[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M719GYTYXMHKAMCSCN1CNS1A":3,"skill-same:01M719GYTYXMHKAMCSCN1CNS1A":58},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"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":6,"ownerDescription":6,"updatedAt":43,"install":44,"resources":57},"01M719GYTYXMHKAMCSCN1CNS1A","gnhf",null,"Use when the user asks to run GNHF, says they are going to sleep or leaving and wants an agent-managed coding run, asks to supervise, steer, or review an active GNHF run, or gives feedback on GNHF results.","dahaliztupe-sketch\u002FKalmeron-Two","dahaliztupe-sketch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F271085317?v=4","01M719765Q83P08JCQ1SWNQR0N","01M719766HQBGF44W90MPJKTD2",1,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdahaliztupe-sketch\u002FKalmeron-Two\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fgnhf\u002FSKILL.md",[],[5,18,19,20,21,22,23,24,25,26,27,28,29,30],"feedback","managed","use","when","steer","review","sleep","results","supervise","active","run","coding","user","2026-11-10 10:12:30",false,"---\nname: gnhf\ndescription: Use when the user asks to run GNHF, says they are going to sleep or leaving and wants an agent-managed coding run, asks to supervise, steer, or review an active GNHF run, or gives feedback on GNHF results.\n---\n\n# GNHF\n\n## Overview\n\nGNHF is an agent orchestrator: it repeatedly calls another coding agent until a natural-language stop condition is met. This skill teaches the host agent to prepare one durable run and, in Companion mode, steer or review it.\n\nCore rule: the host agent orchestrates; GNHF executes. Do not manually implement inside the same scope while a GNHF worker is responsible for it unless the user explicitly changes the delegation.\n\nIn Companion mode, GNHF completion is not user acceptance. \"Stop condition met\" only means the worker stopped; the host still compares the result to the user's latest requirements and fresh verification.\n\n## Modes\n\nChoose exactly one mode for the run.\n\n### Hands-Off\n\nUse when the task is bounded, verification is clear, and the user wants one configured run to proceed without steering.\n\n- Prepare a precise prompt with constraints, non-goals, verification, and stop condition.\n- Launch GNHF and wait for completion.\n- Intervene early only for hard failure, runaway scope, destructive behavior, or impossible prerequisites.\n- Report the final GNHF status after exit.\n\nExamples:\n\n- English: \"I'm going to bed. Use GNHF with Copilot to keep working on this branch and stop when the test suite passes.\"\n- Arabic: \"أنا ذاهب للنوم. استخدم GNHF مع Claude لإكمال العمل على هذا الفرع وتوقف عندما تجتاز مجموعة الاختبارات.\"\n\n### Companion\n\nUse when the task is uncertain, exploratory, design-heavy, research-heavy, or likely to need course correction.\n\nDefault to Companion when the user asks to iterate until satisfied, requests multi-round work, provides review findings, asks for design\u002Fskill\u002Fdocumentation improvement, or asks for supervision.\n\n- Keep a note of original intent, branch, session id, and last known result.\n- Poll the active GNHF process until exit or until an intervention point appears.\n- Intervene when the worker optimizes the wrong thing, repeats failed fixes, skips requested research, drifts scope, or claims success without evidence.\n- Treat review findings as the next acceptance criteria.\n- Prefer a new bounded GNHF prompt over manually taking over implementation.\n\nExamples:\n\n- English: \"Run GNHF for a few rounds on this onboarding flow. Check the diff between rounds and tighten the next prompt if it starts polishing the wrong thing.\"\n- Arabic: \"شغّل GNHF عدة جولات على تدفق onboarding هذا. افحص الـ diff بين الجولات وضيّق الـ prompt التالي إذا بدأ يتشتت.\"\n\n## Launch\n\nCheck the installed CLI before relying on flags:\n\n```bash\ngnhf --help\n```\n\nKnown shape:\n\n```bash\ngnhf \\\n  --agent \u003Cclaude|codex|rovodev|opencode|copilot|pi|acp:\u003Ctarget>> \\\n  --max-iterations \u003Cn> \\\n  --stop-when \"\u003Cobservable completion condition>\" \\\n  --prevent-sleep on \\\n  \"\u003Cworker prompt>\"\n```\n\nIf GNHF has no `--model` flag, put model requirements in the worker prompt or backend config. Do not invent unsupported flags.\n\nBefore launch:\n\n```bash\ngit status --short\ngit branch --show-current\ngit log --oneline --max-count=5\n```\n\nPrompt skeleton:\n\n```text\nObjective: \u003Cone concrete outcome>.