Gingiris Ugc Matrix
Gingiris-1031/Competitor-analysis-tool
🇺🇸 UGC Matrix Growth Playbook — Scale user-generated content with AI + real creators.
Create, manage, or talk to an openclone "clone" — a named AI persona with one or more categories (vc, tech, founder, expert, influencer, politician, celebrity) and attached knowledge.
$ npx skills add team-attention/openclone --skill openclone -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install team-attention/openclone openclone --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "openclone" agent skill from https://github.com/team-attention/openclone/tree/main into .claude/skills/openclone/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openclone", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add team-attention/openclone --skill openclone -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install team-attention/openclone openclone --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "openclone" agent skill from https://github.com/team-attention/openclone/tree/main into .agents/skills/openclone/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openclone", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add team-attention/openclone --skill openclone -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install team-attention/openclone openclone --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "openclone" agent skill from https://github.com/team-attention/openclone/tree/main into .cursor/skills/openclone/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openclone", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add team-attention/openclone --skill openclone -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install team-attention/openclone openclone --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "openclone" agent skill from https://github.com/team-attention/openclone/tree/main into .gemini/skills/openclone/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openclone", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install team-attention/openclone opencloneInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add team-attention/openclone --skill openclone -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "openclone" agent skill from https://github.com/team-attention/openclone/tree/main into .github/skills/openclone/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openclone", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add team-attention/openclone --skill openclone -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install team-attention/openclone openclone --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "openclone" agent skill from https://github.com/team-attention/openclone/tree/main into .opencode/skills/openclone/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openclone", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
opencloneCreate, manage, or talk to an openclone "clone" — a named AI persona with one or more categories (vc, tech, founder, expert, influencer, politician, celebrity) and attached knowledge.
Openclone is an agent skill from team-attention/openclone. Create, manage, or talk to an openclone "clone" — a named AI persona with one or more categories (vc, tech, founder, expert, influencer, politician, celebrity) and attached knowledge. Triggers on phrases like "create a clone", "make a persona", "talk as <name", "switch to <name", "feed knowledge to", "ingest url for <clone", "update <name with latest info", "<name 클론 최신 정보로 업데이트", "ask all VCs", "stop being <name", or any mention of /openclone. Renders the home panel with no args; name/number activates a clone…
Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4432 other files, including scripts, reference files and assets (for example `.github/ISSUE_TEMPLATE/bug_report.md`, `.github/ISSUE_TEMPLATE/clone_add.md` and `.github/ISSUE_TEMPLATE/clone_update.md`).
It sits in Marketing & SEO, covering Influencer and creator marketing. The repository describes itself as: 실제 인물을 학습한 AI 클론과 자유롭게 대화하세요. The licence is MIT.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 40d0586. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
BashReadWriteGlobWebFetchWebSearchFrom allowed-tools in the SKILL.md frontmatter.
Ships 1 file in scripts/ (TypeScript and Shell, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
bashFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
youtube.comyoutu.beFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Openclone loads about 2.6k tokens when it runs, and up to ~17k if it reads all its reference files. Until then it costs about 150 tokens; SKILL.md has 1,268 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check noted patterns worth knowing about, such as sudo or a known installer.
allowed-tools: Bash, Read, Write, Glob, WebFetch, WebSearchAutomated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from team-attention/openclone at commit 40d0586, republished under its MIT licence (© team-attention). 1,268 words, ~2,574 tokens.
.claude/skills/openclone/SKILL.md (or your agent's skills folder). This skill also uses 4428 other files; get the full folder from GitHub.openclone의 단일 진입점. 유저가 /openclone <args>로 직접 호출했거나 자연어("alice로 전환", "새 클론 만들어" 등)로 의도를 밝힌 경우 모두 이 스킬이 처리합니다.
