[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M793RCHYYSPYVZM53MJ2ZP6Y":3,"skill-same:01M793RCHYYSPYVZM53MJ2ZP6Y":59},{"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":5,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M793RCHYYSPYVZM53MJ2ZP6Y","cli-creator",null,"Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read\u002Fwrite commands, return stable JSON, manage auth, and pair with a companion skill.","lovits\u002Fskills-manager-backup","lovits","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F124361371?v=4","01M793DZJFDH6R8M75RTA2FHYQ","Q1anye","01M793DZKGAG18E7G64YC92PS1",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flovits\u002Fskills-manager-backup\u002Fblob\u002Fmain\u002Fcli-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Flovits\u002Fskills-manager-backup\u002Fblob\u002Fmain\u002Fcli-creator\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: cli-creator\ndescription: Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read\u002Fwrite commands, return stable JSON, manage auth, and pair with a companion skill.\n---\n\n# CLI Creator\n\nCreate a real CLI that future Codex threads can run by command name from any working directory.\n\nThis skill is for durable tools, not one-off scripts. If a short script in the current repo solves the task, write the script there instead.\n\n## Start\n\nName the target tool, its source, and the first real jobs it should do:\n\n- Source: API docs, OpenAPI JSON, SDK docs, curl examples, browser app, existing internal script, article, or working shell history.\n- Jobs: literal reads\u002Fwrites such as `list drafts`, `download failed job logs`, `search messages`, `upload media`, `read queue schedule`.\n- Install name: a short binary name such as `ci-logs`, `slack-cli`, `sentry-cli`, or `buildkite-logs`.\n\nPrefer a new folder under `~\u002Fcode\u002Fclis\u002F\u003Ctool-name>` when the user wants a personal tool and has not named a repo.\n\nBefore scaffolding, check whether the proposed command already exists:\n\n```bash\ncommand -v \u003Ctool-name> || true\n```\n\nIf it exists, choose a clearer install name or ask the user.\n\n## Choose the Runtime\n\nBefore choosing, inspect the user's machine and source material:\n\n```bash\ncommand -v cargo rustc node pnpm npm python3 uv || true\n```\n\nThen choose the least surprising toolchain:\n\n- Default to **Rust** for a durable CLI Codex should run from any repo: one fast binary, strong argument parsing, good JSON handling, easy copy\u002Finstall into `~\u002F.local\u002Fbin`.\n- Use **TypeScript\u002FNode** when the official SDK, auth helper, browser automation library, or existing repo tooling is the reason the CLI can be better.\n- Use **Python** when the source is data science, local file transforms, notebooks, SQLite\u002FCSV\u002FJSON analysis, or Python-heavy admin tooling that can still be installed as a durable command.\n\nDo not pick a language that adds setup friction unless it materially improves the CLI. If the best language is not installed, either install the missing toolchain with the user's approval or choose the next-best installed option.\n\nState the choice in one sentence before scaffolding, including the reason and the installed toolchain you found.\n\n## Command Contract\n\nSketch the command surface in chat before coding. Include the binary name, discovery commands, resolve or ID-lookup commands, read commands, write commands, raw escape hatch, auth\u002Fconfig choice, and PATH\u002Finstall command.\n\nWhen designing the command surface, read [references\u002Fagent-cli-patterns.md](references\u002Fagent-cli-patterns.md) for the expected composable CLI shape.\n\nBuild toward this surface:\n\n- `tool-name --help` shows every major capability.\n- `tool-name --json doctor` verifies config, auth, version, endpoint reachability, and missing setup.\n- `tool-name init ...` stores local config when env-only auth is painful.\n- Discovery commands find accounts, projects, workspaces, teams, queues, channels, repos, dashboards, or other top-level containers.\n- Resolve commands turn names, URLs, slugs, permalinks, customer input, or build links into stable IDs so future commands do not repeat broad searches.\n- Read commands fetch exact objects and list\u002Fsearch collections. Paginated lists support a bounded `--limit`, cursor, offset, or clearly documented default.