\n\nUse \u003Cagent\u002Fmodel requirement>. Work in this repo. Treat this as a long-running GNHF task.\n\nBefore coding, inspect the current repo, relevant docs, and recent commits. Preserve user changes. Do not make unrelated refactors.\n\nAfter each meaningful slice, run relevant verification. If blocked, commit no fake success; leave notes with the blocker and evidence.\n\nStop only when: \u003Cobservable completion condition>.\n```\n\n## Kalmeron-Specific Launch Examples\n\n### Fix TypeScript errors overnight:\n```bash\ngnhf \\\n  --agent claude \\\n  --max-iterations 15 \\\n  --stop-when \"npx tsc --noEmit exits with 0 errors\" \\\n  --prevent-sleep on \\\n  \"Fix all TypeScript errors in this Kalmeron Next.js 16 project. Run npx tsc --noEmit after each fix. Do not change business logic. Stop when tsc reports zero errors.\"\n```\n\n### Improve Arabic AI agent responses:\n```bash\ngnhf \\\n  --agent claude \\\n  --max-iterations 20 \\\n  --stop-when \"all agent prompts in lib\u002Fagents\u002F have Arabic system messages and pass lint\" \\\n  --prevent-sleep on \\\n  \"Improve the Arabic system prompts for all Kalmeron agents in lib\u002Fagents\u002F. Ensure each agent has clear, professional Arabic instructions. Run npm run lint after changes. Stop when all agents have quality Arabic prompts and lint passes.\"\n```\n\n### Add unit tests:\n```bash\ngnhf \\\n  --agent claude \\\n  --max-iterations 25 \\\n  --stop-when \"npm run test exits with all tests passing and coverage above 70%\" \\\n  --prevent-sleep on \\\n  \"Add Vitest unit tests for the utility functions in lib\u002Futils\u002F and lib\u002Fagents\u002F in this Kalmeron project. Run npm run test after each addition. Stop when test coverage reaches 70% and all tests pass.\"\n```\n\n## Steer\n\nIn Companion mode, evaluate after each iteration or meaningful output chunk:\n\n| Signal                                                        | Action                                                               |\n| ------------------------------------------------------------- | -------------------------------------------------------------------- |\n| Worker found a real blocker                                   | Stop or relaunch with blocker-specific instructions                  |\n| Good partial slice                                            | Let it continue or tighten the next stop condition                   |\n| Skipped requested research                                    | Relaunch with research as explicit first deliverable                 |\n| Worker changes unrelated files                                | Stop and review before continuing                                    |\n| Worker claims success without verification                    | Review immediately; relaunch only with evidence-based stop condition |\n| Reviewer finds a blocking issue or user says not satisfactory | Relaunch with that finding as the sole bounded correction            |\n\nSteering prompt:\n\n```text\nContinue from the current repo state. The previous run partially succeeded: \u003Cevidence>.\n\nDo not redo completed work. Focus only on \u003Cbounded correction>.\n\nThe issue to fix now is \u003Cspecific observed issue>. Verify with \u003Ccommands\u002Fchecks>.\n\nStop only when \u003Cobservable condition>.\n```\n\n## Companion Review\n\nUse only in Companion mode, when the host is supervising quality or deciding whether to continue with another bounded run.\n\n1. Inspect branch, status, commits, changed files, and diff.\n2. Read GNHF notes\u002Flogs as claims, not evidence.\n3. Run independent verification: tests, lint, build, typecheck, manual QA, or domain-specific checks.\n4. Compare the result to the stop condition and the user's latest feedback.\n5. Decide: **Mergeable**, **Needs follow-up GNHF run**, or **Do not merge**.\n\nIf the result needs follow-up, continue in Companion mode instead of presenting the run as complete. Do not merge unless explicitly authorized.\n\n## Findings\n\nUse when the user provides findings such as \"not preserved\", \"scope drift\", \"missing requirement\", or \"why did you stop\".\n\n1. Treat the run as Companion mode.\n2. Convert each finding into an observable correction. Preserve severity, file\u002Fline scope, and the user's wording.\n3. Relaunch on the same candidate branch when salvageable.