kakaotalk-cli
macOS에서 카카오톡 메시지를 읽고 보낸다. 렌더링 안 된 채팅방도 검색으로 찾아 열고 줄바꿈을 보존한다. 실패하는 경로와 대체 경로를 함께 담았다.
Asset-Profil
Recherche und Wissensarbeit
Deep research, source comparison, literature review, RAG, knowledge search, and reports.
Szenario
RAG and knowledge
I need my agent to build a RAG workflow over documents and retrieve reliable context.
Agent-Fit
Claude Code + CLI + Codex
Geeignet für Codex, Claude Code, Cursor, CLI oder benutzerdefinierte Agents.
Installieren
Bereit
npx skills add bam-bam-2/solo-skills --skill kakaotalk-cli
Wartung
Aktuell
Heute gepusht
Risiko
Prüfung nötig
Dependency or permission surface needs review
GitHub-Qualität
11
57/100 Qualität · 65/100 Vertrauen
Abdeckungs-Tags
Review-Notizen
Dependency or permission surface needs review · Permission surface may require sandboxing
Agent-Adoptionskarte
Vertrauen, Audit und Installationsbereitschaft auf einen Blick
Diese Werte kombinieren öffentliche Repository-Metadaten, OpenAgentSkill-Reviewsignale, Wartungsaktualität und Installationsbereitschaft. Sie helfen bei der Vorauswahl, ersetzen aber keine menschliche Prüfung.
Qualität
VielversprechendUseful candidate, but compare it with alternatives before adopting.
Vertrauen
Do not auto-installTrust Score v5 found insufficient evidence for agent installation. Treat this as discovery material, not an executable recommendation.
Audit
Prüfung nötigMaschinenlesbare Prüfung von Installationsbereitschaft, Sicherheitsmetadaten, Wartung und Akzeptanzrisiko.
OpenAgentSkill Trust Score v5
Menschliche Prüfung vor Installation
Choose a stronger alternative or inspect the source manually before any install attempt.
Stars
11 GitHub-Stars
Repository-Aktivität
11 Stars und 4 Forks
Wartung
Heute gepusht
Lizenz
MIT
Installieren
npx skills add bam-bam-2/solo-skills --skill kakaotalk-cli
Installationssicherheit
Standard-Paket- oder Laufzeit-Installationspfad
Berechtigungsfläche
secrets or environment access, shell or command execution
Agent-Ergebnisse
Noch keine Agent-Ergebnisdaten
Dokumentation
Usable metadata, review docs
Risikoübersicht
Vor Produktion prüfen
- The skill references '에이전트 메모' (Agent Memo) for additional background and fallback details, but that content is not included in the repository. This may leave some context incomplete for agents without access to that memo.
- Low GitHub adoption signal
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
Installationsbereitschaft
Installationspfad verfügbar
- Installationspfad ist verfügbar
- Repository-Belege sind verfügbar
- Lizenz ist angegeben
- Noch keine Agent-Proven-Ergebnisbelege
Agent-lesbare Metadaten
Maschinenlesbare Entscheidungsdaten für diesen Skill.
Nutze diesen Block oder das eingebettete JSON, um zu entscheiden, ob ein Agent diesen Skill installieren, eine Alternative wählen oder zuerst menschliche Prüfung anfordern soll.
Geeignete Aufgaben
- Local desktop-Workflows
- Claude-Code-Teams
- builders willing to evaluate younger projects
- Navigate local resources
Geeignete Agents
Installationsentscheidung
- Befehl
- npx skills add bam-bam-2/solo-skills --skill kakaotalk-cli
- Richtlinie
- Blockieren
- Menschliche Prüfung
- Ja
Vertrauen und Risiko
- Vertrauen
- 57/100
- Audit
- 72/100
- Risikoebene
- Prüfung nötig
Ergebnis-Loop
- Endpoint
- /api/agent/outcome
- Event-ID
- resolve
- Ergebnisse
- 5
Installationsbefehl
npx skills add bam-bam-2/solo-skills --skill kakaotalk-cliNicht verwenden, wenn
- Teams, die ein vom Anbieter unterstütztes SLA benötigen
- production agents without a repository review
- Low GitHub adoption signal
- The skill references '에이전트 메모' (Agent Memo) for additional background and fallback details, but that content is not included in the repository. This may leave some context incomplete for agents without access to that memo.
