[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ADWZQAPATY3AXFMG21B7SF":3,"skill-same:01M7ADWZQAPATY3AXFMG21B7SF":49},{"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":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M7ADWZQAPATY3AXFMG21B7SF","self-extend",null,"Use when evolving the agent's own capabilities with a new skill, custom subagent, plugin, hook, MCP server, or project rule.","Leostruka\u002Fdevin-bundle","Leostruka","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F81370685?v=4","01M7AD8MAK63VDNAWRDRRRW04N","leandro ostruka","01M7AD8MBS65YDS1KMMV7YPM07",0,"MIT","https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Fskills\u002Fself-extend\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: self-extend\ndescription: Use when evolving the agent's own capabilities with a new skill, custom subagent, plugin, hook, MCP server, or project rule.\ntriggers: [user, model]\n---\n# Self-Extension\n\n## Overview\n\nExtend Devin CLI's behavior by adding files to the project (`.\u002F.devin\u002F`) or to your global Devin config (`~\u002F.config\u002Fdevin\u002F` on Linux\u002FmacOS, `%APPDATA%\\devin\\` on Windows). Most changes are picked up at the next session or skill reload.\n\n## What to create for each need\n\n| I want to... | Create | Location | Hot-reload |\n|---|---|---|---|\n| Add a reusable workflow the agent can invoke | Skill | `.devin\u002Fskills\u002F\u003Cname>\u002FSKILL.md` (project) or `~\u002F.config\u002Fdevin\u002Fskills\u002F\u003Cname>\u002FSKILL.md` (global) | next `skill list` \u002F session |\n| Define a specialized worker for a task type | Custom subagent profile | `.devin\u002Fagents\u002F\u003Cname>.md` or `.devin\u002Fagents\u002F\u003Cname>\u002FAGENT.md` (project\u002Fglobal `~\u002F.config\u002Fdevin\u002Fagents\u002F`) | next session |\n| Add always-on context for a project or globally | Rules | `.devin\u002Fglobal_rules.md` or `.devin\u002Frules\u002F*.md` (project); `~\u002F.config\u002Fdevin\u002FAGENTS.md` (global) | session start |\n| Run custom logic at lifecycle events | Hooks | `.devin\u002Fhooks.v1.json` or `.devin\u002Fhooks.json` | next session |\n| Give the agent new API\u002Fdatabase tools | MCP server | `.devin\u002Fmcp_config.json` or `~\u002F.config\u002Fdevin\u002Fmcp_config.json` | next session |\n| Bundle skills\u002Frules\u002Fhooks\u002FMCP for distribution | Plugin | `.devin-plugin\u002Fplugin.json` manifest + skills\u002Frules\u002Fhooks\u002Fmcp | install\u002Freload |\n\n## Creating skills\n\nBefore writing any skill or rule, invoke `writing-for-agents` to ensure the document follows agent-readable conventions (frontmatter, context pointers, completion criteria, pruning).\n\nProject skill (committed to repo):\n\n```markdown\n---\nname: my-skill\ndescription: Use when [specific triggering conditions]\n---\n\n# My Skill\n\n## Overview\n...\n```\n\nSave as `.devin\u002Fskills\u002Fmy-skill\u002FSKILL.md`. For personal skills, use `~\u002F.config\u002Fdevin\u002Fskills\u002Fmy-skill\u002FSKILL.md` (or `%APPDATA%\\devin\\skills\\my-skill\\SKILL.md` on Windows).\n\nSkill frontmatter can also set:\n\n- `allowed-tools`: restrict which tools the skill can use (e.g. `[read, grep, glob, exec]`)\n- `subagent: true`: run the skill as a `subagent_general` subagent\n- `agent: \u003Cprofile>`: run the skill as a specific custom subagent\n- `model`: override the model for this skill (e.g. `swe-2-max` [free], `swe-2-flash-high` [free], `swe-2-flash-medium` [free permanent]) - **never use paid models**\n- `permissions`: add permission grants\u002Frestrictions (e.g. `allow: [Read(src\u002F**)]`, `deny: [exec]`)\n- `triggers`: who can invoke it (default `[user, model]`)\n\nDiscover with `skill list --path .` and `skill search --path . --keywords \"...\"`. Invoke with `\u002Fmy-skill`.\n\n## Creating custom subagents\n\nCustom subagents are Devin CLI profiles that specialize in a kind of work (e.g. `reviewer`, `researcher`).\n\nProfile definition in `.devin\u002Fagents\u002Freviewer.md` or `.devin\u002Fagents\u002Freviewer\u002FAGENT.md`:\n\n```markdown\n---\nname: reviewer\n---\n\nYou are a careful code reviewer. Read the diff, then report only concrete issues with file paths and line numbers.