[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M753WH2ND455K771JSF6Q0XY":3,"skill-same:01M753WH2ND455K771JSF6Q0XY":68},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M753WH2ND455K771JSF6Q0XY","skill-best-practices",null,"Authors and structures professional-grade agent skills following the agentskills.io spec. Use when creating new skill directories, drafting procedural instructions, or optimizing metadata for discoverability. Don't use for general documentation, non-agentic library code, or README files.","haryelramalho\u002Fskills","haryelramalho","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F38708454?v=4","01M753ESC6XNS6GXGV5X9YMKGA","Haryel Ramalho","01M753ESCSPRNDTEJRVRYY1VJ0",0,"MIT","https:\u002F\u002Fgithub.com\u002Fharyelramalho\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcurated\u002Fskill-best-practices\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: skill-best-practices\ndescription: Authors and structures professional-grade agent skills following the agentskills.io spec. Use when creating new skill directories, drafting procedural instructions, or optimizing metadata for discoverability. Don't use for general documentation, non-agentic library code, or README files.\nmetadata:\n  author: Pedro Nauck\n  github: https:\u002F\u002Fgithub.com\u002Fpedronauck\n  repository: https:\u002F\u002Fgithub.com\u002Fpedronauck\u002Fskills\n---\n# Skill Authoring Procedure\n\nFollow these steps to generate a skill that adheres to the agentskills.io specification and progressive disclosure principles.\n\n## Bundled Path Rule\n\nResolve bundled paths relative to the directory that contains this `SKILL.md`. When invoking a helper from another working directory, expand `\u003Cskill-best-practices-dir>` to that directory first so the command is unambiguous.\n\n## Step 1: Initialize and Validate Metadata\n1.  Define a unique `name`: 1-64 characters, lowercase, numbers, and single hyphens only.\n2.  Draft a `description`: Max 1,024 characters, written in the third person, including negative triggers.\n3.  **Execute Validation Script (read-only helper):** Run the validation script to ensure compliance before proceeding:\n    `python3 \u003Cskill-best-practices-dir>\u002Fscripts\u002Fvalidate-metadata.py --name \"[name]\" --description \"[description]\"`\n4.  If the script returns an error, self-correct the metadata based on the `stderr` output and re-run until successful.\n\n## Step 2: Structure the Directory\n1.  Create the root directory using the validated `name`.\n2.  Initialize the following subdirectories:\n    *   `scripts\u002F`: For tiny CLI tools and deterministic logic.\n    *   `references\u002F`: For flat (one-level deep) context like schemas or API docs.\n    *   `assets\u002F`: For output templates, JSON schemas, or static files.\n3.  Ensure no human-centric files (README.md, INSTALLATION.md) are created.\n\n## Step 3: Draft Core Logic (SKILL.md)\n1.  Use the template in `assets\u002FSKILL.template.md` as the starting point.\n2.  Write all instructions in the **third-person imperative** (e.g., \"Extract the text,\" \"Run the build\").\n3.  **Enforce Progressive Disclosure:**\n    *   Keep the main logic under 500 lines.\n    *   If a procedure requires a large schema or complex rule set, move it to `references\u002F`.\n    *   Command the agent to read the specific file only when needed: *\"Read references\u002Fapi-spec.md to identify the correct endpoint.\"*\n\n## Step 4: Identify and Bundle Scripts\n1.  Identify \"fragile\" tasks (regex, complex parsing, or repetitive boilerplate).\n2.  Outline a single-purpose script for the `scripts\u002F` directory.\n3.  Ensure the script uses standard output (stdout\u002Fstderr) to communicate success or failure to the agent.\n4.  In `SKILL.md`, reference bundled helpers by a path that is unambiguous from the agent's working directory (the same path the agent will type to invoke them), rather than bare `scripts\u002Fhelper.py` snippets that silently depend on CWD.\n5.  Label each helper as **read-only**, **bootstrap**, or **mutating** so downstream agents know whether the helper only inspects state or changes it.\n\n## Step 5: Final Logic Validation\n1.  Review the `SKILL.md` for \"hallucination gaps\" (points where the agent is forced to guess).\n2.  Verify all file paths are **relative** and use forward slashes (`\u002F`).\n3.  Verify every referenced helper path is unambiguous from the agent's working directory and that the helper's role (`read-only`, `bootstrap`, or `mutating`) is stated.\n4.  Read `references\u002Fchecklist.md` and cross-reference every checklist item against the final output.\n\n## Error Handling\n*   **Metadata Failure:** If `scripts\u002Fvalidate-metadata.py` fails, identify the specific error (e.g., \"STYLE ERROR\") and rewrite the field to remove first\u002Fsecond person pronouns.