PR Review State Fetch
prisma/orm
Fetches a pull request's canonical review state as JSON, validates it, and renders markdown, a text summary and triage target files from it using bundled scripts.
Loops on a large pull request, merge request or Perforce changelist, fixing Greptile findings until it scores 5/5 with no unresolved comments.
$ npx skills add michaelshimeles/skills --skill greploop-apps -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install michaelshimeles/skills greploop-apps --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/michaelshimeles/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/greploop-apps .claude/skills/greploop-apps && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "greploop-apps" agent skill from https://github.com/michaelshimeles/skills/tree/main/greploop-apps into .claude/skills/greploop-apps/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "greploop-apps", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/michaelshimeles/skills/tree/main/greploop-appsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add michaelshimeles/skills --skill greploop-apps -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install michaelshimeles/skills greploop-apps --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/michaelshimeles/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/greploop-apps .agents/skills/greploop-apps && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "greploop-apps" agent skill from https://github.com/michaelshimeles/skills/tree/main/greploop-apps into .agents/skills/greploop-apps/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "greploop-apps", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add michaelshimeles/skills --skill greploop-apps -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install michaelshimeles/skills greploop-apps --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/michaelshimeles/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/greploop-apps .cursor/skills/greploop-apps && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "greploop-apps" agent skill from https://github.com/michaelshimeles/skills/tree/main/greploop-apps into .cursor/skills/greploop-apps/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "greploop-apps", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/michaelshimeles/skills.git --path greploop-apps--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add michaelshimeles/skills --skill greploop-apps -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install michaelshimeles/skills greploop-apps --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/michaelshimeles/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/greploop-apps .gemini/skills/greploop-apps && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "greploop-apps" agent skill from https://github.com/michaelshimeles/skills/tree/main/greploop-apps into .gemini/skills/greploop-apps/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "greploop-apps", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install michaelshimeles/skills greploop-appsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add michaelshimeles/skills --skill greploop-apps -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/michaelshimeles/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/greploop-apps .github/skills/greploop-apps && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "greploop-apps" agent skill from https://github.com/michaelshimeles/skills/tree/main/greploop-apps into .github/skills/greploop-apps/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "greploop-apps", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add michaelshimeles/skills --skill greploop-apps -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install michaelshimeles/skills greploop-apps --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/michaelshimeles/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/greploop-apps .opencode/skills/greploop-apps && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "greploop-apps" agent skill from https://github.com/michaelshimeles/skills/tree/main/greploop-apps into .opencode/skills/greploop-apps/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "greploop-apps", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
greploop-appsLoops on a large pull request, merge request or Perforce changelist, fixing Greptile findings until it scores 5/5 with no unresolved comments.
Greploop Apps runs a fix loop on a GitHub pull request, a GitLab merge request or a shelved Perforce changelist until Greptile's review reaches a 5/5 confidence score with no unresolved comments. It is the same loop as the plain greploop skill, except reviews are triggered by commenting @greptile-apps, which avoids the file-count limit that makes Greptile refuse very large PRs with a message about too many files changed. Because auto-review skips those PRs, every push needs a fresh review comment.
The agent first detects the platform, checking Perforce and then the git remote, with a --vcs flag to override for self-hosted GitLab hosts. It identifies the PR, MR or changelist, then cycles: push or re-shelve, wait for checks, trigger the review, read Greptile's findings and fix them. The loop stops after at most --max-iterations cycles, 10 by default, and reports the current state; raise it for large PRs or lower it to bound cost. Reference files document the GitLab API and GraphQL queries.
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 4b72f46. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
Bash(gh:*)Bash(glab:*)Bash(git:*)Bash(p4:*)From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
ghglabjqgitFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use gh, glab and git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Requires git, gh (GitHub CLI) or glab (GitLab CLI) authenticated, and Greptile installed on the repo. For Perforce, requires p4 CLI authenticated.
From compatibility in the SKILL.md frontmatter.
Greploop Apps loads about 3.6k tokens when it runs, and up to ~4.6k if it reads all its reference files. Until then it costs about 113 tokens; SKILL.md has 1,045 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from michaelshimeles/skills at commit 4b72f46, republished under its MIT licence (© michaelshimeles). 1,045 words, ~3,625 tokens.