\n```\n\nReference the profile in a skill frontmatter:\n\n```yaml\n---\nname: review-pr\ndescription: Use when the user asks for a focused PR review.\nagent: reviewer\n---\n```\n\nOr dispatch directly from a skill:\n\n```\nRun a `subagent_general` or `researcher` subagent (NOT `subagent_explore` when parent is FREE - runs on the CLI default router, possibly PAID) with the reviewer profile, passing the diff and the review checklist.\n```\n\n## Adding rules\n\n`.devin\u002Fglobal_rules.md` and `.devin\u002Frules\u002F*.md` inside the project are loaded by default. Keep them small; put detailed guidance in skills.\n\n`.devin\u002Frules\u002F*.md` files can have `trigger` frontmatter (`always_on`, `manual`, `model_decision`, `agent`, `glob`) to load only when relevant.\n\n`.devin\u002Fglobal_rules.md` is an always-on file inside `.devin\u002F`.\n\n## Adding hooks\n\nHooks run custom logic at session lifecycle events. Place them in `.devin\u002Fhooks.v1.json` or `.devin\u002Fhooks.json`.\n\nCommon events:\n\n| Event | Use |\n|---|---|\n| `PreToolUse` | Inspect or block a tool call |\n| `PostToolUse` | Log or modify tool output |\n| `PermissionRequest` | Auto-allow\u002Fdeny specific permission patterns |\n| `UserPromptSubmit` | Inject context when the user sends a message |\n| `Stop` | Run cleanup before the agent stops |\n| `SessionStart` \u002F `SessionEnd` | Setup\u002Fteardown |\n\nExample `.devin\u002Fhooks.v1.json`:\n\n```json\n{\n  \"hooks\": [\n    {\n      \"event\": \"PreToolUse\",\n      \"matcher\": \"exec\",\n      \"type\": \"command\",\n      \"command\": \"echo 'exec called: {{tool_name}}' >> .devin\u002Faudit.log\"\n    }\n  ]\n}\n```\n\n## Adding MCP servers\n\nMCP servers give the agent new tools. Configure them in `.devin\u002Fmcp_config.json` (project) or `~\u002F.config\u002Fdevin\u002Fmcp_config.json` (global):\n\n```json\n{\n  \"mcpServers\": {\n    \"github\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@modelcontextprotocol\u002Fserver-github\"],\n      \"env\": { }\n    }\n  }\n}\n```\n\nFor secrets, use `.devin\u002Fmcp_config.local.json` (gitignored).\n\n## Packaging as a plugin\n\nA plugin is a directory with a `.devin-plugin\u002Fplugin.json` manifest. It can ship:\n\n- `skills\u002F\u003Cname>\u002FSKILL.md`\n- `.devin\u002Fglobal_rules.md`\n- `.devin\u002Frules\u002F*.md`\n- `.devin\u002Fagents\u002F\u003Cname>.md`\n- `mcp_config.json`\n- `hooks.json`\u002F`hooks.v1.json`\n\nPlugins can be installed from a GitHub repo, git URL, or local folder when Devin CLI plugin support is enabled. See the Devin CLI docs for `plugin.json` format.\n\n## Helper scripts\n\nIf a skill needs executable helpers, keep them in the skill's `scripts\u002F` directory. Use Python for cross-platform work, Bash for one-off shell integration, or JavaScript if the helper is tool-specific. Document dependencies and exit codes.\n\n## Constraints\n\n- Do not ask users for secrets; put credentials in `.devin\u002Fconfig.local.json` or env vars.\n- Do not modify repository security policies or CI compliance settings.\n- Keep `.devin\u002Fglobal_rules.md` small; prefer skills for detailed guidance.\n- Prefer standard Devin CLI paths; do not reference non-Devin runtimes.\n\n## Dynamic Subagent Construction (AOrchestra 4-tuple)\n\nAny subagent can be described as a 4-tuple: **⟨Instruction, Context, Tools, Model⟩**.\nThe 7 fixed profiles (architect, debugger, implementer, researcher, reviewer,\nsubagent_explore [PAID - não usar quando parent FREE], subagent_general) are pre-configured 4-tuples. For task-specific\nspecialization, override individual tuple elements instead of creating a new profile:\n\n| Element | What it controls | When to override |\n|---|---|---|\n| **Instruction** | What the subagent must accomplish | Task needs a specific goal not covered by any profile |\n| **Context** | Task-relevant working memory | Task needs scoped context (filter out irrelevant files\u002Fhistory) |\n| **Tools** | Actions the subagent can take | Task needs restricted tool access (e.g., read-only exploration) |\n| **Model** | Which LLM executes | Cost-performance trade-off (cheaper model for simple subtasks) |\n\n**How to apply:** When dispatching via `run_subagent`, specify `task` (instruction),\n`profile` (defaults for context\u002Ftools\u002Fmodel), and override with task-specific\nconstraints in the `task` text. The 7 profiles remain as backward-compatible defaults.