[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CZ2BEZB1P4FPDSK0EXQAXT":3,"skill-same:01M6CZ2BEZB1P4FPDSK0EXQAXT":59},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":27,"publishedAt":31,"linkOnly":32,"markdownContent":33,"markdownBody":34,"frontMatter":35,"refName":36,"commitSha":37,"skillDirectory":38,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":41,"ownerHtmlUrl":42,"ownerBlogUrl":41,"ownerDescription":43,"updatedAt":44,"install":45,"resources":58},"01M6CZ2BEZB1P4FPDSK0EXQAXT","code-reviewer",null,"aeonfun\u002Faeon","aeonfun","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F287715280?v=4","01M6CZ23C6MXGMF4N0V1DZ1247","aeon","01M6CZ23GMZP1BR424J8Y8K3DG",793,"MIT","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fdocs\u002Fexamples\u002Fskill-templates\u002Fcode-reviewer\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":25,"taxonomyTypeDesc":26},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[28,29,30],"code","code reviewer","reviewer","2026-11-10 10:12:30",false,"---\nname: [REPLACE: SKILL_NAME]\ndescription: First-touch review of newly opened PRs on [REPLACE: WATCHED_REPO] — verdict + welcoming comment + label\nmetadata:\n  category: dev\n  var: \"\"\n  tags:\n    - dev\n---\n\n> **${var}** — Optional. PR number to review. If empty, scans all newly-opened PRs on `[REPLACE: WATCHED_REPO]`.\n\nToday is ${today}. Review external PRs on **[REPLACE: WATCHED_REPO]** with a focus on **[REPLACE: REVIEW_FOCUS]**.\n\n## Steps\n\n1. **List candidates** — every open PR opened in the last 24h that hasn't been reviewed by this skill yet:\n\n   If `${var}` is set, that PR number is the only candidate. Otherwise get the cutoff with its own call, `date -u -d '24 hours ago' +%Y-%m-%dT%H:%M:%SZ`, and write the printed value into the filter literally (the `\u003CSINCE>` below):\n\n   ```bash\n   gh pr list -R [REPLACE: WATCHED_REPO] --state open --json number,author,createdAt,additions,deletions --jq '.[] | select(.createdAt >= \"\u003CSINCE>\") | select(.author.login != \"github-actions[bot]\" and .author.login != \"aeonframework\") | .number'\n   ```\n\n   Track previously-reviewed PRs in `memory\u002Ftopics\u002F[REPLACE: SKILL_NAME]-reviewed.json` (a flat array of PR numbers). Skip anything already in there.\n\n2. **For each PR** — fetch metadata + diff:\n\n   One call per PR, with its number written in literally (the `\u003CPR>` below). Read the output directly; do not save it to a file:\n\n   ```bash\n   gh pr view \u003CPR> -R [REPLACE: WATCHED_REPO] --json title,body,additions,deletions,files,author\n   ```\n\n   ```bash\n   gh pr diff \u003CPR> -R [REPLACE: WATCHED_REPO]\n   ```\n\n   Run the diff call only for a PR under the size limit. Skip if `additions + deletions > [REPLACE: MAX_PR_LINES]`: flag it as `DEFERRED: too large for first-touch review`, leave a note, and move on.\n\n3. **Apply the rubric** — assign one of four verdicts:\n\n   | Verdict | Trigger |\n   |---------|---------|\n   | **ACCEPT** | Touches expected paths, follows repo conventions, focused scope, no obvious bugs in the diff. |\n   | **NEEDS-CHANGES** | Reasonable intent but specific issues: missing tests, broken format, incorrect assumption, naming. |\n   | **DEFER** | Out of scope for this skill — needs a human reviewer (large refactor, architectural change). |\n   | **OUT-OF-SCOPE** | Touches files outside what the repo accepts contributions on (e.g. lock files, generated assets). |\n\n   Focus the rubric on **[REPLACE: REVIEW_FOCUS]** — that's the lens that matters most for this repo.\n\n4. **Post a comment** — use a friendly, specific tone. Acknowledge the contributor, name the verdict, give 1-3 concrete bullets:\n\n   Write the comment to `\u002Ftmp\u002Freview-comment-\u003CPR>.md` with Write:\n\n   ```markdown\n   Thanks for the PR! [verdict text]\n\n   - [bullet 1]\n   - [bullet 2]\n   ```\n\n   Then post it:\n\n   ```bash\n   gh pr comment \u003CPR> -R [REPLACE: WATCHED_REPO] --body-file \u002Ftmp\u002Freview-comment-\u003CPR>.md\n   ```\n\n5. **Label** the PR via `gh pr edit \u003CPR> -R [REPLACE: WATCHED_REPO] --add-label \"\u003Clabel>\"`: use `accepted` \u002F `needs-changes` \u002F `defer` \u002F `out-of-scope` (create the labels in the target repo first if they don't exist).