[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7B2D9F463YZAM8CTE6BQHD7":3,"skill-same:01M7B2D9F463YZAM8CTE6BQHD7":69},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":31,"commitSha":32,"skillDirectory":33,"forksCount":14,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":36,"updatedAt":37,"install":38,"resources":50},"01M7B2D9F463YZAM8CTE6BQHD7","greploop",null,"Loop a PR through Greptile review until 5\u002F5 confidence with zero unresolved comments.","jorgesolerrr\u002Fskills","jorgesolerrr","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F92542744?v=4","01M7B2B710R5NTAHS08MWZJXB0","Jorge Soler","01M7B2B721D4CAZJH7E6ZM4ZQ5",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjorgesolerrr\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fgreptile\u002Fgreploop\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjorgesolerrr\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fgreptile\u002Fgreploop\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: greploop\ndescription: Loop a PR through Greptile review until 5\u002F5 confidence with zero unresolved comments.\ndisable-model-invocation: true\nlicense: MIT\ncompatibility: Requires git and gh (GitHub CLI) authenticated, and Greptile installed on the repo.\nmetadata:\n  author: greptileai\n  version: \"1.3\"\nallowed-tools: Bash(gh:*) Bash(git:*)\n---\n\n# Greploop\n\nIteratively fix a PR until Greptile gives a perfect review: 5\u002F5 confidence, zero unresolved comments.\n\n## Inputs\n\n- **PR number** (optional): If not provided, detect the PR for the current branch.\n\n## Instructions\n\n### 1. Identify the PR\n\n```bash\ngh pr view --json number,headRefName,headRefOid\n```\n\nSwitch to the PR branch if not already on it.\n\nKey fields: `number`, `headRefName`, `headRefOid`.\n\n### 2. Loop\n\nRepeat the following cycle. **Max 5 iterations** to avoid runaway loops.\n\n#### A. Trigger Greptile review\n\nPush the latest changes (if any):\n\n```bash\ngit push\n```\n\nCheck if Greptile is already running before posting a new trigger comment:\n\n```bash\nGREPTILE_STATE=$(gh pr checks \u003CPR_NUMBER> --json name,state --jq '.[] | select(.name | test(\"greptile\"; \"i\")) | .state')\n```\n\nIf Greptile is **not** already running (`PENDING` or `IN_PROGRESS`), request a fresh review:\n\n```bash\nif [ \"$GREPTILE_STATE\" != \"PENDING\" ] && [ \"$GREPTILE_STATE\" != \"IN_PROGRESS\" ]; then\n  gh pr comment \u003CPR_NUMBER> --body \"@greptile review\"\nfi\n```\n\nThen poll for the Greptile check run to complete. The loop runs up to 10 minutes, so run this block with a 600000 ms timeout (or in the background):\n\n```bash\nHEAD_SHA=$(gh pr view \u003CPR_NUMBER> --json headRefOid -q .headRefOid)\nATTEMPTS=0\nMAX_ATTEMPTS=60\nPOLL_INTERVAL_SECONDS=10\n\nwhile true; do\n  ATTEMPTS=$((ATTEMPTS + 1))\n  if [ \"$ATTEMPTS\" -gt \"$MAX_ATTEMPTS\" ]; then\n    echo \"Timed out waiting for the Greptile check run after approximately 10 minutes.\" >&2\n    exit 1\n  fi\n\n  GREPTILE_CHECK=$(gh api \"repos\u002F{owner}\u002F{repo}\u002Fcommits\u002F$HEAD_SHA\u002Fcheck-runs\" \\\n    --jq '.check_runs[] | select(.name | test(\"greptile\"; \"i\")) | \"\\(.status \u002F\u002F \"completed\") \\(.conclusion \u002F\u002F \"pending\")\"' 2>\u002Fdev\u002Fnull)\n\n  if [ -z \"$GREPTILE_CHECK\" ]; then\n    echo \"Waiting for Greptile check to appear...\"\n    sleep \"$POLL_INTERVAL_SECONDS\"\n    continue\n  fi\n\n  read -r STATUS CONCLUSION \u003C\u003C\u003C \"$GREPTILE_CHECK\"\n\n  if [ \"$STATUS\" = \"completed\" ]; then\n    if [ \"$CONCLUSION\" = \"success\" ]; then\n      echo \"Greptile check passed!\"\n    else\n      echo \"Greptile check completed with: $CONCLUSION\"\n    fi\n    break\n  fi\n\n  echo \"Waiting for Greptile... (status: $STATUS)\"\n  sleep \"$POLL_INTERVAL_SECONDS\"\ndone\n```\n\nIf polling times out, stop the greploop workflow and report the timeout. Do not continue with stale or missing review results.\n\n#### B. Fetch Greptile review results\n\nGreptile may surface its score in several places — check **all** of them:\n\n**1. PR description (body):**\n```bash\ngh pr view \u003CPR_NUMBER> --json body -q '.body'\n```\n\n**2. General PR comments (issue comments):**\n```bash\ngh api --paginate \"repos\u002F{owner}\u002F{repo}\u002Fissues\u002F\u003CPR_NUMBER>\u002Fcomments?per_page=100\"\n```\n\nFilter 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.