[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F6BPR2E18652MMHFJZ7F15":3,"skill-same:01M7F6BPR2E18652MMHFJZ7F15":102},{"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":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":14,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":47},"01M7F6BPR2E18652MMHFJZ7F15","build-skill",null,"Create, redesign or merge a skill, grounded in facts, then hand over the test. Started by you.","yigitkonur\u002Fplugin-agentic-maker","yigitkonur","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9989650?v=4","01M7548A59WS0A38NSK8FASK46","Yigit Konur","01M7F6AQQPM8KBP08NQ3BG7160",0,"MIT","https:\u002F\u002Fgithub.com\u002Fyigitkonur\u002Fplugin-agentic-maker\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-skill\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: build-skill\ndescription: Create, redesign or merge a skill, grounded in facts, then hand over the test. Started by you.\ndisable-model-invocation: true\nargument-hint: \"\u003Cwhat the skill should do | path of a skill to redesign>\"\nallowed-tools: Bash(agentic-maker *) Bash(${CLAUDE_PLUGIN_ROOT}\u002Fbin\u002Fagentic-maker *) Bash(claude plugin validate *) Read Grep Glob Write Edit\n---\n\n# Build a skill\n\n> In Codex: `$ARGUMENTS` is what the user wrote after the skill name. `${CLAUDE_PLUGIN_ROOT}` and `${CLAUDE_SKILL_DIR}` mean the plugin folder and this skill's folder (the plugin folder is two levels above this file); `agentic-maker` is on PATH or is `\u003Cplugin folder>\u002Fbin\u002Fagentic-maker`. A line that starts with an exclamation mark and a backtick is a command: run it yourself first.\n\nRequest: `$ARGUMENTS`\n\nPages are in `${CLAUDE_SKILL_DIR}\u002Freferences\u002F` (listed at the end); the two skill pages in the knowledge base are `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fagent-interface-design\u002Freferences\u002Fskill\u002F`. Open a page when the step names it, not before. This runs in the main conversation, so ask the user directly, and only what changes the result.\n\n## Pick the mode\n\n| The request is | Do |\n|---|---|\n| a new skill | steps 1-7 |\n| an existing skill to redesign (a path, relative to the current working directory, not to the plugin) | `ls` that path in the current directory and read it first. If the user has derail findings for it, read them; they say how it fails today. Then steps 3-7 |\n| several skills or sources to merge | step 2 builds a comparison table (what to inherit, what to drop, why) before any text is written. Every command, flag and path comes verbatim from a source; one found in no source goes in the report as a suggested addition, not in the skill |\n| \"turn this conversation into a skill\" | list what was done as a nested outline, five levels at most: milestone, phase, step, error met and its correction, invariant learned. Corrections and invariants become the skill's rules; repeated commands become scripts. Then steps 2-7 |\n\n## Steps\n\n1. **Scope.** Who invokes it (the model on a matching request, or only the user), in which harnesses it must run, and one sentence for what changes for the agent when it is loaded. [naming-and-boundaries.md](references\u002Fnaming-and-boundaries.md) if one skill or two.\n2. **Ground it.** For any non-trivial domain, gather verified facts first: the official docs, the real command output, the API as it is today. If the `research` plugin is installed use `\u002Fresearch:ask` (one question) or `\u002Fresearch:deep` (five or more sources); otherwise use whatever web and file tools you have. A skill drafted from memory carries the model's guesses into every future run; if you can verify nothing, say so and stop. Look at two or three existing skills for the same job and note what each does well.\n3. **Lay it out before writing.** What stays in `SKILL.md` (under 500 lines), what goes to `references\u002F`, what becomes a script: [references-and-scripts.md](references\u002Freferences-and-scripts.md). Pick the body's shape: [workflow-patterns.md](references\u002Fworkflow-patterns.md). Show the layout to the user when the request was open-ended.\n4. **Write it.**\n   - Frontmatter: [frontmatter.md](references\u002Ffrontmatter.md). Portable fields only if it must run outside Claude Code.\n   - Description: it is the only thing the model sees when deciding to load the skill. [descriptions-that-trigger.md](..