Skip to content
Agentmart
Submit a tool

diagnosing-bugs

Diagnose a difficult reproducible failure or performance regression with a focused feedback loop and evidence.

Skill by kewvydev

IndexedMIT★ 2
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/kewvydev-diagnosing-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

Diagnose a difficult reproducible failure or performance regression with a focused feedback loop and evidence.

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. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Shell scripts

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/diagnosing-bugs

What's inside

Skill name
diagnosing-bugs
Description
Diagnose a difficult reproducible failure or performance regression with a focused feedback loop and evidence.
License
MIT
Instructions
12 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (5)

  • LICENSE
  • SKILL.md
  • openai.yaml · agents/
  • upstream.md · references/
  • hitl-loop.template.sh · scripts/

SKILL.md (first lines)

# diagnosing-bugs

Use the project's existing runtime and checks to reproduce the reported symptom.
Read [the diagnosis workflow](references/upstream.md) when a structured investigation
is needed. Its optional human-feedback helper lives at `scripts/hitl-loop.template.sh`.
Keep hypotheses proportional to the failure. Capture evidence with secrets removed,
fix the demonstrated cause, verify the original symptom and relevant regressions,
and remove temporary instrumentation. Do not introduce a testing framework or
external service solely for this workflow. Record durable cross-module findings
in the project's finding register; leave incomplete work in its task record.

From kewvydev/kewvy-ai-stack, MIT.

More from kewvydev/kewvy-ai-stack

Signals

Stars
2
Forks
0
Open issues
0
Last commit (this folder)
Oct 19, 2026 (8 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/kewvydev/kewvy-ai-stack
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from kewvydev

Cite this page

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