alephic-ai/claude-pr-reviewer New SkillScore Maintained Review a pull request for correctness and style, then summarize the findings. Use when the user asks for a PR review, mentions reviewing a diff, or wants feedback on changes before merging.
by alephic-ai
Use this skill Links this skill to your agents and keeps it current with the author’s updates.
On-demand On-demand: invoked explicitly — never occupies your agent's context until called.
◆ Coding pack
$ decimalai skills pull alephic-ai-claude-pr-reviewerCopy
Copy link Copy README badge Copy SKILL.md Get this skill — curl · raw file $ curl -fsSL https://app.decimal.ai/s/alephic-ai-claude-pr-reviewer/SKILL.mdCopy
how this skill behaves on real traffic · last 30 days
No production data for this skill yet — usage numbers appear here once agents start running it.
Anonymized aggregate across every org using this skill — proof from real production use, not a demo. Sign in and install to see your own agents here →
· Benchmark: with vs. without sign in to run this on your agents 23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 4d ago
No — -25% lift -41% tokens 0% turns 61% of whole cases pass with skill (14/23)
Showing 5 of 23 cases See all cases & grading →
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026
live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported alephic-ai / skref
tests/fixtures/claude-skills/claude-pr-reviewer/SKILL.md
View on GitHub ↗ License Apache-2.0Imported 8/2/2026Version v1
Contents Benchmark Live Traces Versions (1) Ratings (0)
Claude PR Reviewer A skill that reviews a pull request and reports correctness and style findings.
Workflow Read the diff with git diff and the surrounding context. Flag correctness bugs first, then style and clarity nits. Summarize findings grouped by severity. It mixes base-spec fields with Claude Code fields, so it validates only when --allow-claude-fields is set.
Want to see if alephic-ai/claude-pr-reviewer would activate on your phrasing? Try it before you install — no LLM call, no signup. Try this skill →