\n- Write commands do one named action each: create, update, delete, upload, schedule, retry, comment, draft. They accept the narrowest stable resource ID, support `--dry-run`, `draft`, or `preview` first when the service allows it, and do not hide writes inside broad commands such as `fix`, `debug`, or `auto`.\n- `--json` returns stable machine-readable output.\n- A raw escape hatch exists: `request`, `tool-call`, `api`, or the nearest honest name.\n\nDo not expose only a generic `request` command. Give Codex high-level verbs for the repeated jobs.\n\nDocument the JSON policy in the CLI README or equivalent: API pass-through versus CLI envelope, success shape, error shape, and one example for each command family. Under `--json`, errors must be machine-readable and must not contain credentials.\n\n## Auth and Config\n\nSupport the boring paths first, in this precedence order:\n\n1. Environment variable using the service's standard name, such as `GITHUB_TOKEN`.\n2. User config under `~\u002F.\u003Ctool-name>\u002Fconfig.toml` or another simple documented path.\n3. `--api-key` or a tool-specific token flag only for explicit one-off tests. Prefer env\u002Fconfig for normal use because flags can leak into shell history or process listings.\n\nNever print full tokens. `doctor --json` should say whether a token is available, the auth source category (`flag`, `env`, `config`, provider default, or missing), and what setup step is missing.\n\nIf the CLI can run without network or auth, make that explicit in `doctor --json`: report fixture\u002Foffline mode, whether fixture data was found, and whether auth is not required for that mode.\n\nFor internal web apps sourced from DevTools curls, create sanitized endpoint notes before implementing: resource name, method\u002Fpath, required headers, auth mechanism, CSRF behavior, request body, response ID fields, pagination, errors, and one redacted sample response. Never commit copied cookies, bearer tokens, customer secrets, or full production payloads.\n\nUse screenshots to infer workflow, UI vocabulary, fields, and confirmation points. Do not treat screenshots as API evidence unless they are paired with a network request, export, docs page, or fixture.\n\n## Build Workflow\n\n1. Read the source just enough to inventory resources, auth, pagination, IDs, media\u002Ffile flows, rate limits, and dangerous write actions. If the docs expose OpenAPI, download or inspect it before naming commands.\n2. Sketch the command list in chat. Keep names short and shell-friendly.\n3. Scaffold the CLI with a README or equivalent repo-facing instructions.\n4. Implement `doctor`, discovery, resolve, read commands, one narrow draft or dry-run write path if requested, and the raw escape hatch.\n5. Install the CLI on PATH so `tool-name ...` works outside the source folder.\n6. Smoke test from another repo or `\u002Ftmp`, not only with `cargo run` or package-manager wrappers. Run `command -v \u003Ctool-name>`, `\u003Ctool-name> --help`, and `\u003Ctool-name> --json doctor`.\n7. Run format, typecheck\u002Fbuild, unit tests for request builders, pagination\u002Frequest-body builders, no-auth `doctor`, help output, and at least one fixture, dry-run, or live read-only API call.\n\nIf a live write is needed for confidence, ask first and make it reversible or draft-only.\n\nWhen the source is an existing script or shell history, split the working invocation into real phases: setup, discovery, download\u002Fexport, transform\u002Findex, draft, upload, poll, live write. Preserve the flags, paths, and environment variables the user already relies on, then wrap the repeatable phases with stable IDs, bounded JSON, and file outputs.\n\nFor raw escape hatches, support read-only calls first. Do not run raw non-GET\u002FHEAD requests against a live service unless the user asked for that specific write.\n\nFor media, artifact, or presigned upload flows, test each phase separately: create upload, transfer bytes, poll\u002Fread processing status, then attach or reference the resulting ID.\n\nFor fixture-backed prototypes, keep fixtures in a predictable project path and make the CLI locate them after installation. Smoke-test from `\u002Ftmp` to catch binaries that only work inside the source folder.\n\nFor log-oriented CLIs, keep deterministic snippet extraction separate from model interpretation. Prefer a command that emits filenames, line numbers or byte ranges, matched rules, and short excerpts.