\n*   **Context Bloat:** If the draft exceeds 500 lines, extract the largest procedural block and move it to a file in `references\u002F`.\n","# Skill Authoring Procedure\n\nFollow these steps to generate a skill that adheres to the agentskills.io specification and progressive disclosure principles.\n\n## Bundled Path Rule\n\nResolve bundled paths relative to the directory that contains this `SKILL.md`. When invoking a helper from another working directory, expand `\u003Cskill-best-practices-dir>` to that directory first so the command is unambiguous.\n\n## Step 1: Initialize and Validate Metadata\n1.  Define a unique `name`: 1-64 characters, lowercase, numbers, and single hyphens only.\n2.  Draft a `description`: Max 1,024 characters, written in the third person, including negative triggers.\n3.  **Execute Validation Script (read-only helper):** Run the validation script to ensure compliance before proceeding:\n    `python3 \u003Cskill-best-practices-dir>\u002Fscripts\u002Fvalidate-metadata.py --name \"[name]\" --description \"[description]\"`\n4.  If the script returns an error, self-correct the metadata based on the `stderr` output and re-run until successful.\n\n## Step 2: Structure the Directory\n1.  Create the root directory using the validated `name`.\n2.  Initialize the following subdirectories:\n    *   `scripts\u002F`: For tiny CLI tools and deterministic logic.\n    *   `references\u002F`: For flat (one-level deep) context like schemas or API docs.\n    *   `assets\u002F`: For output templates, JSON schemas, or static files.\n3.  Ensure no human-centric files (README.md, INSTALLATION.md) are created.\n\n## Step 3: Draft Core Logic (SKILL.md)\n1.  Use the template in `assets\u002FSKILL.template.md` as the starting point.\n2.  Write all instructions in the **third-person imperative** (e.g., \"Extract the text,\" \"Run the build\").\n3.  **Enforce Progressive Disclosure:**\n    *   Keep the main logic under 500 lines.\n    *   If a procedure requires a large schema or complex rule set, move it to `references\u002F`.\n    *   Command the agent to read the specific file only when needed: *\"Read references\u002Fapi-spec.md to identify the correct endpoint.\"*\n\n## Step 4: Identify and Bundle Scripts\n1.  Identify \"fragile\" tasks (regex, complex parsing, or repetitive boilerplate).\n2.  Outline a single-purpose script for the `scripts\u002F` directory.\n3.  Ensure the script uses standard output (stdout\u002Fstderr) to communicate success or failure to the agent.\n4.  In `SKILL.md`, reference bundled helpers by a path that is unambiguous from the agent's working directory (the same path the agent will type to invoke them), rather than bare `scripts\u002Fhelper.py` snippets that silently depend on CWD.\n5.  Label each helper as **read-only**, **bootstrap**, or **mutating** so downstream agents know whether the helper only inspects state or changes it.\n\n## Step 5: Final Logic Validation\n1.  Review the `SKILL.md` for \"hallucination gaps\" (points where the agent is forced to guess).\n2.  Verify all file paths are **relative** and use forward slashes (`\u002F`).\n3.  Verify every referenced helper path is unambiguous from the agent's working directory and that the helper's role (`read-only`, `bootstrap`, or `mutating`) is stated.\n4.  Read `references\u002Fchecklist.md` and cross-reference every checklist item against the final output.\n\n## Error Handling\n*   **Metadata Failure:** If `scripts\u002Fvalidate-metadata.py` fails, identify the specific error (e.g., \"STYLE ERROR\") and rewrite the field to remove first\u002Fsecond person pronouns.\n*   **Context Bloat:** If the draft exceeds 500 lines, extract the largest procedural block and move it to a file in `references\u002F`.\n",{"name":5,"metadata":24,"description":7},{"author":25,"github":26,"repository":27},"Pedro Nauck","https:\u002F\u002Fgithub.com\u002Fpedronauck","https:\u002F\u002Fgithub.com\u002Fpedronauck\u002Fskills","main","a5b533be2d244bbf3e5606e851742f0e0ba99423","skills\u002Fcurated\u002Fskill-best-practices","https:\u002F\u002Fgithub.com\u002Fharyelramalho\u002Fskills","https:\u002F\u002Fgithub.com\u002Fharyelramalho","linkedin.com\u002Fin\u002Fharyelramalho\u002F","Software Engineer @ SKORR •  Former Vice President of the Junior Computer Association - TecnoJr","2026-07-16 01:34:58",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add haryelramalho\u002Fskills --skill skill-best-practices",{"tool":42,"command":43},"bunx","bunx skills add haryelramalho\u002Fskills --skill skill-best-practices",{"tool":45,"command":46},"pnpm","pnpm dlx skills add haryelramalho\u002Fskills --skill