.claude/skills/greploop-apps/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.Iteratively fix a PR/MR/CL until Greptile gives a perfect review: 5/5 confidence, zero unresolved comments. This variant tags @greptile-apps to trigger reviews, which bypasses the file-count limit that makes Greptile skip huge PRs (e.g. "Too many files changed for review"). Because auto-review skips those PRs, every push needs a fresh @greptile-apps review comment.
--max-iterations N (optional, default 10): cap on review-fix-push cycles before the loop stops and reports the current state. Raise it for large PRs where Greptile keeps surfacing new findings; lower it to bound cost.First check for Perforce, then fall back to git remote detection:
# Check for Perforce environment
if p4 info >/dev/null 2>&1; then
VCS="perforce"
else
REMOTE_URL=$(git remote get-url origin)
if echo "$REMOTE_URL" | grep -qi "gitlab"; then
VCS="gitlab"
else
VCS="github"
fi
fiFor self-hosted GitLab instances whose hostname doesn't contain "gitlab", the user can override by passing --vcs gitlab as an input. For Perforce, pass --vcs perforce.
GitHub:
gh pr view --json number,headRefName -q '{number: .number, branch: .headRefName}'GitLab:
glab mr view --output json | jq '{iid: .iid, branch: .source_branch}'Switch to the PR/MR branch if not already on it.
Perforce:
# List pending changelists for current user/client
p4 changes -s pending -u $P4USER -c $P4CLIENT
# Describe a specific CL
p4 describe -s <CL_NUMBER>Ensure the correct workspace (p4 client) is set before proceeding.
Key field differences:
number, headRefName, headRefOidiid, source_branch, shaP4CLIENT, shelved filesRepeat the following cycle at most --max-iterations times (default 10) to avoid runaway loops.
Push/shelve the latest changes (if any):
GitHub/GitLab:
git pushPerforce:
# Re-shelve to update the shelved files for review
p4 shelve -f -c <CL_NUMBER>Wait for checks to start after push/shelve:
sleep 5GitHub — check if Greptile is already running before posting a new trigger comment:
GREPTILE_STATE=$(gh pr checks <PR_NUMBER> --json name,state | jq -r '.[] | select(.name | test("greptile"; "i")) | .state')If Greptile is not already running (PENDING or IN_PROGRESS), request a fresh review:
if [ "$GREPTILE_STATE" != "PENDING" ] && [ "$GREPTILE_STATE" != "IN_PROGRESS" ]; then
gh pr comment <PR_NUMBER> --body "@greptile-apps review"
fiThen poll for the Greptile check run to complete:
HEAD_SHA=$(gh pr view <PR_NUMBER> --json headRefOid -q .headRefOid)
ATTEMPTS=0
MAX_ATTEMPTS=60
POLL_INTERVAL_SECONDS=10
while true; do
ATTEMPTS=$((ATTEMPTS + 1))
if [ "$ATTEMPTS" -gt "$MAX_ATTEMPTS" ]; then
echo "Timed out waiting for the Greptile check run after approximately 10 minutes." >&2
exit 1
fi
GREPTILE_CHECK=$(gh api "repos/{owner}/{repo}/commits/$HEAD_SHA/check-runs" \
--jq '.check_runs[] | select(.name | test("greptile"; "i"))' 2>/dev/null)
if [ -z "$GREPTILE_CHECK" ]; then
echo "Waiting for Greptile check to appear..."
sleep "$POLL_INTERVAL_SECONDS"
continue
fi
STATUS=$(echo "$GREPTILE_CHECK" | jq -r '.status // "completed"')
CONCLUSION=$(echo "$GREPTILE_CHECK" | jq -r '.conclusion // "pending"')
if [ "$STATUS" = "completed" ]; then
if [ "$CONCLUSION" = "success" ]; then
echo "Greptile check passed!"
else
echo "Greptile check completed with: $CONCLUSION"
fi
break
fi
echo "Waiting for Greptile... (status: $STATUS)"
sleep "$POLL_INTERVAL_SECONDS"
doneHuge-PR fallback: on PRs over Greptile's file limit, the tagged review may never create a check run for the new head — Greptile instead edits its existing summary comment when it finishes. If the check run has not appeared after a few attempts, poll the latest Greptile-authored issue comment instead and stop when its updated_at moves past the time you posted the trigger and its body carries a confidence score (rather than the "Too many files changed" notice):
gh api --paginate "repos/{owner}/{repo}/issues/<PR_NUMBER>/comments?per_page=100" \
--jq '[.[] | select(.user.login | test("greptile"; "i"))] | sort_by(.updated_at) | last | {updated_at, body}'If polling times out, stop the greploop workflow and report the timeout. Do not continue with stale or missing review results.