\n\n## Rust Defaults\n\nWhen building in Rust, use established crates instead of custom parsers:\n\n- `clap` for commands and help\n- `reqwest` for HTTP\n- `serde` \u002F `serde_json` for payloads\n- `toml` for small config files\n- `anyhow` for CLI-shaped error context\n\nAdd a `Makefile` target such as `make install-local` that builds release and installs the binary into `~\u002F.local\u002Fbin`.\n\n## TypeScript\u002FNode Defaults\n\nWhen building in TypeScript\u002FNode, keep the CLI installable as a normal command:\n\n- `commander` or `cac` for commands and help\n- native `fetch`, the official SDK, or the user's existing HTTP helper for API calls\n- `zod` only where external payload validation prevents real breakage\n- `package.json` `bin` entry for the installed command\n- `tsup`, `tsx`, or `tsc` using the repo's existing convention\n\nAdd an install path such as `pnpm install`, `pnpm build`, and `pnpm link --global`, or a `Makefile` target that installs a small wrapper into `~\u002F.local\u002Fbin`.\n\n## Python Defaults\n\nWhen building in Python, prefer boring standard-library pieces unless the workflow needs more:\n\n- `argparse` for commands and help, or `typer` when subcommands would otherwise get messy\n- `urllib.request` \u002F `urllib.parse`, `requests`, or `httpx` for HTTP, matching what is already installed or already used nearby\n- `json`, `csv`, `sqlite3`, `pathlib`, and `subprocess` for local files, exports, databases, and existing scripts\n- `pyproject.toml` console script or a small executable wrapper for the installed command\n- `uv` or a virtualenv only when dependencies are actually needed\n\nAdd a `Makefile` target such as `make install-local` that installs the command on PATH and document whether it depends on `uv`, a virtualenv, or only system Python.\n\n## Companion Skill\n\nAfter the CLI works, create or update a small skill for it. Use `$skill-creator` when it is available. Use `$CODEX_HOME\u002Fskills\u002F\u003Ctool-name>\u002FSKILL.md` for a personal companion skill unless the user names a repo-local `.codex\u002Fskills\u002F...` path or another skill repo.\n\nWrite the companion skill in the order a future Codex thread should use the CLI, not as a tour of every feature. Explain:\n\n- How to verify the installed command exists.\n- Which command to run first.\n- How auth is configured.\n- Which discovery command finds the common ID.\n- The safe read path.\n- The intended draft\u002Fwrite path.\n- The raw escape hatch.\n- What not to do without explicit user approval.\n- Three copy-pasteable command examples.\n\nKeep API reference details in the CLI docs or a skill reference file. Keep the skill focused on ordering, safety, and examples future Codex threads should actually run.\n","# CLI Creator\n\nCreate a real CLI that future Codex threads can run by command name from any working directory.\n\nThis skill is for durable tools, not one-off scripts. If a short script in the current repo solves the task, write the script there instead.\n\n## Start\n\nName the target tool, its source, and the first real jobs it should do:\n\n- Source: API docs, OpenAPI JSON, SDK docs, curl examples, browser app, existing internal script, article, or working shell history.\n- Jobs: literal reads\u002Fwrites such as `list drafts`, `download failed job logs`, `search messages`, `upload media`, `read queue schedule`.\n- Install name: a short binary name such as `ci-logs`, `slack-cli`, `sentry-cli`, or `buildkite-logs`.\n\nPrefer a new folder under `~\u002Fcode\u002Fclis\u002F\u003Ctool-name>` when the user wants a personal tool and has not named a repo.\n\nBefore scaffolding, check whether the proposed command already exists:\n\n```bash\ncommand -v \u003Ctool-name> || true\n```\n\nIf it exists, choose a clearer install name or ask the user.\n\n## Choose the Runtime\n\nBefore choosing, inspect the user's machine and source material:\n\n```bash\ncommand -v cargo rustc node pnpm npm python3 uv || true\n```\n\nThen choose the least surprising toolchain:\n\n- Default to **Rust** for a durable CLI Codex should run from any repo: one fast binary, strong argument parsing, good JSON handling, easy copy\u002Finstall into `~\u002F.local\u002Fbin`.\n- Use **TypeScript\u002FNode** when the official SDK, auth helper, browser automation library, or existing repo tooling is the reason the CLI can be better.