Skip to main content
ClaudeWave
Skill428 estrellas del repoactualizado today

swarm-pr-review

swarm-pr-review executes a multi-stage pull request analysis using parallel exploration lanes to identify potential issues, independent reviewer validation to confirm findings with file:line evidence, and critic challenges to stress-test conclusions. Use this skill when conducting deep code reviews where false positives are costly, existing PR feedback requires validation, or merge conflicts and bot findings need resolution with high confidence.

Instalar en Claude Code
Copiar
git clone --depth 1 https://github.com/ZaxbyHub/opencode-swarm /tmp/swarm-pr-review && cp -r /tmp/swarm-pr-review/.claude/skills/swarm-pr-review ~/.claude/skills/swarm-pr-review
Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

SKILL.md

# Swarm PR Review

Read and follow `../../../.opencode/skills/swarm-pr-review/SKILL.md` as the
canonical workflow.

## Claude Code Execution Notes

- `PR_REVIEW` is read-only with respect to the PR branch. You may fetch refs,
  inspect metadata, and check out the PR head after verifying a clean working
  tree, but do not fix code, resolve conflicts, commit, push, rebase, or reset
  from this mode.
- Ingest every review signal before explorer lanes: PR comments,
  review summaries, requested changes, bot findings, CI/check failures,
  mergeability/conflicts, stale branch/base drift, PR body claims, linked
  issues, and commit messages.
- Treat every ingested signal as a claim until reviewer validation proves or
  disproves it with file:line evidence or explicit counter-evidence.
- Prefer GitHub connector tools when available, or `gh`, to inspect PR metadata,
  comments, review threads, checks, conflicts, and head SHA.
- Use the canonical deterministic lane flow: `dispatch_lanes_async` plus
  `collect_lane_results`, falling back to blocking `dispatch_lanes` only when
  async collection is unavailable.
- When lane results include `output_ref`, call `parse_lane_candidates` and use
  the structured candidates for reviewer dispatch; degraded or incomplete
  outputs are coverage gaps.
- If actionable findings remain, write the handoff artifact described by the
  canonical skill and ask the user whether to continue with
  `swarm-pr-feedback`.

Do not improvise a fix path from review mode. If the user approves follow-up
work, switch to `swarm-pr-feedback` and carry validated findings forward with
their original IDs and provenance.