Skip to content
Agentmart
Submit a tool

report-bugs

Write concise exploratory-testing bug reports for reliably reproducible specification violations or behavior obviously wrong in context.

Skill by testobsessed

IndexedMIT
Write a review

Chalk Labs

Need help deploying report-bugs?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/testobsessed-report-bugs

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Write concise exploratory-testing bug reports for reliably reproducible specification violations or behavior obviously wrong in context. Record reports in the current session log; keep uncertain or unreliable failures as observations.

Use cases: documents, testing, writing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/report-bugs

What's inside

Skill name
report-bugs
Description
Write concise exploratory-testing bug reports for reliably reproducible specification violations or behavior obviously wrong in context. Record reports in the current session log; keep uncertain or unreliable failures as observations.
License
MIT
Instructions
27 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Bug Reporting

The explorer surfaces risks and information. Make judgments needed to choose what to explore and describe findings; leave severity and priority to the reviewer. Resolving product uncertainty is not the explorer’s responsibility.

This skill owns the distinction between an observation and a bug report. Oracle and invariant guidance supplies expectations; it does not add a requirement for stakeholder agreement before reporting behavior that meets the criteria below.

## Observation or bug report

When the specification does not state expected behavior, use judgment about what is reasonable, informed by the domain research already available. Log the expectation and actual observation and flag an uncertain concern as a potential problem. Do not require agreement or resolution before supplying that information.

A bug report is warranted when observed behavior violates a specification, if one exists, or is obviously wrong in context, and the problem can be reproduced reliably. For example, a valid last name such as O’Brien causing a catastrophic error on a contact or profile form is obviously wrong: the user took a reasonable action. This example does not establish the technical cause.

Isolate the simplest steps that still reproduce the problem. If a failure cannot be reproduced reliably, keep it in Observations rather than promoting it to a bug report.

## Report contents and destination

Append each report in a `Bug reports` section of the current session’s exploration log. Include:

- A short descriptive title capturing the failure or incorrect behavior.
- The simplest reproducible steps, including input or conditions necessary to reproduce it.
- The nature of the problem as observed, the expectation, and actual observed behavior.

Link supporting observations where useful. Keep reports concise for readers with basic project context; do not expand them to educate readers about the project. Do not assign severity or priority.

Stick to what the explorer observed. Unless the caller explicitly requests otherwise, do not spend exploration effort locating the exact code defect, offering a suspected cause, or fixing it. Reproducible steps can be handed to another agent to locate and fix the defect without duplicating that agent’s work.

From testobsessed/exploratory-testing-skills, MIT.

More from testobsessed/exploratory-testing-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 4, 2026 (27 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from testobsessed

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get report-bugs running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying report-bugs?

CallGet help
Cite this page

report-bugs skill. Agent Mart. https://agentmart.dev/skills/testobsessed-report-bugs (last updated 2026-10-24)