vinhnx/cmd-review
NewSkillScoreMaintainedReview the current diff or selected files (usage: /review [--last-diff|--target <expr>|--file <path>|files...] [--style <style>])
Code Reviewby vinhnx
Links this skill to your agents and keeps it current with the author’s updates.
On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.
◆Coding pack
$decimalai skills pull vinhnx-cmd-review
Get this skill — curl · raw file
$curl -fsSL https://app.decimal.ai/s/vinhnx-cmd-review/SKILL.md
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.
Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents 24 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 4h ago
Yes — +13% lift · at higher cost+42% tokens0% turns46% of whole cases pass with skill (11/24)
Showing 5 of 24 cases
SkillSafety
✓ 3 of 3 passed✓Code scan15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing
✓IntentSafe
LLM judge · does the skill do what it claims
✓ContentClean
LLM judge · policy & harmful-content review
Source
Importedvinhnx / vtcode
crates/codegen/vtcode-skills/src/skills/assets/samples/cmd-review/SKILL.md
License Apache-2.0Imported 8/3/2026Version v1
Review Changes
Interpret the user input as the raw argument string that follows /review.
- Support the existing slash-style review inputs such as
--last-diff, --target <expr>, --file <path>, positional file paths, and --style <style>. - If the input is empty, review the current diff.
- Focus on bugs, regressions, correctness risks, and missing tests before any summary.
- Use concrete file and line references when you identify a finding.
- Keep findings ordered by severity and keep the high-level summary brief.
Want to see if vinhnx/cmd-review would activate on your phrasing? Try it before you install — no LLM call, no signup.