\n\n**Source:** AOrchestra (ICML 2026, arXiv:2602.03786). \"Sub-agents should be treated\nas recipes created at runtime, not fixed roles.\" Training-free mode: 16.28% relative\nimprovement over baselines. SFT mode: +11.51% pass@1 on GAIA (requires 2K trajectories).\n\n## Cross-skills\n\n- Use `ai-coding-dictionary` to align terms like subagent, harness, and context engineering before writing new skills or rules.\n- Use `continuous-improvement` to validate that the new skill or rule actually improves the bundle, not just adds it.\n","# Self-Extension\n\n## Overview\n\nExtend Devin CLI's behavior by adding files to the project (`.\u002F.devin\u002F`) or to your global Devin config (`~\u002F.config\u002Fdevin\u002F` on Linux\u002FmacOS, `%APPDATA%\\devin\\` on Windows). Most changes are picked up at the next session or skill reload.\n\n## What to create for each need\n\n| I want to... | Create | Location | Hot-reload |\n|---|---|---|---|\n| Add a reusable workflow the agent can invoke | Skill | `.devin\u002Fskills\u002F\u003Cname>\u002FSKILL.md` (project) or `~\u002F.config\u002Fdevin\u002Fskills\u002F\u003Cname>\u002FSKILL.md` (global) | next `skill list` \u002F session |\n| Define a specialized worker for a task type | Custom subagent profile | `.devin\u002Fagents\u002F\u003Cname>.md` or `.devin\u002Fagents\u002F\u003Cname>\u002FAGENT.md` (project\u002Fglobal `~\u002F.config\u002Fdevin\u002Fagents\u002F`) | next session |\n| Add always-on context for a project or globally | Rules | `.devin\u002Fglobal_rules.md` or `.devin\u002Frules\u002F*.md` (project); `~\u002F.config\u002Fdevin\u002FAGENTS.md` (global) | session start |\n| Run custom logic at lifecycle events | Hooks | `.devin\u002Fhooks.v1.json` or `.devin\u002Fhooks.json` | next session |\n| Give the agent new API\u002Fdatabase tools | MCP server | `.devin\u002Fmcp_config.json` or `~\u002F.config\u002Fdevin\u002Fmcp_config.json` | next session |\n| Bundle skills\u002Frules\u002Fhooks\u002FMCP for distribution | Plugin | `.devin-plugin\u002Fplugin.json` manifest + skills\u002Frules\u002Fhooks\u002Fmcp | install\u002Freload |\n\n## Creating skills\n\nBefore writing any skill or rule, invoke `writing-for-agents` to ensure the document follows agent-readable conventions (frontmatter, context pointers, completion criteria, pruning).\n\nProject skill (committed to repo):\n\n```markdown\n---\nname: my-skill\ndescription: Use when [specific triggering conditions]\n---\n\n# My Skill\n\n## Overview\n...\n```\n\nSave as `.devin\u002Fskills\u002Fmy-skill\u002FSKILL.md`. For personal skills, use `~\u002F.config\u002Fdevin\u002Fskills\u002Fmy-skill\u002FSKILL.md` (or `%APPDATA%\\devin\\skills\\my-skill\\SKILL.md` on Windows).\n\nSkill frontmatter can also set:\n\n- `allowed-tools`: restrict which tools the skill can use (e.g. `[read, grep, glob, exec]`)\n- `subagent: true`: run the skill as a `subagent_general` subagent\n- `agent: \u003Cprofile>`: run the skill as a specific custom subagent\n- `model`: override the model for this skill (e.g. `swe-2-max` [free], `swe-2-flash-high` [free], `swe-2-flash-medium` [free permanent]) - **never use paid models**\n- `permissions`: add permission grants\u002Frestrictions (e.g. `allow: [Read(src\u002F**)]`, `deny: [exec]`)\n- `triggers`: who can invoke it (default `[user, model]`)\n\nDiscover with `skill list --path .` and `skill search --path . --keywords \"...\"`. Invoke with `\u002Fmy-skill`.\n\n## Creating custom subagents\n\nCustom subagents are Devin CLI profiles that specialize in a kind of work (e.g. `reviewer`, `researcher`).\n\nProfile definition in `.devin\u002Fagents\u002Freviewer.md` or `.devin\u002Fagents\u002Freviewer\u002FAGENT.md`:\n\n```markdown\n---\nname: reviewer\n---\n\nYou are a careful code reviewer. Read the diff, then report only concrete issues with file paths and line numbers.\n```\n\nReference the profile in a skill frontmatter:\n\n```yaml\n---\nname: review-pr\ndescription: Use when the user asks for a focused PR review.