceed rather than stalling on a round-trip.

Show full SKILL.md (287 more words)Show less

Then offer the regression test

After the report, offer: "Want me to scaffold a failing regression test that reproduces this?" A bug without a test is a bug that comes back. If yes, follow DashClaw's vitest conventions (they're non-obvious — see the notes below), write the test so it fails on today's code for the bug's reason, and say so explicitly. A regression test that passes before the fix is proving nothing.

Name it after the defect, not the function: __tests__/unit/<area>-<symptom>.regression.test.js.

DashClaw vitest conventions that will trip you up if you skip them:

  • Tests live in __tests__/ (unit/integration/smoke). Run the full suite with npx vitest run — targeted runs miss cross-file regressions.
  • No jest-dom. Use vitest's own matchers + @testing-library queries.
  • @/ resolves to app/. Mock next/navigation for anything that reads route params. A .jsx import can resolve to a .tsx file.
  • Postgres numerics come back as strings from the Neon driver — assert on the coerced value, not the raw.
  • For guard/policy behavior, prefer adding a vector to the risk-calibration golden suite over a bespoke test — that's where scoring regressions are pinned.

If the test can't be written cheaply (needs live external state, a real browser flow, a paid provider call), say so plainly and describe the manual repro instead of forcing a brittle test — a flaky test is worse than an honest note.

What this skill does not do

  • It does not fix the bug. Report, optionally pin with a test, then hand off.
  • It does not open a tracker or PR (this repo commits to main; the report is the artifact — paste it into the fix prompt, the maintainer log, or CHANGELOG).
  • It does not guess the root cause with confidence. Leads go in First suspicion, fenced and unverified.

© ucsandman, 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 .claude/skills/repro of ucsandman/DashClaw.

Open the folder on GitHubat commit 704824d

Compare with similar skills

Repro 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.

Repro compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Repro this skillucsandman/DashClaw310—~1.5kAutomated safety check: PassMIT
Builder Smoke Testmastra-ai/mastra29k—~11kAutomated safety check: NotesCustom licence
Agentacct Workflowmikehasa/agentacct766—~1.6kAutomated safety check: PassMIT
ROSClaw SimForge Validatorros-claw/rosclaw218—~2.5kAutomated safety check: PassMIT
Hands On Testktnyt/cclsp675—~1.7kAutomated safety check: PassMIT
Diff-Driven Smoke TestsSkyvern-AI/skyvern23k—~5.2kAutomated safety check: PassAGPL-3.0

Similar skills

  • Builder Smoke Test

    mastra-ai/mastra

    Smoke test the Agent Builder feature branch end-to-end against a hermetic project scaffolded by the skill (linked to the current worktree).

    29k GitHub stars~11k tokensUpdated today
    Testing & QAAuto-check: notes

  • Agentacct Workflow

    mikehasa/agentacct

    A skill your agent uses when working in a repo with agentacct MCP configured, or when asked to track coding-agent work, smoke-test agentacct integrations, or report objective AI-agent task evidence.

    766 GitHub stars~1.6k tokensUpdated 5 days ago
    Testing & QAAuto-check passed

  • ROSClaw SimForge Validator

    ros-claw/rosclaw

    Validates ROSClaw simulation workflows across MuJoCo, ROS 2, Gazebo and Isaac Sim with evidence-backed smoke tests, never touching a real robot.

    218 GitHub stars~2.5k tokensUpdated yesterday
    Testing & QAAuto-check passed

  • Hands On Test

    ktnyt/cclsp

    Performs manual hands-on testing of a web application using playwright-cli.

    675 GitHub stars~1.7k tokensUpdated 7 mo ago
    Testing & QAAuto-check passed

  • Diff-Driven Smoke Tests

    Skyvern-AI/skyvern

    Reads your git diff, writes a handful of happy-path browser smoke tests, runs them with Skyvern or Chrome DevTools MCP and posts screenshot evidence to the PR.

    23k GitHub stars~5.2k tokensUpdated yesterday
    Testing & QAAuto-check passed

  • Glance Test

    DebugBase/glance

    Run E2E browser tests on any web application using Glance MCP.

    156 GitHub stars~827 tokensUpdated 5 mo ago
    Testing & QAAuto-check passed

More from ucsandman/DashClaw

All 13 skills in this repo

  • Dashclaw Governance

    ucsandman/DashClaw

    Governance behavior for AI agents governed by DashClaw. An agent skill from ucsandman/DashClaw.

    310 GitHub stars~2.7k tokensUpdated 2 days ago
    Auto-check passed

  • Dashclaw Ship

    ucsandman/DashClaw

    The single command that gets a DashClaw change ON MAIN AND LIVE — it resolves everything blocking production, never defers, and never hands back a checklist.

    310 GitHub stars~7.2k tokensUpdated 2 days ago
    Auto-check passed

  • Muse Governance

    ucsandman/DashClaw

    Governance behavior for Muse agents governed by DashClaw. An agent skill from ucsandman/DashClaw.

    310 GitHub stars~1.7k tokensUpdated 2 days ago
    Auto-check passed

  • Build Dashclaw

    ucsandman/DashClaw

    Contribute to the DashClaw codebase — architecture, scaffolding, tests, CI

    310 GitHub stars~1.3k tokensUpdated 2 days ago
    Auto-check passed

  • Compliance Drift Evals

    ucsandman/DashClaw

    Set up compliance exports, drift detection, evaluations, scoring, and learning analytics

    310 GitHub stars~1.8k tokensUpdated 2 days ago
    Auto-check passed

  • Create Policies

    ucsandman/DashClaw

    Create and test DashClaw guard policies for agent governance

    310 GitHub stars~1.3k tokensUpdated 2 days ago
    Auto-check passed

Works with

Categories

Questions about Repro

What does Repro do?

Turn a bug symptom into a structured, reproducible bug report — summary, environment, exact repro steps, actual vs expected, and evidence (logs, error text, failing route/test) — and then optionally…. Repro is an agent skill from ucsandman/DashClaw. Turn a bug symptom into a structured, reproducible bug report — summary, environment, exact repro steps, actual vs expected, and evidence (logs, error text, failing route/test) — and then optionally scaffold a failing regression test that pins it.

When should I use Repro?

Repro fits situations like: why is this failing; regression test for a bug; write up this bug.

How do I install Repro in Claude Code?

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

How do I install Repro in Codex?

Run `npx skills add ucsandman/DashClaw --skill repro -a codex`. Or copy the skill folder (.claude/skills/repro in ucsandman/DashClaw) into .agents/skills/repro in your project. Codex loads it when a task matches its description.

Can I use Repro 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 ucsandman/DashClaw --skill repro -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/repro, .gemini/skills/repro, .github/skills/repro and .opencode/skills/repro in your project.

What does Repro need to run?

Going by SKILL.md and its folder, Repro needs the command-line tools its instructions call (git, node, npm and npx). Our summary lists: Node.js.

Does Repro access the network?

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

Is Repro 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 Repro use?

Repro 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 Repro use?

About 1.5k tokens (SKILL.md is roughly 5.9k 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 Repro?

Skills that share tags, products or a category with Repro: Builder Smoke Test (mastra-ai/mastra, 29k stars), Agentacct Workflow (mikehasa/agentacct, 766 stars), ROSClaw SimForge Validator (ros-claw/rosclaw, 218 stars) and Hands On Test (ktnyt/cclsp, 675 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Repro?

ucsandman (a GitHub user) maintains it in ucsandman/DashClaw, which has 310 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 6, 2026.

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