${CLAUDE_SKILL_DIR}/clones/<name>/ (읽기 전용, 저장소와 함께 배포). persona.md는 항상 존재하고 knowledge/는 활성화 시점에 sparse-checkout으로 가져옵니다.~/.openclone/clones/<name>/ (쓰기 가능). 이름 충돌 시 유저 클론이 빌트인을 가립니다 (shadow).상태 파일 (모두 ~/.openclone/ 밑):
active-clone — 현재 활성 클론 이름 (없으면 = 활성 없음)room — 방 멤버 한 줄씩 (없거나 비어 있으면 = 방 없음)menu-context — 최근 홈 패널의 숫자 → 이름 JSON 매핑~/.openclone/room이 비어있지 않으면 room 모드 — 모든 멤버 페르소나와 라우팅 규칙 주입, 턴당 가장 적절한 한두 명이 응답.~/.openclone/active-clone이 존재하면 single-clone 모드 — 그 클론이 매 턴 응답./openclone <args>): $ARGUMENTS의 첫 토큰($1)을 읽어 아래 분기표대로 실행./openclone <sub> 형태의 명령을 보여주고 그 분기를 실행해서 유저가 무엇이 일어나는지 볼 수 있게 합니다.이 스킬을 쓰지 말아야 할 때: 이미 활성 클론·방 안이라면 다음 메시지는 UserPromptSubmit 훅이 자동 처리합니다 — 매 턴 스킬을 재호출하지 마세요.
$1 | 동작 |
|---|---|
| (비어 있음) | 아래 홈 패널 섹션 |
^[0-9]+$ (숫자) | 아래 숫자 선택 섹션 |
stop | 아래 stop 섹션 |
new | 아래 new 섹션 |
ingest | 아래 ingest 섹션 |
update | 아래 update 섹션 |
room | 아래 room 섹션 |
panel | 아래 panel 섹션 |
^[a-z0-9][a-z0-9-]*$ | 아래 use 섹션 (클론 이름으로 해석) |
| 그 외 | 한 줄로 "알 수 없는 서브명령" 안내 후 홈 패널 렌더 |
${CLAUDE_SKILL_DIR}/references/home-workflow.md 를 로드해 그대로 따르세요.
렌더가 끝나면 이 턴은 종료. 유저는 다음 메시지에서 번호/이름을 선택하거나 다른 서브명령을 호출합니다.
~/.openclone/menu-context 파일을 읽습니다. 없거나 JSON 파싱 실패면 "이 번호와 연결된 최근 홈 패널이 없어요. /openclone 로 홈을 다시 열어주세요." 안내 후 중단.items에서 n == $1인 엔트리를 찾습니다. 없으면 "그 번호는 현재 목록에 없어요." 안내 후 중단.name을 <resolved>로 두고 아래 use 섹션을 <resolved>로 진행.~/.openclone/menu-context를 삭제합니다 (rm -f ~/.openclone/menu-context).입력: 클론 이름 <name> (= $1 또는 숫자 해석 결과).
클론 존재 확인. 우선순위:
~/.openclone/clones/<name>/persona.md → origin = user${CLAUDE_SKILL_DIR}/clones/<name>/persona.md → origin = built-in둘 다 없으면 한 줄 안내 후 중단:
<name>클론을 찾을 수 없어요./openclone로 목록을 확인하거나/openclone new <name>으로 새로 만들어 주세요.
built-in이면 지식 lazy-fetch (user clone은 skip):
bash "${CLAUDE_SKILL_DIR}/scripts/fetch-clone-knowledge.sh" "<name>"active-clone 기록:
mkdir -p ~/.openclone
printf '%s' "<name>" > ~/.openclone/active-clonepersona.md frontmatter를 간단히 읽어 display_name, primary_category(없으면 categories[0]), categories 확인. 한두 줄로 확인 메시지:
활성 클론: {display_name} ({primary_category} 렌즈, categories: {categories}, origin: {user | built-in}). 다음 메시지부터 이 클론으로 응답해요.
/openclone stop으로 해제.
origin이 built-in이면 한 줄 덧붙임:
이 클론은 내장형이어서 읽기 전용입니다. 수정하려면 먼저
~/.openclone/clones/<name>/로 폴더를 복사하세요.
이 커맨드 응답에서 클론을 연기하지 마세요 — 페르소나 주입은 훅이 다음 턴부터 담당합니다.
~/.openclone/active-clone, ~/.openclone/room, ~/.openclone/menu-context 상태 확인. 셋 다 없으면 한 줄 안내 후 중단:
활성 클론도, 열린 방도 없어요.
존재하는 것만 제거:
rm -f ~/.openclone/active-clone ~/.openclone/room ~/.openclone/menu-context어느 상태가 정리됐는지 한 줄로 보고. 예:
활성 클론(douglas)과 방(douglas, alice)을 모두 종료했어요. 다음 메시지부터 기본 Claude가 응답.