\n4. Prompt the worker to fix only the bounded finding, preserve completed valid work, verify, and stop only when the finding is no longer true.\n5. Review again after the follow-up.\n6. Repeat until no blocking findings remain, verification passes, or a real blocker is found.\n\n## Morning Review\n\nUse when the user returns with \"good morning\", \"كيف سارت الليلة؟\", \"how did last night's run go?\", or similar after a GNHF run.\n\nDo not ask what to review first. Reconstruct state:\n\n```bash\ngit status --short\ngit branch --show-current\ngit log --oneline --decorate --max-count=20\npgrep -fl 'gnhf|claude|codex|copilot|opencode|rovodev' || true\n```\n\nInspect likely GNHF branches, notes, logs, terminal sessions, and changed files. If a GNHF process is still running, report that first.\n\nReport mode, agent, branch, status, changes, verification, stop-condition result, quality assessment, and recommended next action. Never summarize an overnight run from memory.\n\n## Agent Selection for Kalmeron\n\n- `claude`: reasoning-heavy implementation, Arabic text quality, prompt engineering, or prose-heavy planning.\n- `codex`: repo-aware code work or review-heavy tasks.\n- `copilot`: explicit GitHub Copilot CLI request or local Copilot config.\n- `pi`: explicit Pi request or local Pi configuration.\n- `opencode` \u002F `rovodev`: explicit request or repo-specific setup.\n- `acp:\u003Ctarget>`: explicit ACP target request, or when the user wants to drive a custom ACP-compatible agent through GNHF.\n\n**Default for Kalmeron**: use `claude` unless the user specifies otherwise.\n\n## Safety\n\n- Preserve user changes. Never run destructive git commands to clean up a GNHF branch.\n- In Companion mode, do not trust a worker's success summary without fresh verification.\n- Keep prompts outcome-based and evidence-based.\n- Use concrete stop conditions. Bad: \"looks good\". Good: \"the target workflow succeeds, relevant checks pass, and no unrelated files changed.\"\n- If the user is away, produce branches and a status report, not irreversible changes, unless explicitly authorized.\n- For Kalmeron: never modify Firestore security rules, billing logic, or authentication flows in a Hands-Off run without explicit authorization.\n","# GNHF\n\n## Overview\n\nGNHF is an agent orchestrator: it repeatedly calls another coding agent until a natural-language stop condition is met. This skill teaches the host agent to prepare one durable run and, in Companion mode, steer or review it.\n\nCore rule: the host agent orchestrates; GNHF executes. Do not manually implement inside the same scope while a GNHF worker is responsible for it unless the user explicitly changes the delegation.\n\nIn Companion mode, GNHF completion is not user acceptance. \"Stop condition met\" only means the worker stopped; the host still compares the result to the user's latest requirements and fresh verification.\n\n## Modes\n\nChoose exactly one mode for the run.\n\n### Hands-Off\n\nUse when the task is bounded, verification is clear, and the user wants one configured run to proceed without steering.\n\n- Prepare a precise prompt with constraints, non-goals, verification, and stop condition.\n- Launch GNHF and wait for completion.\n- Intervene early only for hard failure, runaway scope, destructive behavior, or impossible prerequisites.\n- Report the final GNHF status after exit.\n\nExamples:\n\n- English: \"I'm going to bed. Use GNHF with Copilot to keep working on this branch and stop when the test suite passes.\"\n- Arabic: \"أنا ذاهب للنوم. استخدم GNHF مع Claude لإكمال العمل على هذا الفرع وتوقف عندما تجتاز مجموعة الاختبارات.\"\n\n### Companion\n\nUse when the task is uncertain, exploratory, design-heavy, research-heavy, or likely to need course correction.\n\nDefault to Companion when the user asks to iterate until satisfied, requests multi-round work, provides review findings, asks for design\u002Fskill\u002Fdocumentation improvement, or asks for supervision.\n\n- Keep a note of original intent, branch, session id, and last known result.\n- Poll the active GNHF process until exit or until an intervention point appears.\n- Intervene when the worker optimizes the wrong thing, repeats failed fixes, skips requested research, drifts scope, or claims success without evidence.\n- Treat review findings as the next acceptance criteria.