菜单
This skill should be used when posting to GitHub — creating issues, PR comments, PR reviews, or issue comments. Provides the signature format, project SHA retrieval pattern, and safe numbering conventions. Required for every GitHub post from a Forge agent or interactive session.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | forge-signature |
| description | This skill should be used when posting to GitHub — creating issues, PR comments, PR reviews, or issue comments. Provides the signature format, project SHA retrieval pattern, and safe numbering conventions. Required for every GitHub post from a Forge agent or interactive session. |
Any Claude Code session running with the Forge plugin that posts content externally (GitHub issues/PRs, etc.) must include a signature footer that provides traceability back to the project commit used to generate the content.
This applies to:
---
*Via Forge ({agent_name}) • {commit_sha}*
---
*Via Forge (code-reviewer) • a3f2c1b*
---
*Via Forge (implementation-worker) • 1d2891e*
---
*Via Forge (interactive) • bc4ca11*
Concise: 35-45 characters typical length Professional: Italic footer matches existing GitHub patterns Unobtrusive: Separator line provides visual boundary Traceable: Short SHA (7 chars) links to specific project context
Use this bash pattern to retrieve the project commit SHA:
PROJECT_SHA=$(cd "${CLAUDE_PLUGIN_ROOT}/.." 2>/dev/null && \
git rev-parse --short HEAD 2>/dev/null || echo "unknown")
How it works:
$CLAUDE_PLUGIN_ROOT points to the plugin directorygit rev-parse --short HEAD to get the commit SHACRITICAL: Variables must be expanded by the shell, not written literally. In bash, quoting a heredoc delimiter suppresses variable expansion.
# WRONG — variables not expanded:
gh pr comment 123 --body "$(cat <<'EOF'
*Via Forge (interactive) • $PROJECT_SHA*
EOF
)"
# CORRECT — variables are expanded (unquoted delimiter):
PROJECT_SHA=$(cd "${CLAUDE_PLUGIN_ROOT}/.." && \
git rev-parse --short HEAD 2>/dev/null || echo "unknown")
gh pr comment 123 --body "$(cat <<EOF
Comment content here.
---
*Via Forge (interactive) • ${PROJECT_SHA}*
EOF
)"
PROJECT_SHA=$(cd "${CLAUDE_PLUGIN_ROOT}/.." && \
git rev-parse --short HEAD 2>/dev/null || echo "unknown")
gh issue create --repo owner/repo \
--title "Issue title" \
--body "$(cat <<EOF
Issue content here.
---
*Via Forge (ticket-creator) • ${PROJECT_SHA}*
EOF
)"
PROJECT_SHA=$(cd "${CLAUDE_PLUGIN_ROOT}/.." && \
git rev-parse --short HEAD 2>/dev/null || echo "unknown")
gh pr comment 123 --body "$(cat <<EOF
Comment content here.
---
*Via Forge (implementation-worker) • ${PROJECT_SHA}*
EOF
)"
Use these agent identifiers in signatures:
| Agent Name | Usage |
|---|---|
interactive | Interactive sessions posting to GitHub |
ticket-creator | Creating GitHub issues |
pr-discussion-processor | Replying to PR discussions |
implementation-worker | PR self-review comments |
code-reviewer | Code review comments |
When to use "interactive":
Any Claude Code session with Forge posting to GitHub:
When creating numbered lists in posts that are later
referenced in a summary, use item words not #N notation
to avoid GitHub auto-linking to issues.
❌ Bad: "Must fix: #1, #2" (GitHub links to issues 1 and 2)
✅ Good: "Must fix: Items 1, 2"
See the github-posting guidelines in your documentation for complete patterns.
Create and manage Flox development environments. Use when setting up a project environment during /forge:init, when a user asks to add a Flox environment, or when detecting and installing project dependencies. Covers flox init, search, install, manifest basics, and language-specific patterns. For advanced topics (services, builds, CUDA, layering, containers), suggest the full flox plugin.
This skill should be used when "restructuring commits", "organizing PR history", "making commits reviewable", or planning how to split work into atomic commits. The intellectual foundation for /reviewable. Do not use for writing commit messages (see git workflow guideline).
This skill should be used when the user redirects, corrects, or refines agent output — "no, actually", "that's not right", "you missed something". Captures correction moments to improve Forge workflows over time. Always active during feature work; log corrections as they occur.
This skill should be used when the user asks "what is an effort", "effort phases", "how do efforts work", "effort vs slice", or needs to understand the effort lifecycle. Covers the five phases: initialize, story capture, requirements, slice identification, and slice spawning.
Surface Forge plugin documentation when users ask "how does forge work", "forge help", "what commands are available", or need guidance on workflows, commands, or concepts. Use for onboarding, command reference, or workflow overview questions.
This skill should be used when a command needs the full implement-and-review cycle — spawning an implementation worker, running a code review gate, and making a post-review decision. Used by /forge:start-task and /implement. Do not use for review-only or implementation-only workflows.