\nagent: reviewer\n---\n```\n\nOr dispatch directly from a skill:\n\n```\nRun a `subagent_general` or `researcher` subagent (NOT `subagent_explore` when parent is FREE - runs on the CLI default router, possibly PAID) with the reviewer profile, passing the diff and the review checklist.\n```\n\n## Adding rules\n\n`.devin\u002Fglobal_rules.md` and `.devin\u002Frules\u002F*.md` inside the project are loaded by default. Keep them small; put detailed guidance in skills.\n\n`.devin\u002Frules\u002F*.md` files can have `trigger` frontmatter (`always_on`, `manual`, `model_decision`, `agent`, `glob`) to load only when relevant.\n\n`.devin\u002Fglobal_rules.md` is an always-on file inside `.devin\u002F`.\n\n## Adding hooks\n\nHooks run custom logic at session lifecycle events. Place them in `.devin\u002Fhooks.v1.json` or `.devin\u002Fhooks.json`.\n\nCommon events:\n\n| Event | Use |\n|---|---|\n| `PreToolUse` | Inspect or block a tool call |\n| `PostToolUse` | Log or modify tool output |\n| `PermissionRequest` | Auto-allow\u002Fdeny specific permission patterns |\n| `UserPromptSubmit` | Inject context when the user sends a message |\n| `Stop` | Run cleanup before the agent stops |\n| `SessionStart` \u002F `SessionEnd` | Setup\u002Fteardown |\n\nExample `.devin\u002Fhooks.v1.json`:\n\n```json\n{\n  \"hooks\": [\n    {\n      \"event\": \"PreToolUse\",\n      \"matcher\": \"exec\",\n      \"type\": \"command\",\n      \"command\": \"echo 'exec called: {{tool_name}}' >> .devin\u002Faudit.log\"\n    }\n  ]\n}\n```\n\n## Adding MCP servers\n\nMCP servers give the agent new tools. Configure them in `.devin\u002Fmcp_config.json` (project) or `~\u002F.config\u002Fdevin\u002Fmcp_config.json` (global):\n\n```json\n{\n  \"mcpServers\": {\n    \"github\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@modelcontextprotocol\u002Fserver-github\"],\n      \"env\": { }\n    }\n  }\n}\n```\n\nFor secrets, use `.devin\u002Fmcp_config.local.json` (gitignored).\n\n## Packaging as a plugin\n\nA plugin is a directory with a `.devin-plugin\u002Fplugin.json` manifest. It can ship:\n\n- `skills\u002F\u003Cname>\u002FSKILL.md`\n- `.devin\u002Fglobal_rules.md`\n- `.devin\u002Frules\u002F*.md`\n- `.devin\u002Fagents\u002F\u003Cname>.md`\n- `mcp_config.json`\n- `hooks.json`\u002F`hooks.v1.json`\n\nPlugins can be installed from a GitHub repo, git URL, or local folder when Devin CLI plugin support is enabled. See the Devin CLI docs for `plugin.json` format.\n\n## Helper scripts\n\nIf a skill needs executable helpers, keep them in the skill's `scripts\u002F` directory. Use Python for cross-platform work, Bash for one-off shell integration, or JavaScript if the helper is tool-specific. Document dependencies and exit codes.\n\n## Constraints\n\n- Do not ask users for secrets; put credentials in `.devin\u002Fconfig.local.json` or env vars.\n- Do not modify repository security policies or CI compliance settings.\n- Keep `.devin\u002Fglobal_rules.md` small; prefer skills for detailed guidance.\n- Prefer standard Devin CLI paths; do not reference non-Devin runtimes.\n\n## Dynamic Subagent Construction (AOrchestra 4-tuple)\n\nAny subagent can be described as a 4-tuple: **⟨Instruction, Context, Tools, Model⟩**.\nThe 7 fixed profiles (architect, debugger, implementer, researcher, reviewer,\nsubagent_explore [PAID - não usar quando parent FREE], subagent_general) are pre-configured 4-tuples. For task-specific\nspecialization, override individual tuple elements instead of creating a new profile:\n\n| Element | What it controls | When to override |\n|---|---|---|\n| **Instruction** | What the subagent must accomplish | Task needs a specific goal not covered by any profile |\n| **Context** | Task-relevant working memory | Task needs scoped context (filter out irrelevant files\u002Fhistory) |\n| **Tools** | Actions the subagent can take | Task needs restricted tool access (e.g., read-only exploration) |\n| **Model** | Which LLM executes | Cost-performance trade-off (cheaper model for simple subtasks) |\n\n**How to apply:** When dispatching via `run_subagent`, specify `task` (instruction),\n`profile` (defaults for context\u002Ftools\u002Fmodel), and override with task-specific\nconstraints in the `task` text. The 7 profiles remain as backward-compatible defaults.