\u002Fagent-interface-design\u002Freferences\u002Fskill\u002Fdescriptions-that-trigger.md).\n   - Body: exact paths and commands, numbers instead of adjectives, a check on every phase, using only commands and flags that appear in the sources from step 2: [text-as-program.md](..\u002Fagent-interface-design\u002Freferences\u002Fskill\u002Ftext-as-program.md). How strict each step should be: [instruction-strength.md](references\u002Finstruction-strength.md).\n   - A skill that drives MCP tools: [wrapping-mcp-tools.md](references\u002Fwrapping-mcp-tools.md).\n5. **Check what a script can check.** Run each check as its own Bash call, with no `&&`, `;` or heredoc: `claude plugin validate \u003Cskill dir>` (frontmatter and structure), `wc -l \u003Cskill dir>\u002FSKILL.md`, every bundled script on real input. A denied call skips only that check: redo it with Read, Grep or Glob (frontmatter fields, line count, each link and path) and name the denied command in the report. Then open [checklist.md](references\u002Fchecklist.md) and build a table with one row per line, marked checked or unchecked.\n6. **Hand over the test.** Only the user can start `\u002Fagentic-maker:derail`; you cannot, so do not try. Write three scenarios into `.agentic-maker\u002Fscenarios\u002F\u003Cname>.md` (format in `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fderail\u002Freferences\u002Fscenarios.md`): a normal request in the user's words that never names the skill, an ambiguous one, and one with a missing input; each with receipts that check the disk, not the agent's words. Preview one with `agentic-maker run \u003Cname> --dry-run`. End by giving the user the exact command, `\u002Fagentic-maker:derail \u003Cskill dir>`. Until they run it the skill is untested, and your report says so. Procedure and what a pass looks like: [test-with-fresh-agents.md](references\u002Ftest-with-fresh-agents.md). A skill only the user can start is tested through a slash-command prompt; the derail dry-run says so.\n7. **Ship.** The final message is the checklist table from step 5: one row per line of [checklist.md](references\u002Fchecklist.md), marked checked (with the command and its output, or the file and line you read) or unchecked. A message without that table is not a ship.\n\n## Do this, not that\n\n| Do | Not |\n|---|---|\n| Verify every API, flag and path against the real thing | Write them from memory |\n| Fix the sentence that misled the agent | Add a \"never do X\" rule next to it |\n| Keep `SKILL.md` as the routing and the rules; move bulk to references | Paste a 1,500-line guide into one file |\n| Write scripts in Python or Node and run them before you ship | Ship a script you never ran |\n| Report what you could not verify | Present a guess as a fact |\n\n## Pages\n\n| Open | When |\n|---|---|\n| [frontmatter.md](references\u002Ffrontmatter.md) | writing or fixing frontmatter |\n| [naming-and-boundaries.md](references\u002Fnaming-and-boundaries.md) | naming it, splitting or merging |\n| [references-and-scripts.md](references\u002Freferences-and-scripts.md) | deciding what goes where |\n| [workflow-patterns.md](references\u002Fworkflow-patterns.md) | choosing the structure of the body |\n| [instruction-strength.md](references\u002Finstruction-strength.md) | a step is too loose or too rigid |\n| [wrapping-mcp-tools.md](references\u002Fwrapping-mcp-tools.md) | the skill calls MCP tools |\n| [test-with-fresh-agents.md](references\u002Ftest-with-fresh-agents.md) | step 6 |\n| [checklist.md](references\u002Fchecklist.md) | before shipping |\n| [troubleshooting.md](references\u002Ftroubleshooting.md) | it does not load, trigger or behave |\n| [anti-patterns-content.md](references\u002Fanti-patterns-content.md), [anti-patterns-process.md](references\u002Fanti-patterns-process.md) | reviewing a draft or your own process |\n| [worked-examples.md](references\u002Fworked-examples.md) | you want a structure to copy |\n","# Build a skill\n\n> In Codex: `$ARGUMENTS` is what the user wrote after the skill name. `${CLAUDE_PLUGIN_ROOT}` and `${CLAUDE_SKILL_DIR}` mean the plugin folder and this skill's folder (the plugin folder is two levels above this file); `agentic-maker` is on PATH or is `\u003Cplugin folder>\u002Fbin\u002Fagentic-maker`. A line that starts with an exclamation mark and a backtick is a command: run it yourself first.