- No OpenAgentSkill engagement data yet
Agent-Sicherheit v2
36/100 · Automatische Installation vermeiden
This skill should not be selected by an agent without explicit human security review.
Do not auto-install. Inspect the source, dependencies, and permission surface first.
Hoch
Shell- oder Befehlsausführung
Die Skill-Metadaten verweisen auf Terminal-, CLI-, Shell-, Subprozess- oder Befehlsausführungs-Workflows.
Mittel
Netzwerkzugriff
Die Skill ruft wahrscheinlich Remote-Seiten, APIs, Repositories oder externe Dienste ab.
Hoch
Secrets or environment access
Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.
- Hinweise auf Hochrisiko-Berechtigungen: Shell or command execution, Secrets or environment access
- Dependency or permission surface needs review
Installationsziele
Diesen Skill im Agent-Workflow installieren
Über den öffentlichen Endpunkt erhältst du Befehl, Sicherheitscheckliste, Ziel-Prompts und kanonische Links.
OpenAgentSkill CLI
Resolve policy, run the source installer safely, and report a verified install receipt.
$ npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install bam-bam-2-kakaotalk-cliAgent-Auflösungsplan
Lass einen Agent die Eignung vor der Installation prüfen.
Die Resolve API liefert die beste Skill, Alternativen, Sicherheitsrichtlinien, Auditnotizen, Installationsziel und einen direkt nutzbaren Prompt.
JSON öffnen
/api/agent/resolve?task=Use%20kakaotalk-cli%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve-Text
/api/agent/resolve?task=Use%20kakaotalk-cli%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Installationsübergabe
/api/skills/bam-bam-2-kakaotalk-cli/install
Agent sollte prüfen
- Task fit and alternatives from Resolve API.
- Audit score, trust score, and safety policy warnings.
- Install target compatibility for Codex, Claude Code, Cursor, or CLI.
Prompt kopieren
Task: Use kakaotalk-cli in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20kakaotalk-cli%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/bam-bam-2-kakaotalk-cli/install
Install command: npx skills add bam-bam-2/solo-skills --skill kakaotalk-cli
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent-Übergabe
Gib dem Agent den Installationspfad, nicht noch ein Verzeichnis.
Über den öffentlichen Endpunkt erhältst du Befehl, Sicherheitscheckliste, Ziel-Prompts und kanonische Links.
Installationsübergabe
/api/skills/bam-bam-2-kakaotalk-cli/install
LLM-Textformat
/api/skills/bam-bam-2-kakaotalk-cli/install?format=text
Alternativen finden
/api/skills/search?q=kakaotalk-cli&limit=3
Agent-Prompt
Use kakaotalk-cli for this task. Review https://www.openagentskill.com/api/skills/bam-bam-2-kakaotalk-cli/install, then install with: npx skills add bam-bam-2/solo-skills --skill kakaotalk-cliRegistry-Metadaten
Agent-lesbares Profil für die automatische Skill-Auswahl.
Die Registry API stellt Entscheidungs-, Vertrauens-, Audit-, Use-Case- und Installationssignale ohne UI-Scraping bereit.
Manifest
/api/registry/manifest/bam-bam-2-kakaotalk-cli
LLM-Text
/api/registry/manifest/bam-bam-2-kakaotalk-cli?format=text
Installationsalias
/api/registry/install/bam-bam-2-kakaotalk-cli
Empfehlen
/api/registry/recommend?task=Use%20kakaotalk-cli%20in%20an%20agent%20workflow&limit=3
Agent-Fit
Local desktop
Use-Case-Tags
Plattformen
Claude Code
Audit-Bericht
Prüfung nötig · 72/100
Maschinenlesbare Prüfung von Installationsbereitschaft, Sicherheitsmetadaten, Wartung und Akzeptanzrisiko.