\n- Prefer a new bounded GNHF prompt over manually taking over implementation.\n\nExamples:\n\n- English: \"Run GNHF for a few rounds on this onboarding flow. Check the diff between rounds and tighten the next prompt if it starts polishing the wrong thing.\"\n- Arabic: \"شغّل GNHF عدة جولات على تدفق onboarding هذا. افحص الـ diff بين الجولات وضيّق الـ prompt التالي إذا بدأ يتشتت.\"\n\n## Launch\n\nCheck the installed CLI before relying on flags:\n\n```bash\ngnhf --help\n```\n\nKnown shape:\n\n```bash\ngnhf \\\n  --agent \u003Cclaude|codex|rovodev|opencode|copilot|pi|acp:\u003Ctarget>> \\\n  --max-iterations \u003Cn> \\\n  --stop-when \"\u003Cobservable completion condition>\" \\\n  --prevent-sleep on \\\n  \"\u003Cworker prompt>\"\n```\n\nIf GNHF has no `--model` flag, put model requirements in the worker prompt or backend config. Do not invent unsupported flags.\n\nBefore launch:\n\n```bash\ngit status --short\ngit branch --show-current\ngit log --oneline --max-count=5\n```\n\nPrompt skeleton:\n\n```text\nObjective: \u003Cone concrete outcome>.\n\nUse \u003Cagent\u002Fmodel requirement>. Work in this repo. Treat this as a long-running GNHF task.\n\nBefore coding, inspect the current repo, relevant docs, and recent commits. Preserve user changes. Do not make unrelated refactors.\n\nAfter each meaningful slice, run relevant verification. If blocked, commit no fake success; leave notes with the blocker and evidence.\n\nStop only when: \u003Cobservable completion condition>.\n```\n\n## Kalmeron-Specific Launch Examples\n\n### Fix TypeScript errors overnight:\n```bash\ngnhf \\\n  --agent claude \\\n  --max-iterations 15 \\\n  --stop-when \"npx tsc --noEmit exits with 0 errors\" \\\n  --prevent-sleep on \\\n  \"Fix all TypeScript errors in this Kalmeron Next.js 16 project. Run npx tsc --noEmit after each fix. Do not change business logic. Stop when tsc reports zero errors.\"\n```\n\n### Improve Arabic AI agent responses:\n```bash\ngnhf \\\n  --agent claude \\\n  --max-iterations 20 \\\n  --stop-when \"all agent prompts in lib\u002Fagents\u002F have Arabic system messages and pass lint\" \\\n  --prevent-sleep on \\\n  \"Improve the Arabic system prompts for all Kalmeron agents in lib\u002Fagents\u002F. Ensure each agent has clear, professional Arabic instructions. Run npm run lint after changes. Stop when all agents have quality Arabic prompts and lint passes.\"\n```\n\n### Add unit tests:\n```bash\ngnhf \\\n  --agent claude \\\n  --max-iterations 25 \\\n  --stop-when \"npm run test exits with all tests passing and coverage above 70%\" \\\n  --prevent-sleep on \\\n  \"Add Vitest unit tests for the utility functions in lib\u002Futils\u002F and lib\u002Fagents\u002F in this Kalmeron project. Run npm run test after each addition. Stop when test coverage reaches 70% and all tests pass.\"\n```\n\n## Steer\n\nIn Companion mode, evaluate after each iteration or meaningful output chunk:\n\n| Signal                                                        | Action                                                               |\n| ------------------------------------------------------------- | -------------------------------------------------------------------- |\n| Worker found a real blocker                                   | Stop or relaunch with blocker-specific instructions                  |\n| Good partial slice                                            | Let it continue or tighten the next stop condition                   |\n| Skipped requested research                                    | Relaunch with research as explicit first deliverable                 |\n| Worker changes unrelated files                                | Stop and review before continuing                                    |\n| Worker claims success without verification                    | Review immediately; relaunch only with evidence-based stop condition |\n| Reviewer finds a blocking issue or user says not satisfactory | Relaunch with that finding as the sole bounded correction            |\n\nSteering prompt:\n\n```text\nContinue from the current repo state. The previous run partially succeeded: \u003Cevidence>.\n\nDo not redo completed work. Focus only on \u003Cbounded correction>.\n\nThe issue to fix now is \u003Cspecific observed issue>. Verify with \u003Ccommands\u002Fchecks>.\n\nStop only when \u003Cobservable condition>.\n```\n\n## Companion Review\n\nUse only in Companion mode, when the host is supervising quality or deciding whether to continue with another bounded run.