\n\nRequest: `$ARGUMENTS`\n\nPages are in `${CLAUDE_SKILL_DIR}\u002Freferences\u002F` (listed at the end); the two skill pages in the knowledge base are `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fagent-interface-design\u002Freferences\u002Fskill\u002F`. Open a page when the step names it, not before. This runs in the main conversation, so ask the user directly, and only what changes the result.\n\n## Pick the mode\n\n| The request is | Do |\n|---|---|\n| a new skill | steps 1-7 |\n| an existing skill to redesign (a path, relative to the current working directory, not to the plugin) | `ls` that path in the current directory and read it first. If the user has derail findings for it, read them; they say how it fails today. Then steps 3-7 |\n| several skills or sources to merge | step 2 builds a comparison table (what to inherit, what to drop, why) before any text is written. Every command, flag and path comes verbatim from a source; one found in no source goes in the report as a suggested addition, not in the skill |\n| \"turn this conversation into a skill\" | list what was done as a nested outline, five levels at most: milestone, phase, step, error met and its correction, invariant learned. Corrections and invariants become the skill's rules; repeated commands become scripts. Then steps 2-7 |\n\n## Steps\n\n1. **Scope.** Who invokes it (the model on a matching request, or only the user), in which harnesses it must run, and one sentence for what changes for the agent when it is loaded. [naming-and-boundaries.md](references\u002Fnaming-and-boundaries.md) if one skill or two.\n2. **Ground it.** For any non-trivial domain, gather verified facts first: the official docs, the real command output, the API as it is today. If the `research` plugin is installed use `\u002Fresearch:ask` (one question) or `\u002Fresearch:deep` (five or more sources); otherwise use whatever web and file tools you have. A skill drafted from memory carries the model's guesses into every future run; if you can verify nothing, say so and stop. Look at two or three existing skills for the same job and note what each does well.\n3. **Lay it out before writing.** What stays in `SKILL.md` (under 500 lines), what goes to `references\u002F`, what becomes a script: [references-and-scripts.md](references\u002Freferences-and-scripts.md). Pick the body's shape: [workflow-patterns.md](references\u002Fworkflow-patterns.md). Show the layout to the user when the request was open-ended.\n4. **Write it.**\n   - Frontmatter: [frontmatter.md](references\u002Ffrontmatter.md). Portable fields only if it must run outside Claude Code.\n   - Description: it is the only thing the model sees when deciding to load the skill. [descriptions-that-trigger.md](..\u002Fagent-interface-design\u002Freferences\u002Fskill\u002Fdescriptions-that-trigger.md).\n   - Body: exact paths and commands, numbers instead of adjectives, a check on every phase, using only commands and flags that appear in the sources from step 2: [text-as-program.md](..\u002Fagent-interface-design\u002Freferences\u002Fskill\u002Ftext-as-program.md). How strict each step should be: [instruction-strength.md](references\u002Finstruction-strength.md).\n   - A skill that drives MCP tools: [wrapping-mcp-tools.md](references\u002Fwrapping-mcp-tools.md).\n5. **Check what a script can check.** Run each check as its own Bash call, with no `&&`, `;` or heredoc: `claude plugin validate \u003Cskill dir>` (frontmatter and structure), `wc -l \u003Cskill dir>\u002FSKILL.md`, every bundled script on real input. A denied call skips only that check: redo it with Read, Grep or Glob (frontmatter fields, line count, each link and path) and name the denied command in the report. Then open [checklist.md](references\u002Fchecklist.md) and build a table with one row per line, marked checked or unchecked.\n6. **Hand over the test.** Only the user can start `\u002Fagentic-maker:derail`; you cannot, so do not try. Write three scenarios into `.agentic-maker\u002Fscenarios\u002F\u003Cname>.md` (format in `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fderail\u002Freferences\u002Fscenarios.md`): a normal request in the user's words that never names the skill, an ambiguous one, and one with a missing input; each with receipts that check the disk, not the agent's words. Preview one with `agentic-maker run \u003Cname> --dry-run`. End by giving the user the exact command, `\u002Fagentic-maker:derail \u003Cskill dir>`. Until they run it the skill is untested, and your report says so. Procedure and what a pass looks like: [test-with-fresh-agents.md](references\u002Ftest-with-fresh-agents.md). A skill only the user can start is tested through a slash-command prompt; the derail dry-run says so.