SOC 직업 분류 기준
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/s-kostyaev/.emacs.d --skill textweb명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
SKILL.md 표시 중
| name | textweb |
| description | Use this skill to browse the web textually. |
You have access to a text-based web browser via the textweb_* tools. Pages are rendered as structured character grids instead of screenshots.
textweb_navigate(url) — Opens a page and returns a text gridtextweb_click(ref) — Clicks element [ref]textweb_type(ref, text) — Types into input [ref]textweb_select(ref, value) — Selects dropdown optiontextweb_scroll(direction) — Scrolls up/down/toptextweb_snapshot() — Re-renders current pagetextweb_press(key) — Presses a key (Enter, Tab, etc.)textweb_upload(ref, path) — Uploads a file to inputInteractive elements have reference numbers in brackets:
| Element | Appears as | Action |
|---|---|---|
| Link | [3]Click me | click(3) |
| Button | [5 Submit] | click(5) |
| Text input | [7:placeholder___] | type(7, "text") |
| Checkbox | [9:X] Label / [9: ] Label | click(9) to toggle |
| Radio | [11:●] Option / [11:○] Option | click(11) |
| Dropdown | [13:▼ Selected] | select(13, "value") |
| File input | [15:📎 Choose file] | upload(15, "/path/to/file") |
| Heading | ═══ TITLE ═══ | (not interactive) |
snapshot() if you need to re-read the page after waiting for dynamic contentReview code changes with a focused multi-agent workflow. Use when auditing a diff, branch, pull request, patch, commit range, or local worktree for bugs, regressions, missing tests, security issues, API breakage, maintainability risks, or review readiness.
Create or update Ellama Agent Skills. Use when designing new skills, porting skills from other agent systems, improving SKILL.md instructions, adding bundled resources, validating metadata, or adapting skills for small/local models.
Build, audit, or improve agentic coding/research systems and their harnesses. Use when designing agent workflows, small-model scaffolds, tool schemas, progressive-disclosure context, repository knowledge maps, guardrails, validation loops, subagents, evals, recovery mechanisms, or autonomous-agent safety policies.