\n\n1. Inspect branch, status, commits, changed files, and diff.\n2. Read GNHF notes\u002Flogs as claims, not evidence.\n3. Run independent verification: tests, lint, build, typecheck, manual QA, or domain-specific checks.\n4. Compare the result to the stop condition and the user's latest feedback.\n5. Decide: **Mergeable**, **Needs follow-up GNHF run**, or **Do not merge**.\n\nIf the result needs follow-up, continue in Companion mode instead of presenting the run as complete. Do not merge unless explicitly authorized.\n\n## Findings\n\nUse when the user provides findings such as \"not preserved\", \"scope drift\", \"missing requirement\", or \"why did you stop\".\n\n1. Treat the run as Companion mode.\n2. Convert each finding into an observable correction. Preserve severity, file\u002Fline scope, and the user's wording.\n3. Relaunch on the same candidate branch when salvageable.\n4. Prompt the worker to fix only the bounded finding, preserve completed valid work, verify, and stop only when the finding is no longer true.\n5. Review again after the follow-up.\n6. Repeat until no blocking findings remain, verification passes, or a real blocker is found.\n\n## Morning Review\n\nUse when the user returns with \"good morning\", \"كيف سارت الليلة؟\", \"how did last night's run go?\", or similar after a GNHF run.\n\nDo not ask what to review first. Reconstruct state:\n\n```bash\ngit status --short\ngit branch --show-current\ngit log --oneline --decorate --max-count=20\npgrep -fl 'gnhf|claude|codex|copilot|opencode|rovodev' || true\n```\n\nInspect likely GNHF branches, notes, logs, terminal sessions, and changed files. If a GNHF process is still running, report that first.\n\nReport mode, agent, branch, status, changes, verification, stop-condition result, quality assessment, and recommended next action. Never summarize an overnight run from memory.\n\n## Agent Selection for Kalmeron\n\n- `claude`: reasoning-heavy implementation, Arabic text quality, prompt engineering, or prose-heavy planning.\n- `codex`: repo-aware code work or review-heavy tasks.\n- `copilot`: explicit GitHub Copilot CLI request or local Copilot config.\n- `pi`: explicit Pi request or local Pi configuration.\n- `opencode` \u002F `rovodev`: explicit request or repo-specific setup.\n- `acp:\u003Ctarget>`: explicit ACP target request, or when the user wants to drive a custom ACP-compatible agent through GNHF.\n\n**Default for Kalmeron**: use `claude` unless the user specifies otherwise.\n\n## Safety\n\n- Preserve user changes. Never run destructive git commands to clean up a GNHF branch.\n- In Companion mode, do not trust a worker's success summary without fresh verification.\n- Keep prompts outcome-based and evidence-based.\n- Use concrete stop conditions. Bad: \"looks good\". Good: \"the target workflow succeeds, relevant checks pass, and no unrelated files changed.\"\n- If the user is away, produce branches and a status report, not irreversible changes, unless explicitly authorized.\n- For Kalmeron: never modify Firestore security rules, billing logic, or authentication flows in a Hands-Off run without explicit authorization.\n",{"name":5,"description":7},"main","13d9afadbb6a87d6209fe4bd6ca2bbe4553119ac",".agents\u002Fskills\u002Fgnhf",0,"https:\u002F\u002Fgithub.com\u002Fdahaliztupe-sketch\u002FKalmeron-Two","https:\u002F\u002Fkalmeron-two.vercel.app","https:\u002F\u002Fgithub.com\u002Fdahaliztupe-sketch","2026-10-05 12:24:53",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add dahaliztupe-sketch\u002FKalmeron-Two --skill gnhf",{"tool":50,"command":51},"bunx","bunx skills add dahaliztupe-sketch\u002FKalmeron-Two --skill gnhf",{"tool":53,"command":54},"pnpm","pnpm dlx skills add dahaliztupe-sketch\u002FKalmeron-Two --skill gnhf","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdahaliztupe-sketch\u002FKalmeron-Two\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fgnhf\u002FSKILL.md",true,[],[59,76,100,119,147,178],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":63,"sourceHtmlUrl":64,"categories":65,"keywords":71,"publishedAt":31},"01M719SWYD9RGS97HJ69PXWY62","add-new-agent","خطوات تفصيليّة لإضافة وكيل ذكاء اصطناعي جديد إلى منصّة Kalmeron من الفكرة إلى