\n7. **Ship.** The final message is the checklist table from step 5: one row per line of [checklist.md](references\u002Fchecklist.md), marked checked (with the command and its output, or the file and line you read) or unchecked. A message without that table is not a ship.\n\n## Do this, not that\n\n| Do | Not |\n|---|---|\n| Verify every API, flag and path against the real thing | Write them from memory |\n| Fix the sentence that misled the agent | Add a \"never do X\" rule next to it |\n| Keep `SKILL.md` as the routing and the rules; move bulk to references | Paste a 1,500-line guide into one file |\n| Write scripts in Python or Node and run them before you ship | Ship a script you never ran |\n| Report what you could not verify | Present a guess as a fact |\n\n## Pages\n\n| Open | When |\n|---|---|\n| [frontmatter.md](references\u002Ffrontmatter.md) | writing or fixing frontmatter |\n| [naming-and-boundaries.md](references\u002Fnaming-and-boundaries.md) | naming it, splitting or merging |\n| [references-and-scripts.md](references\u002Freferences-and-scripts.md) | deciding what goes where |\n| [workflow-patterns.md](references\u002Fworkflow-patterns.md) | choosing the structure of the body |\n| [instruction-strength.md](references\u002Finstruction-strength.md) | a step is too loose or too rigid |\n| [wrapping-mcp-tools.md](references\u002Fwrapping-mcp-tools.md) | the skill calls MCP tools |\n| [test-with-fresh-agents.md](references\u002Ftest-with-fresh-agents.md) | step 6 |\n| [checklist.md](references\u002Fchecklist.md) | before shipping |\n| [troubleshooting.md](references\u002Ftroubleshooting.md) | it does not load, trigger or behave |\n| [anti-patterns-content.md](references\u002Fanti-patterns-content.md), [anti-patterns-process.md](references\u002Fanti-patterns-process.md) | reviewing a draft or your own process |\n| [worked-examples.md](references\u002Fworked-examples.md) | you want a structure to copy |\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":25,"disable-model-invocation":26},"Bash(agentic-maker *) Bash(${CLAUDE_PLUGIN_ROOT}\u002Fbin\u002Fagentic-maker *) Bash(claude plugin validate *) Read Grep Glob Write Edit","\u003Cwhat the skill should do | path of a skill to redesign>",true,"main","4fbc0dad2dfb64cb1747e69933c261d941c8f074","skills\u002Fbuild-skill","https:\u002F\u002Fgithub.com\u002Fyigitkonur\u002Fplugin-agentic-maker","https:\u002F\u002Fgithub.com\u002Fyigitkonur","https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fyigitkonur\u002F","HKEY_LOCAL_MACHINE","2026-10-26 07:52:56",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":26},[37,40,43],{"tool":38,"command":39},"npx","npx skills add yigitkonur\u002Fplugin-agentic-maker --skill build-skill",{"tool":41,"command":42},"bunx","bunx skills add yigitkonur\u002Fplugin-agentic-maker --skill build-skill",{"tool":44,"command":45},"pnpm","pnpm dlx skills add yigitkonur\u002Fplugin-agentic-maker --skill build-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fyigitkonur\u002Fplugin-agentic-maker\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-skill\u002FSKILL.md",[48,54,58,62,66,70,74,78,82,86,90,94,98],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"agents\u002Fopenai.yaml","REFERENCE","参考文档",256,"https:\u002F\u002Fgithub.com\u002Fyigitkonur\u002Fplugin-agentic-maker\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-skill\u002Fagents\u002Fopenai.yaml",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fanti-patterns-content.md",5015,"https:\u002F\u002Fgithub.com\u002Fyigitkonur\u002Fplugin-agentic-maker\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-skill\u002Freferences\u002Fanti-patterns-content.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fanti-patterns-process.md",5839,"https:\u002F\u002Fgithub.com\u002Fyigitkonur\u002Fplugin-agentic-maker\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-skill\u002Freferences\u002Fanti-patterns-process.