GitLab — check if Greptile is already running before posting a trigger comment:
PIPELINES=$(glab api "projects/:fullpath/merge_requests/<MR_IID>/pipelines")
GREPTILE_RUNNING=$(echo "$PIPELINES" | jq '[.[] | select(.status == "running" or .status == "pending")] | length')If no pipeline is running, post a trigger comment:
if [ "$GREPTILE_RUNNING" = "0" ]; then
glab mr note <MR_IID> --message "@greptile-apps review"
fiPerforce — Perforce does not have native check runs. If Greptile is integrated via a webhook triggered on p4 shelve, wait for it to process. Check your Greptile installation's webhook endpoint or dashboard for the review status. Poll by re-fetching the Greptile review comment on the CL until a score appears.
Then poll for the Greptile pipeline job to complete (see GitLab API reference):
HEAD_SHA=$(glab mr view <MR_IID> --output json | jq -r '.sha')
ATTEMPTS=0
MAX_ATTEMPTS=60
POLL_INTERVAL_SECONDS=10
while true; do
ATTEMPTS=$((ATTEMPTS + 1))
if [ "$ATTEMPTS" -gt "$MAX_ATTEMPTS" ]; then
echo "Timed out waiting for the Greptile pipeline job after approximately 10 minutes." >&2
exit 1
fi
PIPELINES=$(glab api "projects/:fullpath/merge_requests/<MR_IID>/pipelines")
# Find the most recent pipeline for this SHA
PIPELINE_ID=$(echo "$PIPELINES" | jq -r --arg sha "$HEAD_SHA" \
'[.[] | select(.sha == $sha)] | sort_by(.id) | last | .id // empty')
if [ -z "$PIPELINE_ID" ]; then
echo "Waiting for Greptile pipeline to appear..."
sleep "$POLL_INTERVAL_SECONDS"
continue
fi
JOBS=$(glab api "projects/:fullpath/pipelines/$PIPELINE_ID/jobs")
GREPTILE_JOB=$(echo "$JOBS" | jq '.[] | select(.name | test("greptile"; "i"))')
if [ -z "$GREPTILE_JOB" ]; then
echo "Waiting for Greptile job to appear..."
sleep "$POLL_INTERVAL_SECONDS"
continue
fi
JOB_STATUS=$(echo "$GREPTILE_JOB" | jq -r '.status')
if [ "$JOB_STATUS" = "success" ] || [ "$JOB_STATUS" = "failed" ] || [ "$JOB_STATUS" = "canceled" ]; then
echo "Greptile job completed with: $JOB_STATUS"
break
fi
echo "Waiting for Greptile... (status: $JOB_STATUS)"
sleep "$POLL_INTERVAL_SECONDS"
doneIf polling times out, stop the greploop workflow and report the timeout. Do not continue with stale or missing review results.
Greptile may surface its score in several places — check all of the relevant sources:
GitHub:
1. PR description (body):
gh pr view <PR_NUMBER> --json body -q '.body'2. General PR comments (issue comments):
gh api --paginate "repos/{owner}/{repo}/issues/<PR_NUMBER>/comments?per_page=100"Filter for Greptile-authored comments and use the body from the most recently updated comment (updated_at), not the most recently created comment. Greptile may edit the same general PR comment on each review cycle; parse the current body, including the "Prompt to fix all with AI" section, before deciding there are no remaining issues.
3. PR reviews:
gh api repos/{owner}/{repo}/pulls/<PR_NUMBER>/reviewsLook for the most recent entry from greptile-apps[bot] or greptile-apps-staging[bot].
GitLab:
1. MR description (body):
glab mr view <MR_IID> --output json | jq -r '.description'2. MR notes (comments):
glab api "projects/:fullpath/merge_requests/<MR_IID>/notes"Filter for notes from the Greptile bot user (check the author.username field — the exact username may vary per installation; verify on first run).
Perforce:
1. CL description:
p4 describe -s <CL_NUMBER>Check the description field for a Greptile-appended score block.