الإنتاج","https:\u002F\u002Fgithub.com\u002Fdahaliztupe-sketch\u002FKalmeron-Two\u002Fblob\u002Fmain\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fdahaliztupe-sketch\u002FKalmeron-Two\u002Fblob\u002Fmain\u002FSKILL.md",[66],{"categoryNo":67,"categoryName":68,"taxonomyType":69,"taxonomyTypeDesc":70},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[72,73,74,75],"add","add new agent","new","new agent",{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":93,"publishedAt":31},"01M719SSKNBA7T5NS7V6DP0PX4","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Fdahaliztupe-sketch\u002FKalmeron-Two\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwriting-skills\u002FSKILL.md",[82,85,88],{"categoryNo":83,"categoryName":84,"taxonomyType":69,"taxonomyTypeDesc":70},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":86,"categoryName":87,"taxonomyType":69,"taxonomyTypeDesc":70},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[94,95,74,21,96,97,98,20,99],"writing skills","writing","work","editing","deployment","Existing",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":108,"publishedAt":31},"01M719SRFDNKA3044QD3FYZ05R","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002Fdahaliztupe-sketch\u002FKalmeron-Two\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwriting-plans\u002FSKILL.md",[106,107],{"categoryNo":86,"categoryName":87,"taxonomyType":69,"taxonomyTypeDesc":70},{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},[109,95,110,111,112,113,21,20,114,115,116,117,118],"writing plans","plans","code","requirements","you","for","task","multi","spec","multi-step task",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":131,"publishedAt":31},"01M719SPN5FM1JYJSR9DGJQPZ0","web-design-guidelines","Review UI code for Web Interface Guidelines compliance. Use when asked to \"review my UI\", \"check accessibility\", \"audit design\", \"review UX\", or \"check my site against best practices\".","https:\u002F\u002Fgithub.com\u002Fdahaliztupe-sketch\u002FKalmeron-Two\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweb-design-guidelines\u002FSKILL.md",[125,128],{"categoryNo":126,"categoryName":127,"taxonomyType":69,"taxonomyTypeDesc":70},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":129,"categoryName":130,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000032","设计师",[132,133,134,135,136,23,137,138,139,140,141,111,114,142,143,144,20,21,145,146],"web design","web design guidelines","web","design","guidelines","accessibility","ux","audit","compliance","check","vercel","interface","web interface guidelines","best practices","file",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":151,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":158,"publishedAt":31},"01M719SK11T05QYVPTWWYMYY5B","vitest","Set up Vitest testing in any project — detects project type (Cloudflare Workers, React, Node), generates vitest.config.ts, test setup, utilities, and sample tests. Also covers mocking patterns, coverage config, workspace setup, and Jest migration. Trigger with 'set up vitest', 'add tests', 'configure vitest', 'migrate from jest', 'vitest config', 'add unit tests', or 'testing setup'.","MIT","https:\u002F\u002Fgithub.com\u002Fdahaliztupe-sketch\u002FKalmeron-Two\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fvitest\u002FSKILL.md",[154,155],{"categoryNo":83,"categoryName":84,"taxonomyType":69,"taxonomyTypeDesc":70},{"categoryNo":156,"categoryName":157,"taxonomyType":69,"taxonomyTypeDesc":70},"01JBSEEDCAT000000000000009","前端开发",[149,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177],"cloudflare","cloudflare workers","config","node","sample","react","jest","migrate","configure","Utilities","up","testing","workspace setup","project","unit","SET","coverage","test setup","patterns",{"skillNo":179,"name":180,"nameZh":6,"description":181,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":182,"categories":183,"keywords":184,"publishedAt":31},"01M719SGV9R1N88QWAB7Y925HD","verification-loops","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs. Requires running verification commands and confirming output before making any success claims. Evidence before assertions always.","https:\u002F\u002Fgithub.com\u002Fdahaliztupe-sketch\u002FKalmeron-Two\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverification-loops\u002FSKILL.md",[],[185,186,187,188,20,189,190,191,192,193,194,195,96,196,197,21],"loops","verification","verification loops","claim","assertions","prs","complete","evidence","running","commands","about","claims","output"]