\n\n**3. PR reviews:**\n```bash\ngh api repos\u002F{owner}\u002F{repo}\u002Fpulls\u002F\u003CPR_NUMBER>\u002Freviews\n```\n\nLook for the most recent entry from `greptile-apps[bot]` or `greptile-apps-staging[bot]`.\n\nParse the text for:\n- **Confidence score**: a pattern like `3\u002F5` or `5\u002F5` (or `Confidence: 3\u002F5`).\n- **Comment count**: Number of inline review comments noted in the summary.\n\n**4. Unresolved review threads** (`gh` fills `{owner}` and `{repo}`; see [GraphQL reference](references\u002Fgraphql-queries.md)):\n```bash\ngh api graphql --paginate -F owner='{owner}' -F repo='{repo}' -F pr=\u003CPR_NUMBER> -f query='\nquery($owner: String!, $repo: String!, $pr: Int!, $endCursor: String) {\n  repository(owner: $owner, name: $repo) {\n    pullRequest(number: $pr) {\n      reviewThreads(first: 100, after: $endCursor) {\n        pageInfo { hasNextPage endCursor }\n        nodes {\n          id\n          isResolved\n          comments(first: 1) {\n            nodes { body path author { login } }\n          }\n        }\n      }\n    }\n  }\n}' --jq '.data.repository.pullRequest.reviewThreads.nodes[] | select(.isResolved == false)'\n```\n\nThe unresolved comment count is the number of threads this returns.\n\nUse whichever source has the **most recently updated** score. Prefer `updated_at` from issue comments when comparing an edited Greptile summary against older review entries.\n\nAlso carry forward actionable items from the latest Greptile general PR comment, especially the \"Prompt to fix all with AI\" section, even if the thread query in B.4 returns zero unresolved threads.\n\n#### C. Check exit conditions\n\nStop the loop if **any** of these are true:\n\n- Confidence score is **5\u002F5** AND there are **zero unresolved comments**\n- Max iterations reached (report current state)\n\n#### D. Fix actionable comments\n\nFor each unresolved Greptile comment:\n\n1. Read the file and understand the comment in context.\n2. Determine if it's actionable (code change needed) or informational.\n3. If actionable, make the fix.\n4. If informational or a false positive, note it but still resolve the thread.\n\n#### E. Resolve threads\n\nResolve every thread handled in D (fixed, informational, or false positive), using the thread IDs from B.4:\n\n```bash\ngh api graphql -f query='\nmutation {\n  t1: resolveReviewThread(input: {threadId: \"ID1\"}) { thread { isResolved } }\n  t2: resolveReviewThread(input: {threadId: \"ID2\"}) { thread { isResolved } }\n}'\n```\n\n#### F. Commit and push\n\nIf `git status --porcelain` is empty after D, exit the loop and report the remaining comments as informational. Otherwise stage only the files you edited:\n\n```bash\ngit add \u003Cfiles you edited>\ngit commit -m \"address greptile review feedback (greploop iteration N)\"\ngit push\n```\n\nThen go back to step **A**.\n\n### 3. Report\n\nAfter exiting the loop, summarize:\n\n| Field              | Value      |\n| ------------------ | ---------- |\n| Iterations         | N          |\n| Final confidence   | X\u002F5        |\n| Comments resolved  | N          |\n| Remaining comments | N (if any) |\n\nIf the loop exited due to max iterations, list any remaining unresolved comments and suggest next steps.\n\n## Output format\n\n```\nGreploop complete.\n  Iterations:    2\n  Confidence:    5\u002F5\n  Resolved:      7 comments\n  Remaining:     0\n```\n\nIf not fully resolved:\n\n```\nGreploop stopped after 5 iterations.\n  Confidence:    4\u002F5\n  Resolved:      12 comments\n  Remaining:     2\n\nRemaining issues:\n  - src\u002Fauth.ts:45 — \"Consider rate limiting this endpoint\"\n  - src\u002Fdb.ts:112 — \"Missing index on user_id column\"\n```\n","# Greploop\n\nIteratively fix a PR until Greptile gives a perfect review: 5\u002F5 confidence, zero unresolved comments.\n\n## Inputs\n\n- **PR number** (optional): If not provided, detect the PR for the current branch.