Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nousresearch/github-code-review
Review PRs: diffs, inline comments via gh or REST.
Passed 12 of 16 test cases with the skill, and 8 of 16 without it.
and 2 more in the full report
5 fixed11 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
After completing a local review of PR branch `pr-202`, what commands clean up the environment by switching back to `main` and force-deleting the local PR review branch?
| Checked | Without skill | With skill |
|---|---|---|
| Executes git checkout main | Missed | Passed |
| Executes git branch -D pr-202 | Passed | Passed |
The instructions your model reads when the skill loads.
Perform code reviews on local changes before pushing, or review open PRs on GitHub. Most of this skill uses plain git — the gh/curl split only matters for PR-level interactions.
github-auth skill)if command -v gh &>/dev/null && gh auth status &>/dev/null; then
AUTH="gh"
else
AUTH="git"
if [ -z "$GITHUB_TOKEN" ]; then
if _hermes_env="${HERMES_HOME:-$HOME/.hermes}/.env"; [ -f "$_hermes_env" ] && grep -q "^GITHUB_TOKEN=" "$_hermes_env"; then
GITHUB_TOKEN=$(grep "^GITHUB_TOKEN=" "$_hermes_env" | head -1 | cut -d= -f2 | tr -d '\n\r')
elif grep -q "github.com" ~/.git-credentials 2>/dev/null; then
GITHUB_TOKEN=$(uv run python "${HERMES_HOME:-$HOME/.hermes}/skills/github/github-auth/scripts/git-credential-token.py")
fi
fi
fi
REMOTE_URL=$(git remote get-url origin)
OWNER_REPO=$(echo "$REMOTE_URL" | sed -E 's|.*github\.com[:/]||; s|\.git$||')
OWNER=$(echo "$OWNER_REPO" | cut -d/ -f1)
REPO=$(echo "$OWNER_REPO" | cut -d/ -f2)
This is pure git — works everywhere, no API needed.
test cases passed, vs 8 / 16 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.