bug-hunter

Find evidence-backed correctness bugs by tracing failing tests, crash reports, suspicious control flow, unsafe edge-case handling, regressions, decode…

Skill by ravisingh11

IndexedMIT★ 5

Write a review

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/ravisingh11-bug-hunter

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.

About

Find evidence-backed correctness bugs by tracing failing tests, crash reports, suspicious control flow, unsafe edge-case handling, regressions, decode mismatches, and broken user flows. Use when a user asks to find bugs, investigate regressions, review a changed area for defects, or as part of $full-test-suite.

Use cases: testing

Reviews

Write a review

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 and code. 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/bug-hunter

What's inside

Skill name: bug-hunter
Description: Find evidence-backed correctness bugs by tracing failing tests, crash reports, suspicious control flow, unsafe edge-case handling, regressions, decode mismatches, and broken user flows. Use when a user asks to find bugs, investigate regressions, review a changed area for defects, or as part of $full-test-suite.
License: MIT
Instructions: 34 lines in SKILL.md · view on GitHub

Files (2)

SKILL.md
openai.yaml · agents/

SKILL.md (first lines)

# Bug Hunter

Hunt for real, verifiable correctness bugs and fix candidates. Stay repo-grounded and evidence-first.

## Workflow

1. Identify the target surface from changed files, failing tests, logs, traces, or user-reported flows.
2. Inspect control flow, validation, serialization, concurrency, lifecycle handling, error paths, and state transitions.
3. Prefer a minimal repro, targeted test, or strong static proof before promoting a finding.
4. Log confirmed findings in `project-audit-findings.md`.
5. If fixing is in scope, fix one confirmed bug at a time and record verification evidence.

## Common Targets

- off-by-one or nil-path bugs
- state desynchronization and persistence errors
- decode or schema mismatches
- stale caches and partial update bugs
- race conditions, retry loops, cancellation, or lifecycle misuse
- regression risks from refactors or fallback logic

## Rules

- Do not create findings for speculative smells.
- Prefer tests or reproductions over broad assertions.
- Keep fix diffs small and reversible.

## References

- Finding format: `../_shared-project-ops/references/finding-format.md`
- Verification template: `../_shared-project-ops/references/verification-template.md`
- Rerun policy: `../_shared-project-ops/references/rerun-policy.md`

From ravisingh11/ai-software-toolkit, MIT.

Signals

Stars: 5
Forks: 10
Open issues: 0
Last commit (this folder): Aug 27, 2026 (2 months ago)
Last release: Oct 23, 2026 (5 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/ravisingh11/ai-software-toolkit
Website: ravisingh11.github.io/ai-software-toolkit/
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from ravisingh11

Cite this page

bug-hunter skill. Agent Mart. https://agentmart.dev/skills/ravisingh11-bug-hunter (last updated 2026-10-24)