입력 처리:
$2가 비어 있으면 /openclone new <name> 사용법 안내 후 중단.$2를 슬러그 검증: ^[a-z0-9][a-z0-9-]*$. 실패 시 소문자 슬러그로 다시 요청.~/.openclone/clones/$2/persona.md 이미 존재 → 취소/다른 이름/덮어쓰기 중 택1 요청.${CLAUDE_SKILL_DIR}/clones/$2/persona.md 존재 → 사용자 클론이 내장을 가린다고 경고 후 진행/이름 변경/취소 택1 요청.실행:
${CLAUDE_SKILL_DIR}/references/interview-workflow.md 를 로드해 정확히 따르세요. 이 워크플로는 먼저 Chrome MCP preflight를 돌리고, 타겟이 실제 인물이면 Stage 0 자동 발굴(소셜 링크 검색 → Chrome MCP로 LinkedIn/Threads/X/Instagram 스크랩 → YouTube는 scripts/fetch-youtube.sh로 자막 추출)로 페르소나·첫 지식 파일을 자동 작성합니다. 자동 발굴이 성공하면 문답 스테이지 1–5는 스킵, 유저에게 한 번만 확인받습니다. 실패하거나 공개 프레즌스가 없으면 기존 문답 모드로 fallback.
카테고리는 최소 1개 필수 (vc, tech, founder, expert, influencer, politician, celebrity 중).
인터뷰 종료 시:
mkdir -p "$HOME/.openclone/clones/<name>/knowledge"~/.openclone/clones/<name>/persona.md를 ${CLAUDE_SKILL_DIR}/references/clone-schema.md 형식대로 작성. 인터뷰 원문은 ~/.openclone/clones/<name>/knowledge/YYYY-MM-DD-interview.md에 source_type: interview로 저장.
한 줄 확인:
{display_name} 생성 완료 —
~/.openclone/clones/{name}/./openclone {name}으로 활성화.
이 단계에서 클론 연기는 하지 않음.
입력 처리:
~/.openclone/active-clone 없거나 비었으면 "/openclone <name>으로 먼저 클론을 활성화해 주세요." 안내 후 중단.
active-clone 이름으로 persona 경로 탐색:
~/.openclone/clones/<name>/persona.md → user${CLAUDE_SKILL_DIR}/clones/<name>/persona.md → built-inbuilt-in이면 fork-on-write 먼저:
mkdir -p "$HOME/.openclone/clones"
cp -R "${CLAUDE_SKILL_DIR}/clones/<name>" "$HOME/.openclone/clones/<name>"한 줄 안내:
내장 **
<name>**을~/.openclone/clones/<name>/로 포크했어요 (이제 사용자 사본이 내장을 가림). ingest 계속 진행.
$2 이후가 소스(URL, 경로, 또는 텍스트). 비어 있으면 요청.
실행:
https://www.youtube.com/ | https://youtu.be/ → YouTube → ${CLAUDE_SKILL_DIR}/scripts/fetch-youtube.sh <url>http:// | https:// → URL → WebFetch (실패 시 ${CLAUDE_SKILL_DIR}/scripts/fetch-url.sh <url>).md|.txt|.pdf|.docx) → Read (PDF/DOCX은 Read 지원 범위 안에서)${CLAUDE_SKILL_DIR}/references/refine-workflow.md 를 로드해 그대로 따름 — 날짜+토픽별 파일을 ~/.openclone/clones/<name>/knowledge/에 append-only로 기록.**{display_name}**에 추가됨:
~/.openclone/clones/{name}/knowledge/. 토픽:YYYY-MM-DD-<topic>.
입력 처리:
대상 결정:
$2가 슬러그(^[a-z0-9][a-z0-9-]*$)면 그 이름으로.$2가 비어 있으면 ~/.openclone/active-clone 읽기. 비었으면 안내 후 중단:먼저
/openclone <name>으로 클론을 활성화하거나/openclone update <name>으로 이름을 지정해 주세요.
persona 경로 탐색 (user → built-in). 없으면 안내 후 중단.
built-in이면 fork-on-write 먼저 (ingest와 동일):
mkdir -p "$HOME/.openclone/clones"
cp -R "${CLAUDE_SKILL_DIR}/clones/<name>" "$HOME/.openclone/clones/<name>"한 줄 안내 후 진행.
