[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78153J42VKQJSV4X49FVCQE":3,"skill-same:01M78153J42VKQJSV4X49FVCQE":74},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M78153J42VKQJSV4X49FVCQE","settings-validator",null,"Validate or design Claude Code managed, user, shared-project, or project-local settings against the official docs and JSON schema. Use when the user pastes or names settings.json, settings.local.json, managed settings, or an admin-console configuration, or asks to check or write one.","filippolmt\u002Fskills","filippolmt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F61194571?v=4","01M7808VK1A8QF8ZXGT2DWTKHS","Filippo Merante Caparrotta","01M7808VKN74HC3EZMK8EV35KS",1,"MIT","https:\u002F\u002Fgithub.com\u002Ffilippolmt\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fplugins\u002Fpackages\u002Fsettings-validator\u002Fskills\u002Fsettings-validator\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ffilippolmt\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fplugins\u002Fpackages\u002Fsettings-validator\u002Fskills\u002Fsettings-validator\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: settings-validator\ndescription: Validate or design Claude Code managed, user, shared-project, or project-local settings against the official docs and JSON schema. Use when the user pastes or names settings.json, settings.local.json, managed settings, or an admin-console configuration, or asks to check or write one.\n---\n\n# Validate or design a Claude Code settings.json\n\nDeliver a **verdict** on the file (errors, warnings, best practice, each with its\nsource) and the **complete corrected JSON** for the right settings source.\n\n## 1. Scope and intent\n\nAsk with `AskUserQuestion` when available, in rounds of up to four questions\nwith concrete options, and only what the request leaves open: a pasted file\nalready answers the starting point.\n\n**Round 1**:\n\n- **settings source**: *managed*, *user*, *shared project*\n  (`.claude\u002Fsettings.json`), or *project local* (`.claude\u002Fsettings.local.json`);\n  for *managed*, also the **delivery**: admin console (server-managed), MDM, or\n  `managed-settings.json` file\n- **starting point**: an existing file (ask the user to paste it; for a local\n  file you may read it yourself if the user prefers), or **from scratch**\n- **environment**: OS and runtime, including WSL, container or CI constraints\n- **who uses it**: one person, a team, CI, or cloud sessions\n\n**Round 2**, the key questions; from scratch they are the whole design, on an\nexisting file ask only those the file leaves open:\n\n- **use**: everyday development, infrastructure and production access, CI and\n  automation, exploration\n- **posture**: *strict* (deny by default, sandbox without escape), *balanced*\n  (sandbox with escape, prompts on risky actions), *permissive* (few prompts)\n- **permission mode**: recommend a currently documented mode, state its prompt\n  behavior and risk, and ask for confirmation; the Manual label uses the\n  `default` config value\n- **must never happen** (multi-select): secrets read (SSH keys, cloud\n  credentials, `.env`, kubeconfig), commands outside the sandbox, unapproved\n  plugins or marketplaces, bypass permissions mode\n\n**Round 3**, only for the areas the user wants configured:\n\n- plugins and marketplaces: which to enforce, which to allow, auto-update\n- model: default and fallback\n- commit and PR attribution, language, UI\n\nDone when you know the settings source, the starting point, the posture, and a\ngoal for every area the file touches or the answers call for. An area the user\ndeclines to decide keeps its current value, or its default from scratch.\n\n## 2. Sources\n\nRead on every run: keys change often and memory goes stale. Download each\ndocs page as raw Markdown and read a key's type, enum, default and scope from\nits own `` ### `\u003Ckey>` `` section (nested keys use the dotted path):\n\n```bash\ncurl -sfL https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002F\u003Cpage>.md -o \u003Ctmp>\u002F\u003Cpage>.md\ngrep -n -F '### `\u003Ckey>`' \u003Ctmp>\u002F\u003Cpage>.md\n```\n\nA summarizing fetch (`WebFetch`) reads only the first 100 KB of the 400 KB\nreference and returned wrong types, enums and defaults: use it to find pages,\nnever as the source of a key's facts.\n\n- `https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fsettings`: scopes and precedence\n- `https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fsettings-reference`: every key with its scope\n  (`Any file`, `Managed`), default and an example\n- the schema `https:\u002F\u002Fjson.schemastore.org\u002Fclaude-code-settings.json`\n- for the areas touched, the pages the reference links: `permissions`,\n  `sandboxing`, `managed-settings`, `server-managed-settings`, `plugins\u002Forg`,\n  `plugins\u002Floading`, `plugins\u002Fhost-marketplace`, `plugin-marketplaces`\n- **secondary source** for best practice, a third-party copy that may lag:\n\n  ```bash\n  gh api repos\u002Fshanraisshan\u002Fclaude-code-best-practice\u002Fcontents\u002Fbest-practice\u002Fclaude-settings.md --jq .content | base64 -d\n  gh api 'repos\u002Fshanraisshan\u002Fclaude-code-best-practice\u002Fcommits?path=best-practice\u002Fclaude-settings.md&per_page=1' --jq '.