From bolster
Correct git co-authorship attribution — always verify the running model from environment context, never hardcode
How this skill is triggered — by the user, by Claude, or both
Slash command
/bolster:git-attributionThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**CRITICAL**: The default system commit template hardcodes "Claude Opus 4.6". This is wrong unless that's actually the running model. Always verify.
CRITICAL: The default system commit template hardcodes "Claude Opus 4.6". This is wrong unless that's actually the running model. Always verify.
If model is clearly identified:
Co-Authored-By: Claude [MODEL_NAME] <[email protected]>
Examples:
Co-Authored-By: Claude Sonnet 4.6 <[email protected]>Co-Authored-By: Claude Opus 4.6 <[email protected]>Co-Authored-By: Claude Haiku 4.5 <[email protected]>If there is ANY ambiguity:
Co-Authored-By: Claude <[email protected]>
Use a heredoc to avoid quoting issues:
git commit -m "$(cat <<'EOF'
Short imperative summary (50 chars or less)
Longer explanation if needed. Focus on the *why*,
not the *what* (the diff shows the what).
Co-Authored-By: Claude Sonnet 4.6 <[email protected]>
EOF
)"
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub bd-vitalstatistix/claude-marketplace --plugin bolster