실행:
${CLAUDE_SKILL_DIR}/references/update-workflow.md 를 로드해 그대로 따르세요. 이 워크플로는 먼저 Chrome MCP preflight를 돌리고, 사용자 사본의 knowledge/ 최신 파일 날짜를 cutoff로 잡은 뒤 persona.md ## Links의 각 URL을 Chrome MCP / scripts/fetch-youtube.sh로 수집, cutoff 이후 게시물만 refine-workflow.md로 dated 파일에 append 합니다./openclone update <name>을 보여주고 실행.$2(서브 서브명령) 기준 분기:
$2 | 동작 |
|---|---|
| (비어 있음) | 아래 room status |
leave | 아래 room leave |
add (이후 = $3) | 아래 room add |
remove (이후 = $3) | 아래 room remove |
| 그 외 (= 클론 이름 첫 토큰, 이후 더 올 수 있음) | 아래 room start — $2 $3 … 전부를 새 멤버 리스트로 해석 |
~/.openclone/room 읽기. 없거나 비었으면 "현재 열린 방이 없어요. /openclone room <이름1> <이름2> ...으로 시작하세요." 출력. 있으면 멤버 줄별로 표시.
입력: 공백·콤마로 구분된 클론 이름들 (최소 1개, 최대 8개까지 허용. 그 이상은 앞 8개만 취하고 경고).
각 이름 검증 (슬러그 형식). 잘못된 이름이 있으면 그 항목 skip하고 경고.
각 이름에 대해 persona 존재 확인 (user → built-in 순). 없으면 skip + 경고.
built-in이 섞여 있으면 각각에 대해 fetch-clone-knowledge.sh 호출.
결과 이름들을 ~/.openclone/room에 한 줄씩 기록 (기존 방 덮어쓰기). 한 명도 남지 않으면 파일 쓰지 않고 안내.
mkdir -p ~/.openclone
printf '%s\n' "alice" "bob" "charlie" > ~/.openclone/room확인: 방을 열었어요: alice, bob, charlie. 다음 메시지부터 가장 적절한 클론이 자동으로 응답.
세부 규칙은 ${CLAUDE_SKILL_DIR}/references/room-workflow.md 참조.
~/.openclone/room 있어야 함. 없으면 "먼저 /openclone room <이름>으로 방을 시작하세요." 출력 후 중단.$3 검증 + persona 존재 확인 + built-in이면 fetch.<name>은 이미 멤버입니다." 출력 후 중단.printf '%s\n' "<name>" >> ~/.openclone/room).<name>을 방에 추가했어요. 현재 멤버: a, b, c, <name>.~/.openclone/room 있어야 함. 없으면 안내.$3이 방 멤버에 없으면 "그 이름은 방에 없어요." 출력 후 중단.rm -f ~/.openclone/room한 줄 확인. active-clone은 건드리지 않음 (유저가 명시적으로 /openclone stop을 쓰지 않는 한 이전 활성 클론은 유지).
입력: $2 = 카테고리, 이후 = 질문.
$2 가 {vc, tech, founder, expert, influencer, politician, celebrity} 중 하나인지 확인. 아니면 다음 안내 후 중단:카테고리는 vc, tech, founder, expert, influencer, politician, celebrity 중 하나. 예:
/openclone panel vc "내 SaaS 피봇 어때요?"
$3 이후를 합친 질문이 비어 있으면 사용법 안내 후 중단.${CLAUDE_SKILL_DIR}/references/panel-workflow.md 와 ${CLAUDE_SKILL_DIR}/references/categories.md 를 로드. 패널 워크플로를 category = $2, question = 나머지 $ARGUMENTS로 정확히 실행.${CLAUDE_SKILL_DIR}/references/clone-schema.md — 클론 파일 포맷 (frontmatter + 섹션, 멀티 카테고리 규칙)${CLAUDE_SKILL_DIR}/references/categories.md — 고정 카테고리 7종 + 카테고리별 "항상 점검" 축${CLAUDE_SKILL_DIR}/references/home-workflow.md — 홈 패널 렌더 및 menu-context 기록${CLAUDE_SKILL_DIR}/references/interview-workflow.md — new 인터뷰 진행·정리${CLAUDE_SKILL_DIR}/references/refine-workflow.md — ingest가 원본 소스를 토픽 파일로 정제${CLAUDE_SKILL_DIR}/references/update-workflow.md — update가 마지막 지식 일자 이후 소셜/유튜브 자료를 자동 수집${CLAUDE_SKILL_DIR}/references/panel-workflow.md — 카테고리 패널 다중 클론 출력${CLAUDE_SKILL_DIR}/references/room-workflow.md — 방 안 턴별 라우팅${CLAUDE_SKILL_DIR}/assets/clone-template.md — 수기 작성용 시작 템플릿© team-attention, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 4,428 other files (scripts, references, assets) in the repository root of team-attention/openclone.