2. CL comments / review notes: If your installation uses a review tool such as Helix Swarm, fetch comments via its API.
Example (Swarm API): GET /api/v11/comments?topic=reviews/<REVIEW_ID>
Response fields of interest typically include:
Filter to comments authored by the Greptile bot:
For all platforms, parse the text for:
3/5 or 5/5 (or Confidence: 3/5).Use whichever source has the most recently updated score. For GitHub, prefer updated_at from issue comments when comparing an edited Greptile summary against older review entries.
Also fetch all unresolved inline comments:
GitHub:
gh api repos/{owner}/{repo}/pulls/<PR_NUMBER>/commentsAlso carry forward actionable items from the latest Greptile general PR comment, especially the "Prompt to fix all with AI" section, even if the inline comment endpoint returns zero unresolved comments.
GitLab:
glab api "projects/:fullpath/merge_requests/<MR_IID>/discussions"Filter to DiffNote type discussions (notes[0].type == "DiffNote") from Greptile that are on the latest commit and not yet resolved ("resolved": false).
Perforce: If using Swarm:
GET /api/v11/comments?topic=reviews/<REVIEW_ID>
Filter to comments from the Greptile bot user that have not been marked as resolved/addressed.
Stop the loop if any of these are true:
--max-iterations reached (report current state)For each unresolved Greptile comment:
GitHub — fetch unresolved review threads and resolve all that have been addressed (see GraphQL reference):
gh api graphql -f query='
query($cursor: String) {
repository(owner: "OWNER", name: "REPO") {
pullRequest(number: PR_NUMBER) {
reviewThreads(first: 100, after: $cursor) {
pageInfo { hasNextPage endCursor }
nodes {
id
isResolved
comments(first: 1) {
nodes { body path author { login } }
}
}
}
}
}
}'Resolve addressed threads:
gh api graphql -f query='
mutation {
t1: resolveReviewThread(input: {threadId: "ID1"}) { thread { isResolved } }
t2: resolveReviewThread(input: {threadId: "ID2"}) { thread { isResolved } }
}'GitLab — fetch unresolved discussions and resolve each one (see GitLab API reference):
glab api "projects/:fullpath/merge_requests/<MR_IID>/discussions?per_page=100"Filter for "resolved": false discussions. Then resolve each by its id:
glab api --method PUT \
"projects/:fullpath/merge_requests/<MR_IID>/discussions/<DISCUSSION_ID>" \
--field resolved=trueRepeat for each unresolved discussion ID. (GitLab has no batch resolution — loop through each one.)
GitHub/GitLab:
git add -A
git commit -m "address greptile review feedback (greploop iteration N)"
git pushPerforce:
# Stage changes back into the CL and re-shelve for the next review round
p4 shelve -f -c <CL_NUMBER>Wait for checks to start after push/shelve:
sleep 5Then go back to step A.
After exiting the loop, summarize:
| Field | Value |
|---|---|
| Platform | GitHub / GitLab / Perforce |
| Iterations | N |
| Final confidence | X/5 |
| Comments resolved | N |
| Remaining comments | N (if any) |
If the loop exited due to max iterations, list any remaining unresolved comments and suggest next steps.
Greploop complete.
Platform: GitHub
Iterations: 2
Confidence: 5/5
Resolved: 7 comments
Remaining: 0If not fully resolved (<N> is the effective cap — the --max-iterations value supplied, or 10 by default):
Greploop stopped after <N> iterations (--max-iterations <N>).
Platform: GitLab
Confidence: 4/5
Resolved: 12 comments
Remaining: 2
Remaining issues:
- src/auth.ts:45 — "Consider rate limiting this endpoint"
- src/db.ts:112 — "Missing index on user_id column"Perforce example:
Greploop complete.
Platform: Perforce
Changelist: 12345
Iterations: 3
Confidence: 5/5
Resolved: 9 comments
Remaining: 0© michaelshimeles, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 3 other files (references) in greploop-apps of michaelshimeles/skills.
Open the folder on GitHubat commit 4b72f46
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in michaelshimeles/skills, which our catalogue first saw on October 7, 2026.