[0].commit.committer.date'\n  ```\n\n  Where it disagrees with the official docs, the docs win and the disagreement\n  is reported; the known ones are under *Secondary-source errata* in\n  [`references\u002Fbest-practice.md`](references\u002Fbest-practice.md).\n\nDone when every page covering a key in the file, or an area the answers call\nfor, has been read, and you hold the secondary source's last commit date.\n\n## 3. Validation\n\nFrom scratch there is no file yet: skip to step 4, and run this step on the\ndraft before delivering it.\n\n1. Run [`scripts\u002Fcheck.py`](scripts\u002Fcheck.py) on the JSON saved to a temp file,\n   with the reference downloaded in step 2:\n\n   ```bash\n   uv run \u003Cskill dir>\u002Fscripts\u002Fcheck.py \u003Cfile> --reference \u003Ctmp>\u002Fsettings-reference.md\n   ```\n\n   `uv run` installs `jsonschema` from the script's header; without `uv`, use\n   `python3` and, if `jsonschema` is missing, install it as the script says.\n   It reports `SYNTAX`, `DUP`, `SCHEMA` and `UNKNOWN`, the last tagged\n   `(documented)` or `(undocumented)`; weigh each `UNKNOWN` as\n   [`references\u002Fbest-practice.md`](references\u002Fbest-practice.md) says. Exit 2\n   means the check did not run; when the schema did not load, fetch its URL\n   with `curl` into a file and rerun with `--schema \u003Cfile>`.\n\n   A check that never ran is reported as such: the verdict says the schema\n   was not checked, never that the file is clean.\n2. Check every key against the reference:\n   - **scope**: confirm that the chosen settings source supports the key; flag\n     global-config keys because they belong in `~\u002F.claude.json`\n   - **values**: types, enums and limits\n   - **default**: on an existing file, a value equal to the documented default\n     is redundant; report it as informational\n   - **deprecated or renamed keys**\n\nDone when every key has been checked against reference and schema, and\n`check.py` ran and is clean or every line it reports is explained.\n\n## 4. Best practice\n\nApply [`references\u002Fbest-practice.md`](references\u002Fbest-practice.md) and the\nsecondary source to every area touched, measured against the goals from step 1.\nA best practice that contradicts a stated goal becomes a warning with its risk,\nnot an imposed fix.\n\nThen look for the **gaps**: keys absent from the file that serve a stated goal\n(a `deny` rule, a sandbox exception, a hook, an `env` value, a model default).\nWalk the settings reference area by area against the goals; propose each gap\nwith what it buys, what it costs, and a recommendation. Where two valid\nconfigurations trade off against a goal, ask the user rather than pick.\n\nDone when every area touched has a judgement (compliant, or the proposed change\nwith its reason) and every goal has either a key serving it or a stated reason\nnone is needed.\n\n## 5. Delivery\n\n- **Verdict**, in three groups: errors, warnings, best practice. Per item: the\n  key, the problem, the source (docs page or schema), and whether it is a\n  verified fact or an inference.\n- **The complete corrected JSON**, never a fragment: the user pastes it whole.\n  From scratch, write only keys\n  that serve an answer: a key restating its default adds nothing to maintain.\n- Below the JSON, what you changed and what you left alone on purpose.\n- The secondary source's last commit date, and each disagreement with the\n  official docs.\n- *Managed*: the JSON for its delivery, and which other managed sources it\n  overrides (*Managed settings* in\n  [`references\u002Fbest-practice.md`](references\u002Fbest-practice.md)). Once the user confirms it is deployed, verify each changed key\n  yourself with the probes in\n  [`references\u002Fverify-managed.md`](references\u002Fverify-managed.md), and hand the\n  user only the checks the CLI cannot make. *User*, *shared project*, or\n  *project local*: write the file only after the user's yes, and read its\n  current contents first.\n\nDone when `check.py` is clean on the delivered JSON, or each remaining line is\nan accepted trade-off named in the verdict; every verdict item names its\nsource; and, for managed settings the user deployed, every changed key is\nverified or listed as a manual check.