Agent-Entscheidungspanel
Needs validation for Local desktop
Do a manual repository review before adding this to an agent workflow.
Rolle im Stack
Validierung nötig
Primäre Eignung
Local desktop
Vertrauenslabel
Manuelle Prüfung nötig
Installationspfad
Befehl bereit
Verwenden wenn
- Local desktop-Workflows
- Claude-Code-Teams
- builders willing to evaluate younger projects
Evidenz
- recent repository activity
- install command or GitHub repo available
- Qualitätsprofil 57/100
zuerst prüfen
- Low GitHub adoption signal
- The skill references '에이전트 메모' (Agent Memo) for additional background and fallback details, but that content is not included in the repository. This may leave some context incomplete for agents without access to that memo.
- No OpenAgentSkill engagement data yet
Implementierungspfad
- 1Installieren Sie es in einem Sandbox-Agent und führen Sie eine Local desktop-Aufgabe vollständig aus.
- 2Compare output quality, latency, and failure behavior against at least one alternative.
- 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.
Vertrauensprofil
Do not auto-install
Trust Score v5 found insufficient evidence for agent installation. Treat this as discovery material, not an executable recommendation.
GitHub-Akzeptanz
Beheben11 GitHub-Stars
Star-/Fork-Aktivität
Beheben11 Stars und 4 Forks; Issue-Aktivität ist in den aktuellen Metadaten nicht verfügbar
Aktuelle Wartung
BestandenHeute gepusht
Lizenzklarheit
BestandenMIT
Positive Signale
- KI-Prüfung genehmigt
- Installationspfad ist verfügbar
- Repository-Belege sind verfügbar
- Kürzlich gewartetes Repository
- Der Installationsbefehl weist kein offensichtliches Hochrisikomuster auf
- Ergebniszyklus ist bereit, benötigt aber den ersten echten Agent-Lauf
Vor Installation prüfen
- The skill references '에이전트 메모' (Agent Memo) for additional background and fallback details, but that content is not included in the repository. This may leave some context incomplete for agents without access to that memo.
- Low GitHub adoption signal
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
- GitHub adoption: 11 GitHub stars
- Stars/forks activity: 11 stars, 4 forks; issue activity unavailable in current metadata
- Dependency/runtime risk: command execution surface, credential or environment access
- Permission surface: secrets or environment access, shell or command execution
- Noch keine echten Agent-Ergebnisberichte
- Vor unbeaufsichtigter Installation ist menschliche Prüfung erforderlich
Empfohlene Aktion
Choose a stronger alternative or inspect the source manually before any install attempt.
Qualitätsprofil
Vielversprechend Kandidat für Agent-Workflows
Useful candidate, but compare it with alternatives before adopting.
Workflow-Eignung
Diese Skill in diesen Szenarien nutzen
Operate local tools
Local desktop
I need my agent to operate local files and desktop apps in a repeatable workflow.
Operate web apps
Browser automation
I need my agent to control a browser, fill forms, and verify web app workflows.
Search private knowledge
RAG and knowledge
I need my agent to build a RAG workflow over documents and retrieve reliable context.
Workflow-Eignung
Zum vollständigen Workflow hinzufügen
Operate and verify web apps
Browser QA agent
A workflow for agents that navigate products, fill forms, take screenshots, and verify real user flows across web applications.
Turn skills into distribution
Content growth agent
A workflow for turning newly indexed skills into SEO briefs, social drafts, comparison pages, and reusable publishing workflows.
Ingest, retrieve, and cite
RAG knowledge base
A workflow for document-heavy agents that ingest files, create searchable knowledge, retrieve relevant context, and answer with grounded sources.