Greploop Apps next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Greploop Apps this skillmichaelshimeles/skills | 1.3k | 1 repos | ~3.6k | Automated safety check: Pass | MIT | |
| PR Review State Fetchprisma/orm | 48k | — | ~767 | Automated safety check: Pass | Apache-2.0 | |
| Visual Reviewai-dynamo/dynamo | 8.3k | — | ~4.5k | Automated safety check: Pass | Apache-2.0 | |
| PR Triagertk-ai/rtk | 83k | — | ~2.5k | Automated safety check: Notes | Apache-2.0 | |
| Difit Reviewyoshiko-pg/difit | 3.2k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Address PR Feedback for ruby-gitruby-git/ruby-git | 1.8k | — | ~657 | Automated safety check: Pass | MIT |
prisma/orm
Fetches a pull request's canonical review state as JSON, validates it, and renders markdown, a text summary and triage target files from it using bundled scripts.
ai-dynamo/dynamo
Create self-contained interactive HTML code-review dashboards from GitHub or GitLab pull requests, checked-out branch diffs, or supplied unified diffs, with correctness and safe-to-merge scores…
rtk-ai/rtk
Audits a repository's open pull requests, deep-reviews chosen ones and drafts review comments that are only posted after you approve them.
yoshiko-pg/difit
Review a specific diff (branch, commit, or GitHub PR) and show the findings as comments inside difit, the local diff viewer.
ruby-git/ruby-git
Addresses unresolved pull request review threads and suppressed (low-confidence) Copilot review comments on the current branch, folds each fix into the…
pytorch/executorch
Reviews ExecuTorch pull requests or local branches for what CI cannot check, using a checklist, with an optional detailed line-by-line mode.
michaelshimeles/skills
Captures before and after screenshots of two URLs or images with the Vercel before-and-after CLI, uploads them and can add a markdown comparison to a pull request.
michaelshimeles/skills
Records an annotated screen recording of the agent testing an app hands-on, then posts the video and a results summary to the PR and tracker issue.
michaelshimeles/skills
Start a new task in an isolated Git worktree branched from origin/main so multiple agents can work on the same repo in parallel without conflicts.
Categories
Loops on a large pull request, merge request or Perforce changelist, fixing Greptile findings until it scores 5/5 with no unresolved comments. Greploop Apps runs a fix loop on a GitHub pull request, a GitLab merge request or a shelved Perforce changelist until Greptile's review reaches a 5/5 confidence score with no unresolved comments. It is the same loop as the plain greploop skill, except reviews are triggered by commenting @greptile-apps, which avoids the file-count limit that makes Greptile refuse very large PRs with a message about too many files changed.
Greploop Apps fits situations like: A large PR that Greptile will not review because too many files changed; driving a GitLab merge request to a clean Greptile review; iterating on a shelved Perforce changelist against Greptile feedback; capping review-fix-push cycles with a maximum iteration count.
Run `npx skills add michaelshimeles/skills --skill greploop-apps -a claude-code`. Or copy the skill folder (greploop-apps in michaelshimeles/skills) into .claude/skills/greploop-apps in your project. Claude Code loads it when a task matches its description.
Run `npx skills add michaelshimeles/skills --skill greploop-apps -a codex`. Or copy the skill folder (greploop-apps in michaelshimeles/skills) into .agents/skills/greploop-apps in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add michaelshimeles/skills --skill greploop-apps -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/greploop-apps, .gemini/skills/greploop-apps, .github/skills/greploop-apps and .opencode/skills/greploop-apps in your project.
Going by SKILL.md and its folder, Greploop Apps needs the command-line tools its instructions call (gh, glab, jq and git). Our summary lists: git; An authenticated gh (GitHub CLI) or glab (GitLab CLI); Greptile installed on the repository; An authenticated p4 CLI for Perforce. Its frontmatter pre-approves these tools: Bash(gh:*), Bash(glab:*), Bash(git:*), Bash(p4:*). Compatibility (from SKILL.md): Requires git, gh (GitHub CLI) or glab (GitLab CLI) authenticated, and Greptile installed on the repo. For Perforce, requires p4 CLI authenticated..
SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Greploop Apps is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.6k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 988 tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Greploop Apps: PR Review State Fetch (prisma/orm, 48k stars), Visual Review (ai-dynamo/dynamo, 8.3k stars), PR Triage (rtk-ai/rtk, 83k stars) and Difit Review (yoshiko-pg/difit, 3.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
michaelshimeles (a GitHub user) maintains it in michaelshimeles/skills, which has 1,274 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 4, 2026.
Source: michaelshimeles/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.