\n","# Validate or design a Claude Code settings.json\n\nDeliver a **verdict** on the file (errors, warnings, best practice, each with its\nsource) and the **complete corrected JSON** for the right settings source.\n\n## 1. Scope and intent\n\nAsk with `AskUserQuestion` when available, in rounds of up to four questions\nwith concrete options, and only what the request leaves open: a pasted file\nalready answers the starting point.\n\n**Round 1**:\n\n- **settings source**: *managed*, *user*, *shared project*\n  (`.claude\u002Fsettings.json`), or *project local* (`.claude\u002Fsettings.local.json`);\n  for *managed*, also the **delivery**: admin console (server-managed), MDM, or\n  `managed-settings.json` file\n- **starting point**: an existing file (ask the user to paste it; for a local\n  file you may read it yourself if the user prefers), or **from scratch**\n- **environment**: OS and runtime, including WSL, container or CI constraints\n- **who uses it**: one person, a team, CI, or cloud sessions\n\n**Round 2**, the key questions; from scratch they are the whole design, on an\nexisting file ask only those the file leaves open:\n\n- **use**: everyday development, infrastructure and production access, CI and\n  automation, exploration\n- **posture**: *strict* (deny by default, sandbox without escape), *balanced*\n  (sandbox with escape, prompts on risky actions), *permissive* (few prompts)\n- **permission mode**: recommend a currently documented mode, state its prompt\n  behavior and risk, and ask for confirmation; the Manual label uses the\n  `default` config value\n- **must never happen** (multi-select): secrets read (SSH keys, cloud\n  credentials, `.env`, kubeconfig), commands outside the sandbox, unapproved\n  plugins or marketplaces, bypass permissions mode\n\n**Round 3**, only for the areas the user wants configured:\n\n- plugins and marketplaces: which to enforce, which to allow, auto-update\n- model: default and fallback\n- commit and PR attribution, language, UI\n\nDone when you know the settings source, the starting point, the posture, and a\ngoal for every area the file touches or the answers call for. An area the user\ndeclines to decide keeps its current value, or its default from scratch.\n\n## 2. Sources\n\nRead on every run: keys change often and memory goes stale. Download each\ndocs page as raw Markdown and read a key's type, enum, default and scope from\nits own `` ### `\u003Ckey>` `` section (nested keys use the dotted path):\n\n```bash\ncurl -sfL https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002F\u003Cpage>.md -o \u003Ctmp>\u002F\u003Cpage>.md\ngrep -n -F '### `\u003Ckey>`' \u003Ctmp>\u002F\u003Cpage>.md\n```\n\nA summarizing fetch (`WebFetch`) reads only the first 100 KB of the 400 KB\nreference and returned wrong types, enums and defaults: use it to find pages,\nnever as the source of a key's facts.\n\n- `https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fsettings`: scopes and precedence\n- `https:\u002F\u002Fcode.claude.com\u002Fdocs\u002Fen\u002Fsettings-reference`: every key with its scope\n  (`Any file`, `Managed`), default and an example\n- the schema `https:\u002F\u002Fjson.schemastore.org\u002Fclaude-code-settings.json`\n- for the areas touched, the pages the reference links: `permissions`,\n  `sandboxing`, `managed-settings`, `server-managed-settings`, `plugins\u002Forg`,\n  `plugins\u002Floading`, `plugins\u002Fhost-marketplace`, `plugin-marketplaces`\n- **secondary source** for best practice, a third-party copy that may lag:\n\n  ```bash\n  gh api repos\u002Fshanraisshan\u002Fclaude-code-best-practice\u002Fcontents\u002Fbest-practice\u002Fclaude-settings.md --jq .content | base64 -d\n  gh api 'repos\u002Fshanraisshan\u002Fclaude-code-best-practice\u002Fcommits?path=best-practice\u002Fclaude-settings.md&per_page=1' --jq '.[0].commit.committer.date'\n  ```\n\n  Where it disagrees with the official docs, the docs win and the disagreement\n  is reported; the known ones are under *Secondary-source errata* in\n  [`references\u002Fbest-practice.md`](references\u002Fbest-practice.md).\n\nDone when every page covering a key in the file, or an area the answers call\nfor, has been read, and you hold the secondary source's last commit date.\n\n## 3. Validation\n\nFrom scratch there is no file yet: skip to step 4, and run this step on the\ndraft before delivering it.\n\n1. Run [`scripts\u002Fcheck.py`](scripts\u002Fcheck.py) on the JSON saved to a temp file,\n   with the reference downloaded in step 2:\n\n   ```bash\n   uv run \u003Cskill dir>\u002Fscripts\u002Fcheck.py \u003Cfile> --reference \u003Ctmp>\u002Fsettings-reference.md\n   ```\n\n   `uv run` installs `jsonschema` from the script's header; without `uv`, use\n   `python3` and, if `jsonschema` is missing, install it as the script says.