\n\n6. **Notify** via `.\u002Fnotify` only on `ACCEPT` or `OUT-OF-SCOPE` — those are the actionable verdicts for the operator. Silent on `NEEDS-CHANGES` and `DEFER` (the comment on the PR is the signal).\n\n7. **Log** — append to `memory\u002Flogs\u002F${today}.md`:\n   ```\n   ## [REPLACE: SKILL_NAME]\n   - **PRs reviewed**: N (skipped M as previously seen)\n   - **Verdicts**: accept=X, needs-changes=Y, defer=Z, out-of-scope=W\n   - **Status**: REVIEW_OK | REVIEW_QUIET (no new PRs)\n   ```\n\n## Network note\n\n`gh` handles auth via the workflow's `GITHUB_TOKEN`. To comment on or label a PR in **[REPLACE: WATCHED_REPO]**, the token needs `pull-requests: write` and `issues: write` permission on that repo — verify the workflow grants those, or this skill will silently fail to write.\n\n**Shell shape.** Each Bash call is one allowed command (pipes are fine). The run refuses a call that sets a variable (`PRS=$(gh pr list ...)`), uses `if` \u002F `for`, joins commands with `;`, `&&` or `||`, or redirects into a file (`> .pr-meta.json`), and each refusal costs a model turn. So make one `gh` call per PR with the number written in literally, read `gh` output directly, and write the comment body, `reviewed.json` and the log with Write\u002FEdit.\n\n## Constraints\n\n- **Be welcoming**. The PR may be someone's first open-source contribution. Lead with thanks, then specifics.\n- **Never auto-merge**. This skill is first-touch review, not auto-merge. Even an `ACCEPT` verdict still waits for a human merge.\n- **Idempotent**. Re-running the skill must never double-comment. The `reviewed.json` state file is what enforces that.\n","> **${var}** — Optional. PR number to review. If empty, scans all newly-opened PRs on `[REPLACE: WATCHED_REPO]`.\n\nToday is ${today}. Review external PRs on **[REPLACE: WATCHED_REPO]** with a focus on **[REPLACE: REVIEW_FOCUS]**.\n\n## Steps\n\n1. **List candidates** — every open PR opened in the last 24h that hasn't been reviewed by this skill yet:\n\n   If `${var}` is set, that PR number is the only candidate. Otherwise get the cutoff with its own call, `date -u -d '24 hours ago' +%Y-%m-%dT%H:%M:%SZ`, and write the printed value into the filter literally (the `\u003CSINCE>` below):\n\n   ```bash\n   gh pr list -R [REPLACE: WATCHED_REPO] --state open --json number,author,createdAt,additions,deletions --jq '.[] | select(.createdAt >= \"\u003CSINCE>\") | select(.author.login != \"github-actions[bot]\" and .author.login != \"aeonframework\") | .number'\n   ```\n\n   Track previously-reviewed PRs in `memory\u002Ftopics\u002F[REPLACE: SKILL_NAME]-reviewed.json` (a flat array of PR numbers). Skip anything already in there.\n\n2. **For each PR** — fetch metadata + diff:\n\n   One call per PR, with its number written in literally (the `\u003CPR>` below). Read the output directly; do not save it to a file:\n\n   ```bash\n   gh pr view \u003CPR> -R [REPLACE: WATCHED_REPO] --json title,body,additions,deletions,files,author\n   ```\n\n   ```bash\n   gh pr diff \u003CPR> -R [REPLACE: WATCHED_REPO]\n   ```\n\n   Run the diff call only for a PR under the size limit. Skip if `additions + deletions > [REPLACE: MAX_PR_LINES]`: flag it as `DEFERRED: too large for first-touch review`, leave a note, and move on.\n\n3. **Apply the rubric** — assign one of four verdicts:\n\n   | Verdict | Trigger |\n   |---------|---------|\n   | **ACCEPT** | Touches expected paths, follows repo conventions, focused scope, no obvious bugs in the diff. |\n   | **NEEDS-CHANGES** | Reasonable intent but specific issues: missing tests, broken format, incorrect assumption, naming. |\n   | **DEFER** | Out of scope for this skill — needs a human reviewer (large refactor, architectural change). |\n   | **OUT-OF-SCOPE** | Touches files outside what the repo accepts contributions on (e.g. lock files, generated assets). |\n\n   Focus the rubric on **[REPLACE: REVIEW_FOCUS]** — that's the lens that matters most for this repo.