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fchecklist.md",6357,"https:\u002F\u002Fgithub.com\u002Fyigitkonur\u002Fplugin-agentic-maker\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-skill\u002Freferences\u002Fchecklist.md",{"path":67,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":68,"sourceHtmlUrl":69},"references\u002Ffrontmatter.md",5894,"https:\u002F\u002Fgithub.com\u002Fyigitkonur\u002Fplugin-agentic-maker\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-skill\u002Freferences\u002Ffrontmatter.md",{"path":71,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Finstruction-strength.md",6433,"https:\u002F\u002Fgithub.com\u002Fyigitkonur\u002Fplugin-agentic-maker\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-skill\u002Freferences\u002Finstruction-strength.md",{"path":75,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fnaming-and-boundaries.md",6150,"https:\u002F\u002Fgithub.com\u002Fyigitkonur\u002Fplugin-agentic-maker\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-skill\u002Freferences\u002Fnaming-and-boundaries.md",{"path":79,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Freferences-and-scripts.md",6983,"https:\u002F\u002Fgithub.com\u002Fyigitkonur\u002Fplugin-agentic-maker\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-skill\u002Freferences\u002Freferences-and-scripts.md",{"path":83,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Ftest-with-fresh-agents.md",6838,"https:\u002F\u002Fgithub.com\u002Fyigitkonur\u002Fplugin-agentic-maker\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-skill\u002Freferences\u002Ftest-with-fresh-agents.md",{"path":87,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Ftroubleshooting.md",6979,"https:\u002F\u002Fgithub.com\u002Fyigitkonur\u002Fplugin-agentic-maker\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-skill\u002Freferences\u002Ftroubleshooting.md",{"path":91,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fworked-examples.md",4654,"https:\u002F\u002Fgithub.com\u002Fyigitkonur\u002Fplugin-agentic-maker\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-skill\u002Freferences\u002Fworked-examples.md",{"path":95,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Fworkflow-patterns.md",5793,"https:\u002F\u002Fgithub.com\u002Fyigitkonur\u002Fplugin-agentic-maker\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-skill\u002Freferences\u002Fworkflow-patterns.md",{"path":99,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Fwrapping-mcp-tools.md",6006,"https:\u002F\u002Fgithub.com\u002Fyigitkonur\u002Fplugin-agentic-maker\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-skill\u002Freferences\u002Fwrapping-mcp-tools.md",[103,109,115,121,128,135],{"skillNo":104,"name":105,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M7F6C40YCW0N1P9ENGE9WN50","design","https:\u002F\u002Fgithub.com\u002Fyigitkonur\u002Fplugin-agentic-maker\u002Fblob\u002Fmain\u002Fskills\u002Fdesign\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":19},"01M7F6C1RY3KEX7MZ34NF0SR2V","derailment-method","https:\u002F\u002Fgithub.com\u002Fyigitkonur\u002Fplugin-agentic-maker\u002Fblob\u002Fmain\u002Fskills\u002Fderailment-method\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":19},"01M7F6BYP9843BZRKVG0K13HBK","targets","https:\u002F\u002Fgithub.com\u002Fyigitkonur\u002Fplugin-agentic-maker\u002Fblob\u002Fmain\u002Fskills\u002Fderail\u002Freferences\u002Ftargets\u002Fskill.md",[],[],{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":19},"01M7F6BTN9TZSN9QD6B5QG0JQD","derail","Test a skill, plugin, CLI or MCP tool with fresh agents and fix the text that misled them. Started by you; spends usage.","https:\u002F\u002Fgithub.com\u002Fyigitkonur\u002Fplugin-agentic-maker\u002Fblob\u002Fmain\u002Fskills\u002Fderail\u002FSKILL.md",[],[],{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":19},"01M7F6BK9QTJC0KR2GR6KGX4QQ","build-mcp","Build, extend or repair an MCP server for agents, probe it, hand over the test. Started by you.","https:\u002F\u002Fgithub.com\u002Fyigitkonur\u002Fplugin-agentic-maker\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-mcp\u002FSKILL.md",[],[],{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":19},"01M7F6BGP7DJJ3HJ604SF207TZ","build-cli","Build or repair an agent-facing CLI, probe it, hand over the test. Started by you.","https:\u002F\u002Fgithub.com\u002Fyigitkonur\u002Fplugin-agentic-maker\u002Fblob\u002Fmain\u002Fskills\u002Fbuild-cli\u002FSKILL.md",[],[]]