Alternativen-Shortlist
Vor Installation vergleichen
Similar skills that may fit this task.
UI-TARS Desktop
Run multimodal agents that operate desktop interfaces
MoneyPrinterTurbo
利用AI大模型,一键生成高清短视频 Generate short videos with one click using AI LLM.
Cua
Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
Übersicht
--- name: kakaotalk-cli description: "macOS에서 카카오톡 메시지를 읽고 보낸다. 렌더링 안 된 채팅방도 검색으로 찾아 열고 줄바꿈을 보존한다. 실패하는 경로와 대체 경로를 함께 담았다." ---
# 카카오톡 보내기·읽기
**정본 도구는 `kmsg`다.** `kakaocli send`는 쓰지 않는다 — 화면에 렌더링된 채팅 목록만 훑어서 아래로 밀린 방을 못 찾고, DB 키를 받는 옵션도 없다.
## 왜 SSH를 거치나
Aside 샌드박스는 **GUI 실행·AX(손쉬운 사용)·타 프로세스 조회가 전부 막혀 있다.** 그래서 모든 명령은 SSH 루프백으로 샌드박스 밖에서 실행한다.
```bash ssh -o BatchMode=yes localhost 'export PATH=/opt/homebrew/bin:$PATH; kmsg ...' ```
`kakaocli status`가 "App state: notRunning"이라고 해도 믿지 말 것. 샌드박스가 프로세스를 못 볼 뿐 카톡은 대개 켜져 있다.
선행 조건(2026-08-15 부여 완료): `/usr/libexec/sshd-keygen-wrapper`에 시스템 설정 → 개인정보 보호 및 보안 → **손쉬운 사용** 권한. 없으면 모든 AX 호출이 `-25211`로 막힌다.
## 절차
```bash # 1. 상태와 열린 창 확인 — 이 단계를 건너뛰지 말 것 kmsg status --verbose
# 2. (메인 창 외에 채팅 창이 열려 있으면 닫는다)
# 3. 보낼 내용을 파일로 빼서 따옴표 문제를 피한다 kmsg send "<방이름>" "$(cat /path/msg.txt)"
# 4. 실제로 나갔는지 읽어서 확인 kmsg read "<방이름>" --limit 1 --json ```
- **`kmsg send`는 성공 후 방 창을 닫는다.** 그래서 직후 `kmsg read`는 창이 없다며 실패한다. 발송 검증은 `kakaocli messages --chat-id ... --key`로 DB를 보거나, 창을 다시 열고 읽는다. - 방은 이름 substring 또는 `--chat-id`로 지정한다. `kmsg chats --json`로 목록. - 보내기 전 `--dry-run`으로 수신자를 한 번 확인한다. - **나와의 채팅은 `나와의 채팅`이 아니라 프로필명 `내 프로필명`으로 지정한다.** - 처음 보내는 상대이거나 내용이 길면 먼저 `내 프로필명`으로 연습 발송해 서식을 확인한다.
## AI가 보냈다는 표시 (필수)
카톡은 사용자 본인 명의로 나가므로, **대신 보내는 전달·공지·안내성 메시지에는 본문 맨 끝에 서명 한 줄을 붙인다.**
``` — 이 메시지는 사용자을 대신해 AI가 정리해서 보냈습니다 ```
사용자가 2026-08-15에 직접 요청했다("디스코드 봇은 그렇게 해주잖아"). 디스코드는 커뮤니티봇 봇 계정이라 이미 드러나지만 카톡은 안 드러난다는 게 이유. 개인 브랜드 콘텐츠(블로그·스레드·링크드인)는 예외.
