Forge Report — Git skill for Claude Code
File a harness failure as a Forge diagnostics ticket (Firestore → GitHub issue, no GitHub account needed).
How to install Forge Report
Installs to ~/.claude/skills/benchagi-bench-cowork-forge-report/SKILL.md
mkdir -p ~/.claude/skills/benchagi-bench-cowork-forge-report && curl -fsSL https://raw.githubusercontent.com/BenchAGI/bench-cowork/HEAD/commands/forge-report.md -o ~/.claude/skills/benchagi-bench-cowork-forge-report/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Forge Report does
name: forge-report description: File a harness failure as a Forge diagnostics ticket (Firestore → GitHub issue, no GitHub account needed). Calls the bench-forge MCP's forge_submit_diagnostics tool and polls forge_ticket_status for the issue URL.
File `$ARGUMENTS` as a Forge diagnostics ticket.
If `$ARGUMENTS` is a file path (e.g. `~/Downloads/diagnostics.md`), read it and use it as the runbook body. If it's a freeform description, gather the failing output from the current conversation
Alternatives in Git
- Triage Open Pull Requests — Review, label, and act on all open PRs for a repository using parallel review agents 10.8k ★
- Claude Relay Service — GitHub Repo stars Self-built Claude code mirror service supporting multi-account switching Relay service 9.9k ★
- GitHub Review Failures — Use when CI checks are failing on a PR — fetches failure logs, diagnoses root causes, implements fixes, and pu 1.5k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Land Ticket
Publish + close a ticket — open the Linear-linked PR if needed, analyze conflicts by reading code, resolve, mi
Submit Feedback
Report a bug or request a feature for the pyramid-principle plugin — drafts a GitHub issue and files it only a
提交资源 Submit Resource
🐛 报告问题 Report Issue
Poll CI
Polls the current branch's CI run and reports pass/fail/in-progress (fallback for monitor-ci)
Bug Fixer
Engineering Workflow Directive — Bug Remediation & Diagnostics. Sweeps every open confirmed-bug issue unattend
Bench Setup
Build a new benchmark scope tailored to the user's task. Four-question intake plus a provider picker; accepts
Related Agents
Forge Deployment
Forge's Deployment & Rollback agent — polls a health-check endpoint after a deploy and reports pass/fail, with
Secretary Monitor
Gatekeeper daemon. Polls messages, filters noise, reports important ones. Exits after each cycle (harness resp
Grind
Runs multi-step shell work — fleet/ssh sweeps, build+deploy, test-harness runs, service polls. Use when the ne