\n\n## Instructions\n\n### 1. Identify the PR\n\n```bash\ngh pr view --json number,headRefName,headRefOid\n```\n\nSwitch to the PR branch if not already on it.\n\nKey fields: `number`, `headRefName`, `headRefOid`.\n\n### 2. Loop\n\nRepeat the following cycle. **Max 5 iterations** to avoid runaway loops.\n\n#### A. Trigger Greptile review\n\nPush the latest changes (if any):\n\n```bash\ngit push\n```\n\nCheck if Greptile is already running before posting a new trigger comment:\n\n```bash\nGREPTILE_STATE=$(gh pr checks \u003CPR_NUMBER> --json name,state --jq '.[] | select(.name | test(\"greptile\"; \"i\")) | .state')\n```\n\nIf Greptile is **not** already running (`PENDING` or `IN_PROGRESS`), request a fresh review:\n\n```bash\nif [ \"$GREPTILE_STATE\" != \"PENDING\" ] && [ \"$GREPTILE_STATE\" != \"IN_PROGRESS\" ]; then\n  gh pr comment \u003CPR_NUMBER> --body \"@greptile review\"\nfi\n```\n\nThen poll for the Greptile check run to complete. The loop runs up to 10 minutes, so run this block with a 600000 ms timeout (or in the background):\n\n```bash\nHEAD_SHA=$(gh pr view \u003CPR_NUMBER> --json headRefOid -q .headRefOid)\nATTEMPTS=0\nMAX_ATTEMPTS=60\nPOLL_INTERVAL_SECONDS=10\n\nwhile true; do\n  ATTEMPTS=$((ATTEMPTS + 1))\n  if [ \"$ATTEMPTS\" -gt \"$MAX_ATTEMPTS\" ]; then\n    echo \"Timed out waiting for the Greptile check run after approximately 10 minutes.\" >&2\n    exit 1\n  fi\n\n  GREPTILE_CHECK=$(gh api \"repos\u002F{owner}\u002F{repo}\u002Fcommits\u002F$HEAD_SHA\u002Fcheck-runs\" \\\n    --jq '.check_runs[] | select(.name | test(\"greptile\"; \"i\")) | \"\\(.status \u002F\u002F \"completed\") \\(.conclusion \u002F\u002F \"pending\")\"' 2>\u002Fdev\u002Fnull)\n\n  if [ -z \"$GREPTILE_CHECK\" ]; then\n    echo \"Waiting for Greptile check to appear...\"\n    sleep \"$POLL_INTERVAL_SECONDS\"\n    continue\n  fi\n\n  read -r STATUS CONCLUSION \u003C\u003C\u003C \"$GREPTILE_CHECK\"\n\n  if [ \"$STATUS\" = \"completed\" ]; then\n    if [ \"$CONCLUSION\" = \"success\" ]; then\n      echo \"Greptile check passed!\"\n    else\n      echo \"Greptile check completed with: $CONCLUSION\"\n    fi\n    break\n  fi\n\n  echo \"Waiting for Greptile... (status: $STATUS)\"\n  sleep \"$POLL_INTERVAL_SECONDS\"\ndone\n```\n\nIf polling times out, stop the greploop workflow and report the timeout. Do not continue with stale or missing review results.\n\n#### B. Fetch Greptile review results\n\nGreptile may surface its score in several places — check **all** of them:\n\n**1. PR description (body):**\n```bash\ngh pr view \u003CPR_NUMBER> --json body -q '.body'\n```\n\n**2. General PR comments (issue comments):**\n```bash\ngh api --paginate \"repos\u002F{owner}\u002F{repo}\u002Fissues\u002F\u003CPR_NUMBER>\u002Fcomments?per_page=100\"\n```\n\nFilter 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.\n\n**3. PR reviews:**\n```bash\ngh api repos\u002F{owner}\u002F{repo}\u002Fpulls\u002F\u003CPR_NUMBER>\u002Freviews\n```\n\nLook for the most recent entry from `greptile-apps[bot]` or `greptile-apps-staging[bot]`.\n\nParse the text for:\n- **Confidence score**: a pattern like `3\u002F5` or `5\u002F5` (or `Confidence: 3\u002F5`).\n- **Comment count**: Number of inline review comments noted in the summary.\n\n**4. Unresolved review threads** (`gh` fills `{owner}` and `{repo}`; see [GraphQL reference](references\u002Fgraphql-queries.md)):\n```bash\ngh api graphql --paginate -F owner='{owner}' -F repo='{repo}' -F pr=\u003CPR_NUMBER> -f query='\nquery($owner: String!, $repo: String!, $pr: Int!, $endCursor: String) {\n  repository(owner: $owner, name: $repo) {\n    pullRequest(number: $pr) {\n      reviewThreads(first: 100, after: $endCursor) {\n        pageInfo { hasNextPage endCursor }\n        nodes {\n          id\n          isResolved\n          comments(first: 1) {\n            nodes { body path author { login } }\n          }\n        }\n      }\n    }\n  }\n}' --jq '.data.repository.pullRequest.reviewThreads.nodes[] | select(.isResolved == false)'\n```\n\nThe unresolved comment count is the number of threads this returns.\n\nUse whichever source has the **most recently updated** score. Prefer `updated_at` from issue comments when comparing an edited Greptile summary against older review entries.