## 단톡방에 보낼 때
- **진짜 @멘션은 걸 수 없다.** 카톡 멘션은 `@` 입력 시 뜨는 멤버 선택 팝업에서 골라야 생기고, 자동 입력은 그 팝업 때문에 문장이 깨질 위험이 있다. 이름을 본문에 나열하는 방식으로 쓰고, 하이라이트가 필요하면 사용자가 직접 단다. - 여러 명이 읽는 메시지는 **먼저 `내 프로필명`으로 연습 발송해 서식을 확인**하고, 사용자 승인을 받은 뒤 보낸다.
## 실패하면
| 증상 | 원인과 조치 | |---|---| | `[SEARCH_MISS] Search field not found` | 다른 채팅 창이 열려 있다. 닫고 `--refresh-cache` | | 같은 오류인데 창이 메인 하나뿐 | 방 창이 막 열리는 중이라 AX 캐시가 어긋난 것. **그대로 `--refresh-cache`로 한 번만 재시도하면 나간다**(2026-08-16 실측). 첫 실패로 발송이 안 된 것이 맞는지 `kakaocli messages`로 먼저 확인할 것 | | `[WINDOW_NOT_READY]` | 같은 원인. `open -a KakaoTalk` 후 재시도 | | `[BACKGROUND_SAFE_BLOCKED]` | `--background-safe`는 이미 열린 창만 읽는다. 정상 동작 | | 방을 못 찾음 | `kmsg chats --limit 200 --json`로 이름 확인 |
## 하지 말 것
- **`kmsg harvest`류의 메타데이터 재수집을 실행하지 말 것.** `kakaocli harvest`가 `~/.kakaocli/metadata.json`의 방 이름을 전부 `(unknown)`으로 덮어쓴 사고가 있었다. 백업: `~/.kakaocli/backups/` - AppleScript `keystroke`로 한글을 치지 말 것 — `ㅁㅁㅁ`으로 깨진다. SSH `pbcopy`도 GUI 페이스트보드에 닿지 않는다. - **대량 발송·무인 자동응답 봇으로 확장하지 말 것.** 카카오 운영정책에 자동화 프로그램 이용 제한이 있고 계정 제재 가능성이 있다. 사용자가 2026-08-15에 무인 자동응답은 돌리지 않겠다고 명시했다.
## 참고
- 읽기 전용 대량 조회·검색이 필요하면 `kakaocli`(DB 직접 복호화)를 쓴다. 키는 원격 머신 `~/Projects/<프로젝트>/dashboard/.env`의 `KAKAOCLI_KEY`이며 `--key`로 넘긴다(환경변수는 읽지 않는다). 절대 출력하지 말 것. - 전체 배경·폴백(수동 AX 주입)·AppleScript 함정: `에이전트 메모` - 무인 상시 운영이 필요해지면: `에이전트 메모`
Technische Details
- Version
- 1.0.0
- Lizenz
- MIT
- Letzte Aktualisierung
- 22. Aug. 2026
- Veröffentlicht
- 22. Aug. 2026
Entscheidungsübersicht
Validierung nötig
recent repository activity
Audit
Installationsprüfung
Installations- und Adoptionsprüfung
- Sicherheit
- 72/100
- Wartung
- 100/100
- Installieren
- 92/100
Von Agent belegte Evidenz
Von Agent belegte Evidenz
Ergebnisberichte nach Resolve, Prüfung, Installation und einem begrenzten Lauf.
- Erfolgsrate
- —
- Letzter Fehler
- —
- Ergebnisse
- 0
- Ausgabequalität
- —
- Fehlgeschlagen
- 0
- Nicht relevant
- 0
- Installationen
- 0
- Durch Risiko blockiert
- 0
- Einrichtung erforderlich
- 0
- Produktion
- 0
Noch keine Agent-Ergebnisdaten. Der erste Lauf kann Erfolg, Einrichtungsbedarf, Risikoblockaden, Fehler oder Irrelevanz über /api/agent/outcome melden.
Installieren
Zum Agent-Workflow hinzufügen
Kostenlos und Open Source. Bericht vor der Installation in Produktions-Agents prüfen.
