MCPInstall

fusion-skill-self-report-bug

by equinorCode Quality & Workflow

Capture Fusion skill workflow failure context and guide a draft-first bug reporting flow with explicit confirmation before any GitHub mutation.

Installs
770
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/equinor/fusion-skills --skill fusion-skill-self-report-bug
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads fusion-skill-self-report-bug automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Deprecated as of 2026-03-21. This skill has been superseded by the warden agent in fusion-skills, which inlines the full bug reporting workflow and adds proactive frustration detection and skill smell inspection. Use fusion-skills instead.

Install: npx -y skills add equinor/fusion-skills fusion-skills

Self-report Fusion Skill Bugs

When to use

Use this skill when a Fusion skill workflow fails and you need a consistent, triage-ready bug report draft. Treat this as the default failure handoff for any fusion-* skill execution.

Typical triggers:

  • "a fusion-* skill failed"
  • "this skill run failed"
  • "self-report this skill error"
  • "create a bug from this workflow failure"
  • "capture this automation failure for triage"

When not to use

Do not use this skill for:

  • Feature requests or roadmap planning
  • General implementation tasks without observed failure
  • Publishing GitHub changes without explicit user confirmation

Required inputs

Collect before drafting:

  • Target repository for the bug report (default: equinor/fusion-skills)
  • Failing command or workflow step
  • Environment context (OS/shell/runtime/tooling versions if available)
  • Observed output/error evidence
  • Reproduction signal (exact steps or best-effort notes)
  • Optional parent issue number for linking

Instructions

  1. Detect or confirm failure intent.
    • If failure context is missing, ask for command used, expected behavior, actual behavior, and key error output.
  2. Capture failure context.
    • Normalize context into: command, environment, observed error/output, reproducibility, and impact.
  3. Draft locally first.
    • Write .tmp/BUG-skill-failure-<context>.md using assets/issue-templates/skill-workflow-failure-bug.md.
    • Include reproducible steps and explicit observed/expected behavior.
  4. Propose issue metadata.
    • Recommend issue type: Bug.
    • Recommend labels for reliability/automation triage (for example bug, automation, reliability), then validate labels against the target repository before mutation.
    • Ask assignee preference (@me, specific user, or unassigned).
  5. Offer optional relationship linking.
    • If parent issue is provided, prepare to link the new bug as a sub-issue after issue creation.
  6. Ask explicit publish confirmation.
    • Do not run any GitHub mutation until the user explicitly confirms publish.
  7. Mutate only after confirmation.
    • Create issue via MCP issue mutation.
    • Apply labels/assignee.
    • If parent issue was provided, link as sub-issue.
  8. If confirmation is not provided, stop after draft.
    • Return status No GitHub state changes made.

Expected output

Return:

  • Draft bug report file path under .tmp/
  • Captured failure-context summary (command, environment, observed output)
  • Proposed title/body and reproduction steps
  • Proposed issue type + labels + assignee plan
  • Optional parent issue linking plan
  • Explicit status: Awaiting publish confirmation or No GitHub state changes made
  • Created issue URL/number only after confirmed mutation

Safety & constraints

Never:

  • Perform GitHub create/edit/comment/close actions without explicit confirmation
  • Claim failure evidence that was not provided or observed
  • Request or expose secrets/credentials

Always:

  • Keep draft-first behavior
  • Prefer minimal reproducible detail over long narrative
  • Validate label existence in the target repository before applying

FAQ

What does the fusion-skill-self-report-bug skill do?

Capture Fusion skill workflow failure context and guide a draft-first bug reporting flow with explicit confirmation before any GitHub mutation.

How do I install fusion-skill-self-report-bug?

Run npx skills add https://github.com/equinor/fusion-skills --skill fusion-skill-self-report-bug in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/fusion-skill-self-report-bug/ (personal) or .claude/skills/fusion-skill-self-report-bug/ (project).

Which AI agents can use fusion-skill-self-report-bug?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is fusion-skill-self-report-bug safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains fusion-skill-self-report-bug?

It is published by equinor in equinor/fusion-skills. It has 770 recorded installs.

More from equinor/fusion-skills

View all →

fusion-issue-authoring

equinor/fusion-skills

Classify issue type, activate the matching agent mode for type-specific drafting, and enforce shared safety gates before GitHub mutation.

2.8K installs

fusion-github-review-resolution

equinor/fusion-skills

Resolves unresolved GitHub PR review threads end-to-end: evaluates whether each review comment is correct, applies a targeted fix when valid, replies with rationale when not, commits, and resolves the thread. USE FOR: unresolved review threads, PR review feedback, changes requested PRs, PR review URLs (pullrequestreview-...), fix the review comments, close the open threads, address PR feedback. DO NOT USE FOR: summarizing feedback without code changes, creating new PRs, or read-only branches.

Code Quality & Workflow2.4K installs

fusion-issue-solving

equinor/fusion-skills

Handles GitHub issue resolution end-to-end for prompts like "solve 123", "lets solve 123", "work on 123", "work on https://github.com/owner/repo/issues/123", or by pasting a direct GitHub issue URL as the request. USE FOR: solve 123, continue work on issue 123, work on https://github.com/owner/repo/issues/123, paste a GitHub issue URL for implementation work. DO NOT USE FOR: issue drafting only, PR review only, or non-implementation research.

Code Quality & Workflow2.2K installs

fusion-code-conventions

equinor/fusion-skills

Applies and explains code conventions across TypeScript, React, C, and Markdown. Enforces naming rules, file naming patterns, TSDoc and XML doc standards, inline comment intent (the why, not the what), code structure, error handling, async patterns, and dead code policy. Also enforces ADR and contributor doc decisions, and flags decisions that appear stale or misaligned with current tooling. USE FOR: convention questions, code review against project standards, applying naming rules, auditing intent comments, checking TSDoc completeness, enforcing recorded ADR decisions, and flagging stale architectural decisions. DO NOT USE FOR: security vulnerability scanning, performance profiling, runtime debugging, or generating net-new code without a review target.

Code Quality & Workflow2.2K installs

fusion-dependency-review

equinor/fusion-skills

Review dependency PRs with structured research, existing-PR-discussion capture, multi-lens analysis (security, code quality, impact), and a repeatable verdict template. USE FOR: dependency update PRs, Renovate/Dependabot PRs, library upgrade reviews, "review this dependency PR", "should we merge this update". DO NOT USE FOR: feature PRs, application code reviews, dependency automation/bot configuration, or unattended merge without confirmation.

Code Quality & Workflow2K installs

fusion-mcp

equinor/fusion-skills

Explain what Fusion MCP is and guide users through setting it up when they need Fusion-aware MCP capabilities in Copilot workflows.

AI & Agents2K installs

Popular code quality & workflow skills

View category →

grill-me

mattpocock/skills

A relentless interview to sharpen a plan or design.

Code Quality & Workflow1.4M installs

improve-codebase-architecture

mattpocock/skills

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Code Quality & Workflow1.2M installs

handoff

mattpocock/skills

Compact the current conversation into a handoff document for another agent to pick up.

Code Quality & Workflow1.1M installs

domain-modeling

mattpocock/skills

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

Code Quality & Workflow890.6K installs

codebase-design

mattpocock/skills

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

Code Quality & Workflow863.8K installs

diagnosing-bugs

mattpocock/skills

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

Code Quality & Workflow848.4K installs