\n   It reports `SYNTAX`, `DUP`, `SCHEMA` and `UNKNOWN`, the last tagged\n   `(documented)` or `(undocumented)`; weigh each `UNKNOWN` as\n   [`references\u002Fbest-practice.md`](references\u002Fbest-practice.md) says. Exit 2\n   means the check did not run; when the schema did not load, fetch its URL\n   with `curl` into a file and rerun with `--schema \u003Cfile>`.\n\n   A check that never ran is reported as such: the verdict says the schema\n   was not checked, never that the file is clean.\n2. Check every key against the reference:\n   - **scope**: confirm that the chosen settings source supports the key; flag\n     global-config keys because they belong in `~\u002F.claude.json`\n   - **values**: types, enums and limits\n   - **default**: on an existing file, a value equal to the documented default\n     is redundant; report it as informational\n   - **deprecated or renamed keys**\n\nDone when every key has been checked against reference and schema, and\n`check.py` ran and is clean or every line it reports is explained.\n\n## 4. Best practice\n\nApply [`references\u002Fbest-practice.md`](references\u002Fbest-practice.md) and the\nsecondary source to every area touched, measured against the goals from step 1.\nA best practice that contradicts a stated goal becomes a warning with its risk,\nnot an imposed fix.\n\nThen look for the **gaps**: keys absent from the file that serve a stated goal\n(a `deny` rule, a sandbox exception, a hook, an `env` value, a model default).\nWalk the settings reference area by area against the goals; propose each gap\nwith what it buys, what it costs, and a recommendation. Where two valid\nconfigurations trade off against a goal, ask the user rather than pick.\n\nDone when every area touched has a judgement (compliant, or the proposed change\nwith its reason) and every goal has either a key serving it or a stated reason\nnone is needed.\n\n## 5. Delivery\n\n- **Verdict**, in three groups: errors, warnings, best practice. Per item: the\n  key, the problem, the source (docs page or schema), and whether it is a\n  verified fact or an inference.\n- **The complete corrected JSON**, never a fragment: the user pastes it whole.\n  From scratch, write only keys\n  that serve an answer: a key restating its default adds nothing to maintain.\n- Below the JSON, what you changed and what you left alone on purpose.\n- The secondary source's last commit date, and each disagreement with the\n  official docs.\n- *Managed*: the JSON for its delivery, and which other managed sources it\n  overrides (*Managed settings* in\n  [`references\u002Fbest-practice.md`](references\u002Fbest-practice.md)). Once the user confirms it is deployed, verify each changed key\n  yourself with the probes in\n  [`references\u002Fverify-managed.md`](references\u002Fverify-managed.md), and hand the\n  user only the checks the CLI cannot make. *User*, *shared project*, or\n  *project local*: write the file only after the user's yes, and read its\n  current contents first.\n\nDone when `check.py` is clean on the delivered JSON, or each remaining line is\nan accepted trade-off named in the verdict; every verdict item names its\nsource; and, for managed settings the user deployed, every changed key is\nverified or listed as a manual check.\n",{"name":5,"description":7},"main","e63612d78f9099c1970584ea3faef109f42d20bb",".agents\u002Fplugins\u002Fpackages\u002Fsettings-validator\u002Fskills\u002Fsettings-validator",0,"https:\u002F\u002Fgithub.com\u002Ffilippolmt\u002Fskills","https:\u002F\u002Fgithub.com\u002Ffilippolmt","2026-11-14 22:46:00",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add filippolmt\u002Fskills --skill settings-validator",{"tool":38,"command":39},"bunx","bunx skills add filippolmt\u002Fskills --skill settings-validator",{"tool":41,"command":42},"pnpm","pnpm dlx skills add filippolmt\u002Fskills --skill settings-validator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ffilippolmt\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fplugins\u002Fpackages\u002Fsettings-validator\u002Fskills\u002Fsettings-validator\u002FSKILL.md",true,[46,50,56,60,66,70],{"path":47,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":16},"LICENSE","许可证",1083,{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fbest-practice.md","REFERENCE","参考文档",8769,"https:\u002F\u002Fgithub.com\u002Ffilippolmt\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fplugins\u002Fpackages\u002Fsettings-validator\u002Fskills\u002Fsettings-validator\u002Freferences\u002Fbest-practice.md",{"path":57,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fverify-managed.md",2121,"https:\u002F\u002Fgithub.com\u002Ffilippolmt\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fplugins\u002Fpackages\u002Fsettings-validator\u002Fskills\u002Fsettings-validator\u002Freferences\u002Fverify-managed.