\n- Use **Python** when the source is data science, local file transforms, notebooks, SQLite\u002FCSV\u002FJSON analysis, or Python-heavy admin tooling that can still be installed as a durable command.\n\nDo not pick a language that adds setup friction unless it materially improves the CLI. If the best language is not installed, either install the missing toolchain with the user's approval or choose the next-best installed option.\n\nState the choice in one sentence before scaffolding, including the reason and the installed toolchain you found.\n\n## Command Contract\n\nSketch the command surface in chat before coding. Include the binary name, discovery commands, resolve or ID-lookup commands, read commands, write commands, raw escape hatch, auth\u002Fconfig choice, and PATH\u002Finstall command.\n\nWhen designing the command surface, read [references\u002Fagent-cli-patterns.md](references\u002Fagent-cli-patterns.md) for the expected composable CLI shape.\n\nBuild toward this surface:\n\n- `tool-name --help` shows every major capability.\n- `tool-name --json doctor` verifies config, auth, version, endpoint reachability, and missing setup.\n- `tool-name init ...` stores local config when env-only auth is painful.\n- Discovery commands find accounts, projects, workspaces, teams, queues, channels, repos, dashboards, or other top-level containers.\n- Resolve commands turn names, URLs, slugs, permalinks, customer input, or build links into stable IDs so future commands do not repeat broad searches.\n- Read commands fetch exact objects and list\u002Fsearch collections. Paginated lists support a bounded `--limit`, cursor, offset, or clearly documented default.\n- Write commands do one named action each: create, update, delete, upload, schedule, retry, comment, draft. They accept the narrowest stable resource ID, support `--dry-run`, `draft`, or `preview` first when the service allows it, and do not hide writes inside broad commands such as `fix`, `debug`, or `auto`.\n- `--json` returns stable machine-readable output.\n- A raw escape hatch exists: `request`, `tool-call`, `api`, or the nearest honest name.\n\nDo not expose only a generic `request` command. Give Codex high-level verbs for the repeated jobs.\n\nDocument the JSON policy in the CLI README or equivalent: API pass-through versus CLI envelope, success shape, error shape, and one example for each command family. Under `--json`, errors must be machine-readable and must not contain credentials.\n\n## Auth and Config\n\nSupport the boring paths first, in this precedence order:\n\n1. Environment variable using the service's standard name, such as `GITHUB_TOKEN`.\n2. User config under `~\u002F.\u003Ctool-name>\u002Fconfig.toml` or another simple documented path.\n3. `--api-key` or a tool-specific token flag only for explicit one-off tests. Prefer env\u002Fconfig for normal use because flags can leak into shell history or process listings.\n\nNever print full tokens. `doctor --json` should say whether a token is available, the auth source category (`flag`, `env`, `config`, provider default, or missing), and what setup step is missing.\n\nIf the CLI can run without network or auth, make that explicit in `doctor --json`: report fixture\u002Foffline mode, whether fixture data was found, and whether auth is not required for that mode.\n\nFor internal web apps sourced from DevTools curls, create sanitized endpoint notes before implementing: resource name, method\u002Fpath, required headers, auth mechanism, CSRF behavior, request body, response ID fields, pagination, errors, and one redacted sample response. Never commit copied cookies, bearer tokens, customer secrets, or full production payloads.\n\nUse screenshots to infer workflow, UI vocabulary, fields, and confirmation points. Do not treat screenshots as API evidence unless they are paired with a network request, export, docs page, or fixture.\n\n## Build Workflow\n\n1. Read the source just enough to inventory resources, auth, pagination, IDs, media\u002Ffile flows, rate limits, and dangerous write actions. If the docs expose OpenAPI, download or inspect it before naming commands.\n2. Sketch the command list in chat. Keep names short and shell-friendly.\n3. Scaffold the CLI with a README or equivalent repo-facing instructions.