\n\nAlso carry forward actionable items from the latest Greptile general PR comment, especially the \"Prompt to fix all with AI\" section, even if the thread query in B.4 returns zero unresolved threads.\n\n#### C. Check exit conditions\n\nStop the loop if **any** of these are true:\n\n- Confidence score is **5\u002F5** AND there are **zero unresolved comments**\n- Max iterations reached (report current state)\n\n#### D. Fix actionable comments\n\nFor each unresolved Greptile comment:\n\n1. Read the file and understand the comment in context.\n2. Determine if it's actionable (code change needed) or informational.\n3. If actionable, make the fix.\n4. If informational or a false positive, note it but still resolve the thread.\n\n#### E. Resolve threads\n\nResolve every thread handled in D (fixed, informational, or false positive), using the thread IDs from B.4:\n\n```bash\ngh api graphql -f query='\nmutation {\n  t1: resolveReviewThread(input: {threadId: \"ID1\"}) { thread { isResolved } }\n  t2: resolveReviewThread(input: {threadId: \"ID2\"}) { thread { isResolved } }\n}'\n```\n\n#### F. Commit and push\n\nIf `git status --porcelain` is empty after D, exit the loop and report the remaining comments as informational. Otherwise stage only the files you edited:\n\n```bash\ngit add \u003Cfiles you edited>\ngit commit -m \"address greptile review feedback (greploop iteration N)\"\ngit push\n```\n\nThen go back to step **A**.\n\n### 3. Report\n\nAfter exiting the loop, summarize:\n\n| Field              | Value      |\n| ------------------ | ---------- |\n| Iterations         | N          |\n| Final confidence   | X\u002F5        |\n| Comments resolved  | N          |\n| Remaining comments | N (if any) |\n\nIf the loop exited due to max iterations, list any remaining unresolved comments and suggest next steps.\n\n## Output format\n\n```\nGreploop complete.\n  Iterations:    2\n  Confidence:    5\u002F5\n  Resolved:      7 comments\n  Remaining:     0\n```\n\nIf not fully resolved:\n\n```\nGreploop stopped after 5 iterations.\n  Confidence:    4\u002F5\n  Resolved:      12 comments\n  Remaining:     2\n\nRemaining issues:\n  - src\u002Fauth.ts:45 — \"Consider rate limiting this endpoint\"\n  - src\u002Fdb.ts:112 — \"Missing index on user_id column\"\n```\n",{"name":5,"license":15,"metadata":25,"description":7,"allowed-tools":28,"compatibility":29,"disable-model-invocation":30},{"author":26,"version":27},"greptileai","1.3","Bash(gh:*) Bash(git:*)","Requires git and gh (GitHub CLI) authenticated, and Greptile installed on the repo.",true,"main","5affa1dd6283cecc37579e77a6de9288f5a4177f","skills\u002Fgreptile\u002Fgreploop","https:\u002F\u002Fgithub.com\u002Fjorgesolerrr\u002Fskills","https:\u002F\u002Fgithub.com\u002Fjorgesolerrr","Computer Scientist | Backend developer | Python developer","2026-11-04 06:49:16",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":30},[40,43,46],{"tool":41,"command":42},"npx","npx skills add jorgesolerrr\u002Fskills --skill greploop",{"tool":44,"command":45},"bunx","bunx skills add jorgesolerrr\u002Fskills --skill greploop",{"tool":47,"command":48},"pnpm","pnpm dlx skills add jorgesolerrr\u002Fskills --skill greploop","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjorgesolerrr\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fgreptile\u002Fgreploop\u002FSKILL.md",[51,57,61,65],{"path":52,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":55,"sourceHtmlUrl":56},"agents\u002Fopenai.yaml","REFERENCE","参考文档",189,"https:\u002F\u002Fgithub.com\u002Fjorgesolerrr\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fgreptile\u002Fgreploop\u002Fagents\u002Fopenai.yaml",{"path":58,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":59,"sourceHtmlUrl":60},"CREDITS.md",320,"https:\u002F\u002Fgithub.com\u002Fjorgesolerrr\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fgreptile\u002Fgreploop\u002FCREDITS.md",{"path":62,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":16},"LICENSE","许可证",1068,{"path":66,"resourceType":53,"resourceTypeDesc":54,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fgraphql-queries.md",2146,"https:\u002F\u002Fgithub.com\u002Fjorgesolerrr\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fgreptile\u002Fgreploop\u002Freferences\u002Fgraphql-queries.md",[70,78,86,94,102,110],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":74,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":20},"01M7B31X3JCSHDXNTNZ0VH2773","explainroo","Make