greenfield-inc/pane/bug-intake

Claude Code and agent skill by greenfield-inc/pane

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Use when the person reports broken behaviour or starts a session to file a bug. Reproduces and reports. Never fixes.

Install

npx vskill@latest install greenfield-inc/pane/bug-intake

SKILL.md

Bug intake

The goal is a report someone else can act on. The first move is reproduction, not theory.

Steps

  1. Restate the symptom in one sentence and confirm it with the person. Get the environment, the account or record involved, and when it started.
  2. Reproduce it.
  • If it needs the running app, reproduce it with the `verify-app` skill, yourself or through a subagent given the steps to attempt, and collect screenshots, console output, and network failures.
  • Otherwise give a fresh-context subagent one question at a time to answer with the `gather-evidence` skill: find the failing test, collect logs, trace the code path, list touched files. Give it the question and a fresh context, not this conversation.
  1. Interpret the evidence yourself. Classify the failure early: compile, logic, race, state, integration, environment, or interface. Write three to five ranked hypotheses before reading deeply, then test them against the code and its recent history. Compare a broken path with a working one when you can. Drop a theory once the evidence rules it out, and leave choosing the fix to whoever takes the report. If only diagnostic logging would settle it, say exactly what you would add and ask first.
  2. Write the success definition: the bug is gone when what is observably true.
  3. Choose a route:
  • direct-to-implementation: obvious locus, contained change, tests exist. The report can serve as the whole task for an implementation session.
  • options-first: unclear locus, or fixing it forces a design choice. It goes to a planning session.
  • cannot-reproduce: say what was tried and what evidence would help. Stay in intake.
  1. File the report wherever the person tracks work (a GitHub issue, Linear, or another tracker). With no tracker, save it as index.html in a bundle of its own in the format at references/bug-report.md, rendered with the `page` house standard, then stop.

Banned

  • Fixes, patches, "quick" changes, refactors
  • Writing a plan
  • Presenting a hypothesis as the confirmed cause without evidence

If the person then says "fix it"

Hand it on. For direct-to-implementation, tell them to start an implementation session with the report as its source. For options-first, tell them to take the report to a planning session.

Security

  • Security scanPassed, 96 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/greenfield-inc/pane/bug-intake/badge)](https://verified-skill.com/skills/greenfield-inc/pane/bug-intake)

Something wrong with this skill or its page? Tell us.