\n4. Implement `doctor`, discovery, resolve, read commands, one narrow draft or dry-run write path if requested, and the raw escape hatch.\n5. Install the CLI on PATH so `tool-name ...` works outside the source folder.\n6. Smoke test from another repo or `\u002Ftmp`, not only with `cargo run` or package-manager wrappers. Run `command -v \u003Ctool-name>`, `\u003Ctool-name> --help`, and `\u003Ctool-name> --json doctor`.\n7. Run format, typecheck\u002Fbuild, unit tests for request builders, pagination\u002Frequest-body builders, no-auth `doctor`, help output, and at least one fixture, dry-run, or live read-only API call.\n\nIf a live write is needed for confidence, ask first and make it reversible or draft-only.\n\nWhen the source is an existing script or shell history, split the working invocation into real phases: setup, discovery, download\u002Fexport, transform\u002Findex, draft, upload, poll, live write. Preserve the flags, paths, and environment variables the user already relies on, then wrap the repeatable phases with stable IDs, bounded JSON, and file outputs.\n\nFor raw escape hatches, support read-only calls first. Do not run raw non-GET\u002FHEAD requests against a live service unless the user asked for that specific write.\n\nFor media, artifact, or presigned upload flows, test each phase separately: create upload, transfer bytes, poll\u002Fread processing status, then attach or reference the resulting ID.\n\nFor fixture-backed prototypes, keep fixtures in a predictable project path and make the CLI locate them after installation. Smoke-test from `\u002Ftmp` to catch binaries that only work inside the source folder.\n\nFor log-oriented CLIs, keep deterministic snippet extraction separate from model interpretation. Prefer a command that emits filenames, line numbers or byte ranges, matched rules, and short excerpts.\n\n## Rust Defaults\n\nWhen building in Rust, use established crates instead of custom parsers:\n\n- `clap` for commands and help\n- `reqwest` for HTTP\n- `serde` \u002F `serde_json` for payloads\n- `toml` for small config files\n- `anyhow` for CLI-shaped error context\n\nAdd a `Makefile` target such as `make install-local` that builds release and installs the binary into `~\u002F.local\u002Fbin`.\n\n## TypeScript\u002FNode Defaults\n\nWhen building in TypeScript\u002FNode, keep the CLI installable as a normal command:\n\n- `commander` or `cac` for commands and help\n- native `fetch`, the official SDK, or the user's existing HTTP helper for API calls\n- `zod` only where external payload validation prevents real breakage\n- `package.json` `bin` entry for the installed command\n- `tsup`, `tsx`, or `tsc` using the repo's existing convention\n\nAdd an install path such as `pnpm install`, `pnpm build`, and `pnpm link --global`, or a `Makefile` target that installs a small wrapper into `~\u002F.local\u002Fbin`.\n\n## Python Defaults\n\nWhen building in Python, prefer boring standard-library pieces unless the workflow needs more:\n\n- `argparse` for commands and help, or `typer` when subcommands would otherwise get messy\n- `urllib.request` \u002F `urllib.parse`, `requests`, or `httpx` for HTTP, matching what is already installed or already used nearby\n- `json`, `csv`, `sqlite3`, `pathlib`, and `subprocess` for local files, exports, databases, and existing scripts\n- `pyproject.toml` console script or a small executable wrapper for the installed command\n- `uv` or a virtualenv only when dependencies are actually needed\n\nAdd a `Makefile` target such as `make install-local` that installs the command on PATH and document whether it depends on `uv`, a virtualenv, or only system Python.\n\n## Companion Skill\n\nAfter the CLI works, create or update a small skill for it. Use `$skill-creator` when it is available. Use `$CODEX_HOME\u002Fskills\u002F\u003Ctool-name>\u002FSKILL.md` for a personal companion skill unless the user names a repo-local `.codex\u002Fskills\u002F...` path or another skill repo.\n\nWrite the companion skill in the order a future Codex thread should use the CLI, not as a tour of every feature. Explain:\n\n- How to verify the installed command exists.\n- Which command to run first.\n- How auth is configured.\n- Which discovery command finds the common ID.\n- The safe read path.\n- The intended draft\u002Fwrite path.\n- The raw escape hatch.\n- What not to do without explicit user approval.\n- Three copy-pasteable command examples.