From dev-team
Summarizes code review results into a compact markdown file saved to disk. Useful after /code-review or when user says 'summarize the review'.
How this skill is triggered — by the user, by Claude, or both
Slash command
/dev-team:review-summary [--from <json-file>][--from <json-file>]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Role: orchestrator. This skill summarizes and persists review results — it does not review code.
Role: orchestrator. This skill summarizes and persists review results — it does not review code.
You have been invoked with the /review-summary skill. Generate a compact summary of the most recent code review.
Arguments: $ARGUMENTS
--from <json-file>: Read review results from a JSON file (output
of /code-review --json). If not provided, summarize from the
most recent /code-review output in the conversation.If --from is specified, read the JSON file. Otherwise, look for
the most recent code review results in the current conversation
context.
Extract: overall status, agent statuses, issue counts by severity, and top issues.
Write a summary under 150 words following this template:
## Review: <branch> @ <short-sha> — <date>
**Status**: <PASS|WARN|FAIL> (<N> agents, <N> issues)
**Findings**:
- <top 3-5 findings, one line each, severity prefix>
**Blocked by**: <agent names that returned fail, or "none">
**Action items**: <1-3 concrete next steps>
Write the summary to .claude/review-summaries/<date>-<short-sha>.md.
Create the .claude/review-summaries/ directory if it doesn't exist.
Display the summary to the user. Note that it will be available as context in future sessions.
npx claudepluginhub bdfinst/agentic-dev-team --plugin dev-teamOrchestrates code review by running review agents and static analysis gates. Use before commits or PRs to get structured feedback.
Produces ultra-compressed, one-line code review comments with location, problem, and fix. Cuts noise while preserving actionable signal.
Use this skill when posting the final summary comment after all inline comments are posted. Apply as the LAST step of code review after all findings are classified and inline comments are complete. Detects context (agent mode sticky comment, GitHub Actions MCP tool, or local file) and routes output accordingly.