skill-best-practices","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fharyelramalho\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcurated\u002Fskill-best-practices\u002FSKILL.md",true,[50,56,62],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"assets\u002FSKILL.template.md","ASSET","资产文件",974,"https:\u002F\u002Fgithub.com\u002Fharyelramalho\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcurated\u002Fskill-best-practices\u002Fassets\u002FSKILL.template.md",{"path":57,"resourceType":58,"resourceTypeDesc":59,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Fchecklist.md","REFERENCE","参考文档",2768,"https:\u002F\u002Fgithub.com\u002Fharyelramalho\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcurated\u002Fskill-best-practices\u002Freferences\u002Fchecklist.md",{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"scripts\u002Fvalidate-metadata.py","SCRIPT","脚本",2124,"https:\u002F\u002Fgithub.com\u002Fharyelramalho\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcurated\u002Fskill-best-practices\u002Fscripts\u002Fvalidate-metadata.py",[69,76,83,90,97,104],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M753YDMKSDB7320THEQ2CVW5","to-prompt-opus","Use when preparing or rewriting prompts for Claude Opus 4.8, Anthropic API agents, XML-structured prompts, long-context document work, coding agents, research synthesis, frontend\u002Fdesign tasks, or model-specific prompt optimization. Do not use for GPT\u002FOpenAI prompts or raw context packaging without Opus-specific tuning.","https:\u002F\u002Fgithub.com\u002Fharyelramalho\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fmine\u002Fto-prompt-opus\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M753YAP95W4K2MCEAEEAV6YA","to-prompt-gpt","Use when preparing or rewriting prompts for GPT-5.5, OpenAI API agents, Responses workflows, coding agents, research synthesis, support assistants, or model-specific prompt optimization. Do not use for Claude\u002FOpus prompts or raw context packaging without GPT-specific tuning.","https:\u002F\u002Fgithub.com\u002Fharyelramalho\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fmine\u002Fto-prompt-gpt\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"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},"01M753Y700AZ0GVJDNW9Q1Q54F","plan-refactor-qa","Plans and runs qa-report before executing Compozy refactor tasks. Use when the user provides a refactor or issue slug and wants Codex to inspect the matching .compozy\u002Ftasks directory, related PRD\u002FTechSpec\u002FADR\u002Ftask artifacts, affected code, and existing tests, then invoke $qa-report with a repository-grounded prompt. Do not use to run tests, execute qa-execution, implement code, or perform post-refactor verification.","https:\u002F\u002Fgithub.com\u002Fharyelramalho\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fmine\u002Fplan-refactor-qa\u002FSKILL.md",[],[],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M753XZENG0Z8S2ET75EM8CGB","multi-tool-branch-review","Orchestrates a multi-tool branch review of the current git branch against a base branch. By default it runs two independent thermo-nuclear maintainability audits, one on Codex GPT-5.5 xhigh and one on Claude Opus xhigh, then consolidates the findings into a single remediation plan via writing-plans. If the user explicitly asks for native reviews, it can add the Claude native review pass, the Codex native review pass, or both. Use when the user wants a deep cross-model review of a branch or PR before merge, or asks to review this branch with multiple tools or models. Encodes known infra failure modes and their fixes (missing Claude ACP adapter, Codex MCP auth hangs, false-positive report files, long jobs orphaned inside subagents). Do not use for reviewing a single uncommitted snippet, for non-git work, for running only one reviewer, or when the user only wants a quick lint or test run.","https:\u002F\u002Fgithub.com\u002Fharyelramalho\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fmine\u002Fmulti-tool-branch-review\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M753XQM40XCK55BH5WPA88EW","create-pr-with-template","Create a GitHub Pull Request with gh CLI and prefer repository PR templates automatically. Use this whenever the user asks to open\u002Fcreate a PR, especially when template compliance is needed. If multiple templates exist, ask the user which template to use.","https:\u002F\u002Fgithub.com\u002Fharyelramalho\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fmine\u002Fcreate-pr-with-template\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":19},"01M753XJMBJ8VFPRCDCC1JJ9G4","ui-craft","Provides guardrails for user-facing UI work: usability heuristics, accessibility floors, design-system discipline, component states, microcopy, motion, dark mode, responsive behavior, and human-AI UX. Use when designing, generating, reviewing, or refactoring visible product surfaces such as components, pages, dashboards, forms, dialogs, loading\u002Fempty\u002Ferror states, or AI interfaces. Do not use for backend-only work, infrastructure, CLI\u002FTUI design, or pure documentation editing.","https:\u002F\u002Fgithub.com\u002Fharyelramalho\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fcurated\u002Fui-craft\u002FSKILL.md",[],[]]