\n\nKeep API reference details in the CLI docs or a skill reference file. Keep the skill focused on ordering, safety, and examples future Codex threads should actually run.\n",{"name":5,"description":7},"main","4002a5c44b4116647123f4eb7b559118f5b07451","https:\u002F\u002Fgithub.com\u002Flovits\u002Fskills-manager-backup","https:\u002F\u002Fgithub.com\u002Flovits","2026-11-15 00:39:40",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add lovits\u002Fskills-manager-backup --skill cli-creator",{"tool":36,"command":37},"bunx","bunx skills add lovits\u002Fskills-manager-backup --skill cli-creator",{"tool":39,"command":40},"pnpm","pnpm dlx skills add lovits\u002Fskills-manager-backup --skill cli-creator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flovits\u002Fskills-manager-backup\u002Fblob\u002Fmain\u002Fcli-creator\u002FSKILL.md",true,[44,50,55],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"agents\u002Fopenai.yaml","REFERENCE","参考文档",280,"https:\u002F\u002Fgithub.com\u002Flovits\u002Fskills-manager-backup\u002Fblob\u002Fmain\u002Fcli-creator\u002Fagents\u002Fopenai.yaml",{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":16},"LICENSE.txt","LICENSE","许可证",10776,{"path":56,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fagent-cli-patterns.md",5244,"https:\u002F\u002Fgithub.com\u002Flovits\u002Fskills-manager-backup\u002Fblob\u002Fmain\u002Fcli-creator\u002Freferences\u002Fagent-cli-patterns.md",[60,68,76,84,92,100],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":64,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":20},"01M795K6G8GP7ABAEFKHD0HQA9","xlsx","Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.","https:\u002F\u002Fgithub.com\u002Flovits\u002Fskills-manager-backup\u002Fblob\u002Fmain\u002Fxlsx\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Flovits\u002Fskills-manager-backup\u002Fblob\u002Fmain\u002Fxlsx\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":72,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":20},"01M795EHJGAN10CBC8AC3VCEBD","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Flovits\u002Fskills-manager-backup\u002Fblob\u002Fmain\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Flovits\u002Fskills-manager-backup\u002Fblob\u002Fmain\u002Fwebapp-testing\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":80,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":20},"01M795EBZRZTS22VE1SVQ1J8FX","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","https:\u002F\u002Fgithub.com\u002Flovits\u002Fskills-manager-backup\u002Fblob\u002Fmain\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Flovits\u002Fskills-manager-backup\u002Fblob\u002Fmain\u002Fweb-artifacts-builder\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":88,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":20},"01M79533Y82G6DG7HTQP9VDMJ0","theme-factory","Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors\u002Ffonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.","https:\u002F\u002Fgithub.com\u002Flovits\u002Fskills-manager-backup\u002Fblob\u002Fmain\u002Ftheme-factory\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Flovits\u002Fskills-manager-backup\u002Fblob\u002Fmain\u002Ftheme-factory\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":96,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":20},"01M7952HE8Z6MVDPYYQPP4ZE6C","stop-that-shit","Complete requested work while preventing speculative defenses and scope creep. Use when considering extra hardening, reviewing possible overengineering, resolving repeated verification loops, following explicit task boundaries, or when the user invokes Stop That Shit. Ordinary use of validation, retries, or dependencies alone is not a trigger.","MIT","https:\u002F\u002Fgithub.com\u002Flovits\u002Fskills-manager-backup\u002Fblob\u002Fmain\u002Fstop-that-shit\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":15,"licenseFileUrl":104,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":20},"01M79523NWKWJM5JBXY02B3DHE","slack-gif-creator","Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like \"make me a GIF of X doing Y for Slack.\"","https:\u002F\u002Fgithub.com\u002Flovits\u002Fskills-manager-backup\u002Fblob\u002Fmain\u002Fslack-gif-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Flovits\u002Fskills-manager-backup\u002Fblob\u002Fmain\u002Fslack-gif-creator\u002FSKILL.md",[],[]]