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fcheck_test.py","SCRIPT","脚本",1570,"https:\u002F\u002Fgithub.com\u002Ffilippolmt\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fplugins\u002Fpackages\u002Fsettings-validator\u002Fskills\u002Fsettings-validator\u002Fscripts\u002Fcheck_test.py",{"path":67,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fcheck.py",5144,"https:\u002F\u002Fgithub.com\u002Ffilippolmt\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fplugins\u002Fpackages\u002Fsettings-validator\u002Fskills\u002Fsettings-validator\u002Fscripts\u002Fcheck.py",{"path":71,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":72,"sourceHtmlUrl":73},"SOURCE.md",207,"https:\u002F\u002Fgithub.com\u002Ffilippolmt\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fplugins\u002Fpackages\u002Fsettings-validator\u002Fskills\u002Fsettings-validator\u002FSOURCE.md",[75,83,92,100,108,116],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":79,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":20},"01M781ZJN9KDK0YY8EAQ8WXPRQ","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Ffilippolmt\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-for-agents\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ffilippolmt\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwriting-for-agents\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":87,"licenseFileUrl":88,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":20},"01M781ZDZ8CQ30GRY5XNT1RF91","wrangler","Run or troubleshoot Wrangler CLI commands in projects that have a wrangler.jsonc, wrangler.json, or wrangler.toml file, including local development, Previews, deployment, and resource management. For new projects and projects without a Wrangler configuration file, use the cf CLI instead.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Ffilippolmt\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwrangler\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ffilippolmt\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwrangler\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":87,"licenseFileUrl":96,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":20},"01M781ZA1MB7E7T1R1TE0BTTJS","workers-profiling","Profile or debug CPU usage and memory allocation in deployed Cloudflare Workers and Durable Objects. Then use this information to optimize your code.","https:\u002F\u002Fgithub.com\u002Ffilippolmt\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fworkers-profiling\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ffilippolmt\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fworkers-profiling\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":87,"licenseFileUrl":104,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":20},"01M781Z52Q7PBMDA2YBC3SCTYM","workers-development","Run, inspect, and debug Cloudflare Workers during local development with cf dev, wrangler dev, or the Cloudflare Vite plugin, using Local Explorer to read and seed binding data and query local traces and logs. Also routes production debugging to Workers observability. Use for debugging requests whether or not the project uses Wrangler.","https:\u002F\u002Fgithub.com\u002Ffilippolmt\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fworkers-development\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ffilippolmt\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fworkers-development\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":87,"licenseFileUrl":112,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":20},"01M781Z193MG7SHF4DSD1WK583","workers-best-practices","Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.","https:\u002F\u002Fgithub.com\u002Ffilippolmt\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fworkers-best-practices\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ffilippolmt\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fworkers-best-practices\u002FSKILL.md",[],[],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":120,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":20},"01M781YT0JB3GVA1HTFZ9QJHM7","wordpress-pro","Develops custom WordPress themes and plugins, creates and registers Gutenberg blocks and block patterns, configures WooCommerce stores, implements WordPress REST API endpoints, applies security hardening (nonces, sanitization, escaping, capability checks), and optimizes performance through caching and query tuning. Use when building WordPress themes, writing plugins, customizing Gutenberg blocks, extending WooCommerce, working with ACF, using the WordPress REST API, applying hooks and filters, or improving WordPress performance and security.","https:\u002F\u002Fgithub.com\u002Ffilippolmt\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwordpress-pro\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Ffilippolmt\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fwordpress-pro\u002FSKILL.md",[],[]]