Stats
Actions
Tags
How this skill is triggered — by the user, by Claude, or both
Slash command
/dev-harness:audit-skillopusThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
单 Skill 模式：只运行 audit 阶段。
单 Skill 模式：只运行 audit 阶段。
bash "${CLAUDE_PLUGIN_ROOT}/scripts/dh-python.sh" "${CLAUDE_PLUGIN_ROOT}/scripts/harness.py" \
init "code-audit" --route C --mode single --skills audit
python "${CLAUDE_PLUGIN_ROOT}/scripts/skill-resolver.py" audit.claude/reports/audit-*.mdbash "${CLAUDE_PLUGIN_ROOT}/scripts/dh-python.sh" "${CLAUDE_PLUGIN_ROOT}/scripts/harness.py" update audit DONE
npx claudepluginhub brothelmdzz/dev-harness --plugin dev-harnessProvides 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.