Wachstums-Loop
Share-Kit
Szenariobasierter Entwurf für kakaotalk-cli, bereit für einen manuellen X-Post.
Before you hand an agent a repeatable workflow, give it a repeatable starting point. kakaotalk-cli: macOS에서 카카오톡 메시지를 읽고 보낸다. 렌더링 안 된 채팅방도 검색으로 찾아 열고 줄바꿈을 보존한다. 실패하는 경로와 대체 경로를 함께 담았다. 11 stars https://www.openagentskill.com/skills/bam-bam-2-kakaotalk-cli?ref=x
Optionale Antwort mit Installationsbefehl
Listing + install path for kakaotalk-cli: https://www.openagentskill.com/skills/bam-bam-2-kakaotalk-cli?ref=x Install: npx skills add bam-bam-2/solo-skills --skill kakaotalk-cli
Quelle des Eintrags
Registry-indexiert
Dieser Eintrag wurde aus öffentlichen Quellen indexiert und ist erst nach Genehmigung eines Maintainer-Anspruchs offiziell.
- Ersteller
- bam-bam-2
- Quelle
- bam-bam-2/solo-skills
- Indexiert von
- OpenAgentSkill Community-Index
Die Zuordnung verlinkt auf das öffentliche Repository oder Creator-Profil. Creator können den Eintrag beanspruchen, um Eigentümersignale zu aktualisieren.
Diesen Skill beanspruchenEigentümeranspruch
Diesen Skill-Eintrag beanspruchen
Dieser Registry-indexiert-Eintrag wird bam-bam-2 zugeschrieben, ist aber noch nicht offiziell markiert. Beanspruche ihn, um ein verifiziertes Eigentümersignal hinzuzufügen und künftige Launch-, Installations- und Audit-Updates vertrauenswürdiger zu machen.
Creator-Backlink-Kit
Evidenz-Badges in deine README einfügen
Zeige den kanonischen Eintrag, aktuelle Vertrauens- und Audit-Signale sowie echte Agent-Proven-Evidenz dort, wo Entwickler das Repository bewerten.
[](https://www.openagentskill.com/skills/bam-bam-2-kakaotalk-cli)
[](https://www.openagentskill.com/skills/bam-bam-2-kakaotalk-cli)
[](https://www.openagentskill.com/skills/bam-bam-2-kakaotalk-cli/audit)
[](https://www.openagentskill.com/skills/bam-bam-2-kakaotalk-cli)Autor
bam-bam-2
@bam-bam-2
Tags
Plattform-Fit
Gesundheitssignale
- GitHub-Stars
- 11
- Qualitätswert
- 31/100
- Letzter GitHub-Push
- 22. Aug. 2026
- Framework-Hinweise
- Unbekannt
- OpenAgentSkill-Aufrufe
- 0
- Installationskopien
- 0
- Externe Klicks
- 0
Community-Signal
Teile mit, ob dieser Skill für deinen Agent-Workflow nützlich ist. Zusammengefasstes Feedback verbessert das Ranking im Laufe der Zeit.
Vertrauen & Sicherheit
Do not auto-install
- GitHub-Akzeptanz11 GitHub-StarsBeheben
- Star-/Fork-Aktivität11 Stars und 4 Forks; Issue-Aktivität ist in den aktuellen Metadaten nicht verfügbarBeheben
- Aktuelle WartungHeute gepushtBestanden
- LizenzklarheitMITBestanden
- README/SKILL.md-VollständigkeitÖffentliche Metadaten benötigen mehr README/SKILL.md-KontextInfo
- Abhängigkeits-/Laufzeitrisikocommand execution surface, credential or environment accessPrüfen
Ähnliche Skills
UI-TARS Desktop
Run multimodal agents that operate desktop interfaces
37.0K StarsMoneyPrinterTurbo
利用AI大模型,一键生成高清短视频 Generate short videos with one click using AI LLM.
88.5K StarsCua
Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
21.4K Stars