\n\n4. **Post a comment** — use a friendly, specific tone. Acknowledge the contributor, name the verdict, give 1-3 concrete bullets:\n\n   Write the comment to `\u002Ftmp\u002Freview-comment-\u003CPR>.md` with Write:\n\n   ```markdown\n   Thanks for the PR! [verdict text]\n\n   - [bullet 1]\n   - [bullet 2]\n   ```\n\n   Then post it:\n\n   ```bash\n   gh pr comment \u003CPR> -R [REPLACE: WATCHED_REPO] --body-file \u002Ftmp\u002Freview-comment-\u003CPR>.md\n   ```\n\n5. **Label** the PR via `gh pr edit \u003CPR> -R [REPLACE: WATCHED_REPO] --add-label \"\u003Clabel>\"`: use `accepted` \u002F `needs-changes` \u002F `defer` \u002F `out-of-scope` (create the labels in the target repo first if they don't exist).\n\n6. **Notify** via `.\u002Fnotify` only on `ACCEPT` or `OUT-OF-SCOPE` — those are the actionable verdicts for the operator. Silent on `NEEDS-CHANGES` and `DEFER` (the comment on the PR is the signal).\n\n7. **Log** — append to `memory\u002Flogs\u002F${today}.md`:\n   ```\n   ## [REPLACE: SKILL_NAME]\n   - **PRs reviewed**: N (skipped M as previously seen)\n   - **Verdicts**: accept=X, needs-changes=Y, defer=Z, out-of-scope=W\n   - **Status**: REVIEW_OK | REVIEW_QUIET (no new PRs)\n   ```\n\n## Network note\n\n`gh` handles auth via the workflow's `GITHUB_TOKEN`. To comment on or label a PR in **[REPLACE: WATCHED_REPO]**, the token needs `pull-requests: write` and `issues: write` permission on that repo — verify the workflow grants those, or this skill will silently fail to write.\n\n**Shell shape.** Each Bash call is one allowed command (pipes are fine). The run refuses a call that sets a variable (`PRS=$(gh pr list ...)`), uses `if` \u002F `for`, joins commands with `;`, `&&` or `||`, or redirects into a file (`> .pr-meta.json`), and each refusal costs a model turn. So make one `gh` call per PR with the number written in literally, read `gh` output directly, and write the comment body, `reviewed.json` and the log with Write\u002FEdit.\n\n## Constraints\n\n- **Be welcoming**. The PR may be someone's first open-source contribution. Lead with thanks, then specifics.\n- **Never auto-merge**. This skill is first-touch review, not auto-merge. Even an `ACCEPT` verdict still waits for a human merge.\n- **Idempotent**. Re-running the skill must never double-comment. The `reviewed.json` state file is what enforces that.\n",{},"main","fddec052c66754287c08582d49ae5fe6a3657221","docs\u002Fexamples\u002Fskill-templates\u002Fcode-reviewer",308,"https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon","https:\u002F\u002Fwww.aeon.fun\u002F","https:\u002F\u002Fgithub.com\u002Faeonfun","The most autonomous agent framework.","2026-11-15 03:40:18",{"source":7,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add aeonfun\u002Faeon --skill code-reviewer",{"tool":51,"command":52},"bunx","bunx skills add aeonfun\u002Faeon --skill code-reviewer",{"tool":54,"command":55},"pnpm","pnpm dlx skills add aeonfun\u002Faeon --skill code-reviewer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fdocs\u002Fexamples\u002Fskill-templates\u002Fcode-reviewer\u002FSKILL.md",true,[],[60,67,73,79,85,91],{"skillNo":61,"name":62,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":66},"01M7DSM3QWBJ44FKRMDDRAGNET","Warn Mixed Script","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fwarn-mixed-script\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":68,"name":69,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":66},"01M7DSM0496DRYYW5A4NAAHZDX","Warn Hidden CSS","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fwarn-hidden-css\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":66},"01M7DSKWCGDVYZSDJM31YHS2JB","Malicious Injection Uppercase","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fmalicious-injection-uppercase\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":66},"01M7DSKRV2RRA1V0HK13KYWJXD","Malicious Injection Homoglyph","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fmalicious-injection-homoglyph\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":66},"01M7DSKMXJKY0167YHVCKF7B49","Malicious Injection Disregard Prior","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fmalicious-injection-disregard-prior\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":66},"01M7DSKGFQ5V2VNSA4K97CVFMB","Benign Greek Math","https:\u002F\u002Fgithub.com\u002Faeonfun\u002Faeon\u002Fblob\u002Fmain\u002Fscripts\u002Ftests\u002Fskill-scan-fixtures\u002Fbenign-greek-math\u002FSKILL.md",[],[]]