an explainer video (MP4) with a voice-over using explainroo. The voice is made on this computer and no API key is needed. Use when the user asks for an explainer, how-to, walkthrough, launch or tutorial video, an animated diagram with a voice-over, or a short for YouTube, Reels or TikTok.","https:\u002F\u002Fgithub.com\u002Fjorgesolerrr\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fvincentsch\u002Fexplainroo\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjorgesolerrr\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fvincentsch\u002Fexplainroo\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":82,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":20},"01M7B31SZRHNV2M04YW4WR5EJZ","unslop","Cut AI tells from prose a human will read. Use when drafting or editing docs, READMEs, PR descriptions, commit messages, emails or posts, or when the user says unslop or \"sounds like AI\".","https:\u002F\u002Fgithub.com\u002Fjorgesolerrr\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Funslop\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjorgesolerrr\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Funslop\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":90,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":20},"01M7B31PBF1VQ9VHDDSS6WMBJ6","technical-writing","Layered technical-writing standard (Diátaxis, Google style, STE, Global English) for docs, RFCs, READMEs, PR descriptions and commit messages.","https:\u002F\u002Fgithub.com\u002Fjorgesolerrr\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Ftechnical-writing\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjorgesolerrr\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Ftechnical-writing\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":98,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":20},"01M7B31KHS6P377SZT8SD1RTHW","no-comments","Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.","https:\u002F\u002Fgithub.com\u002Fjorgesolerrr\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Fno-comments\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjorgesolerrr\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fpstack\u002Fno-comments\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":106,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":20},"01M7B31FAY1MDAQ6RDXCFJH2P3","ponytail","Lazy senior dev mode: the smallest change that fully solves the task, and a reply a busy human understands in one read. Use on any coding task (writing, fixing, refactoring, reviewing, choosing dependencies) and when the user says \"ponytail\", \"be lazy\", \"simplest solution\", \"yagni\", or complains about over-engineering or bloat. Levels: lite, full (default), ultra.","https:\u002F\u002Fgithub.com\u002Fjorgesolerrr\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fponytail\u002Fponytail\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjorgesolerrr\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fponytail\u002Fponytail\u002FSKILL.md",[],[],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":114,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":20},"01M7B31AXF7VDH9NFSRXBN6FAM","ponytail-review","Quality review of a change: is the logic right, is it safe, does it hold under real load, is risky code tested, is it fast enough, and is every line needed. Reads the connected code, not only the diff. Each finding is explained in plain English. Use for \"review this\", \"code review\", \"review the last commit\", \"review my PR\", \"is this over-engineered\", \u002Fponytail-review.","https:\u002F\u002Fgithub.com\u002Fjorgesolerrr\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fponytail\u002Fponytail-review\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fjorgesolerrr\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fponytail\u002Fponytail-review\u002FSKILL.md",[],[]]