Open the folder on GitHubat commit 40d0586
Openclone next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Openclone this skillteam-attention/openclone | 130 | — | ~2.6k | Automated safety check: Notes | MIT | |
| Gingiris Ugc MatrixGingiris-1031/Competitor-analysis-tool | 110 | — | ~790 | Automated safety check: Pass | None | |
| Creator Profile TeardownScrapeCreators/social-media-research-skills | 3.3k | — | ~550 | Automated safety check: Notes | MIT | |
| Ugcfal-ai-community/skills | 249 | — | ~1.5k | Automated safety check: Pass | None | |
| Gingiris Kol OutreachGingiris-1031/Competitor-analysis-tool | 110 | — | ~965 | Automated safety check: Pass | None | |
| Funnel PlannerAffitor/affiliate-skills | 698 | — | ~2.2k | Automated safety check: Pass | MIT |
Gingiris-1031/Competitor-analysis-tool
🇺🇸 UGC Matrix Growth Playbook — Scale user-generated content with AI + real creators.
ScrapeCreators/social-media-research-skills
A skill your agent uses when the user wants to analyze a creator, influencer, founder, or brand social account and understand positioning, content pillars, outlier posts, hooks, format choices…
fal-ai-community/skills
Plan and run UGC-style creator ads and social proof videos with genmedia.
Gingiris-1031/Competitor-analysis-tool
🇺🇸 KOL Outreach & Influencer Marketing Playbook — Complete SOP from discovery to ROI tracking.
Affitor/affiliate-skills
Plan a complete affiliate funnel from research to revenue. An agent skill from Affitor/affiliate-skills.
scenario-labs/skills
A skill your agent uses when producing UGC-style creator video with Scenario: a talking-head ad or testimonial from a portrait and a script, a founder clip, a product demo or unboxing, a reaction or…
team-attention/openclone
A skill your agent uses when the user wants to consult an AI persona "clone" for advice, strategy, analysis, or domain expertise—especially in startup, VC, tech, growth, HR, or business contexts.
Categories
Create, manage, or talk to an openclone "clone" — a named AI persona with one or more categories (vc, tech, founder, expert, influencer, politician, celebrity) and attached knowledge. Openclone is an agent skill from team-attention/openclone. Create, manage, or talk to an openclone "clone" — a named AI persona with one or more categories (vc, tech, founder, expert, influencer, politician, celebrity) and attached knowledge.
Openclone fits situations like: phrases like create a clone; switch to <name; feed knowledge to; ingest url for <clone.
Run `npx skills add team-attention/openclone --skill openclone -a claude-code`. Or copy the skill folder (the team-attention/openclone repository) into .claude/skills/openclone in your project. Claude Code loads it when a task matches its description.
Run `npx skills add team-attention/openclone --skill openclone -a codex`. Or copy the skill folder (the team-attention/openclone repository) into .agents/skills/openclone in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add team-attention/openclone --skill openclone -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/openclone, .gemini/skills/openclone, .github/skills/openclone and .opencode/skills/openclone in your project.
Going by SKILL.md and its folder, Openclone needs TypeScript and a shell for the scripts in its folder and the command-line tools its instructions call (bash). Our summary lists: Node.js; A Bash shell. Its frontmatter pre-approves these tools: Bash, Read, Write, Glob, WebFetch, WebSearch.
SKILL.md names 2 domains. In commands or code: youtube.com and youtu.be; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Openclone is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 15k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Openclone: Gingiris Ugc Matrix (Gingiris-1031/Competitor-analysis-tool, 110 stars), Creator Profile Teardown (ScrapeCreators/social-media-research-skills, 3.3k stars), Ugc (fal-ai-community/skills, 249 stars) and Gingiris Kol Outreach (Gingiris-1031/Competitor-analysis-tool, 110 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
team-attention (a GitHub organization) maintains it in team-attention/openclone, which has 130 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on August 17, 2026.
Source: team-attention/openclone on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.