\n\n**Source:** AOrchestra (ICML 2026, arXiv:2602.03786). \"Sub-agents should be treated\nas recipes created at runtime, not fixed roles.\" Training-free mode: 16.28% relative\nimprovement over baselines. SFT mode: +11.51% pass@1 on GAIA (requires 2K trajectories).\n\n## Cross-skills\n\n- Use `ai-coding-dictionary` to align terms like subagent, harness, and context engineering before writing new skills or rules.\n- Use `continuous-improvement` to validate that the new skill or rule actually improves the bundle, not just adds it.\n",{"name":5,"triggers":24,"description":7},[25,26],"user","model","main","02b95ddb62959a00b3c31442c2046aca0d19563c","skills\u002Fself-extend",1,"https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle","https:\u002F\u002Fleostruka.github.io\u002Fdevin-bundle\u002F","https:\u002F\u002Fgithub.com\u002FLeostruka","2026-11-15 05:19:58",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add Leostruka\u002Fdevin-bundle --skill self-extend",{"tool":41,"command":42},"bunx","bunx skills add Leostruka\u002Fdevin-bundle --skill self-extend",{"tool":44,"command":45},"pnpm","pnpm dlx skills add Leostruka\u002Fdevin-bundle --skill self-extend","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Fskills\u002Fself-extend\u002FSKILL.md",true,[],[50,57,64,71,78,85],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7E0K3MG2XC4FSRV0MK6SFR1","montador-de-ideias","Use when assembling, expanding, or elevating a raw project idea or initial prompt into an ultra-detailed, first-principles dossier and compiled master prompt with journalistic OSINT market research, Tech Lead and Staff Architect justifications, atomic and modular hardening\u002Foptimization, and high-impact contact surfaces.","https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Fskills\u002Fmontador-de-ideias\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M7E0J7JJWZ8QMK01RZ3B3C9Z","git-github-adaptive-engineering","Use when any task touches git history, GitHub issues\u002FPRs\u002Freleases\u002FCI, repo governance, or branch and merge decisions. Runs the Fase Zero situational-awareness battery, picks one of five delivery flows via the adaptive decision engine, and enforces commit\u002FPR information-density standards. Orchestrates the gh, git-workflows, github-actions, pr, and debug\u002Ffinish skills.","https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Fskills\u002Fgit-github-adaptive-engineering\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7E0GJFRPFEVQQMXEM58EWDM","adaptive-agenda-calendar-routine-engine","Use when planning or executing work across hours, days, weeks, or sprints. Turns the calendar into a strict time-blocked agenda (HH:MM-HH:MM blocks carrying a routine profile, expected inputs, and a handoff output artifact), runs the 5-stage cognitive flow (Radar and Hunt -> Triage plus Steve Jobs conception -> workbench manifest -> >=32-cycle loop -> Close plus Open-Minded Scrum), and unfolds macro calendar milestones into micro agenda blocks through extensions\u002Fgcal\u002Fwrapper.py.","https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Fskills\u002Fadaptive-agenda-calendar-routine-engine\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7AE2K9FTY0BVS48N0A9JFKF","demo","Use when demonstrating a skill in a fixture project.","https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fdevin-config\u002Fproject\u002F.devin\u002Fskills\u002Fdemo\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":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7AE2G3DP38PTV3B1N7MW5TS","duplicate-skill","Use when testing duplicate skill name detection.","https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fdevin-config\u002Fproject\u002F.devin\u002Fskills\u002Fbeta\u002FSKILL.md",[],[],{"skillNo":86,"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":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7AE2DBR8ZHT6T875MJ392GK","https:\u002F\u002Fgithub.com\u002FLeostruka\u002Fdevin-bundle\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fdevin-config\u002Fproject\u002F.devin\u002Fskills\u002Falpha\u002FSKILL.md",[],[]]