원클릭으로
anytype-skill
Interact with Anytype's local REST API to manage spaces, objects, types, properties, tags, lists, and search.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Interact with Anytype's local REST API to manage spaces, objects, types, properties, tags, lists, and search.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | anytype-skill |
| description | Interact with Anytype's local REST API to manage spaces, objects, types, properties, tags, lists, and search. |
| disable-model-invocation | true |
| allowed-tools | Read, Grep, Glob, Bash, WebFetch |
| argument-hint | <command> [args] (e.g., /anytype search 'meeting notes', /anytype objects list <space_id>) |
Interact with Anytype's local-first REST API from Claude Code. Manage spaces, objects, types, properties, tags, lists, and run searches across your knowledge base — all without leaving the terminal.
Anytype runs a local HTTP API on your machine (no cloud). The desktop app listens on 127.0.0.1:31009; anytype-cli on 127.0.0.1:31012.
Command group (auth, search, spaces, objects, files, types, properties, tags, lists, members)
Subcommand (list, get, create, update, delete, etc.)
Space ID (required for most operations)
Object/type/property IDs as needed
Search queries and filter expressions
Template paths are resolved from ${AGENTS_SKILLS_ROOT}/anytype-skill/.
anytype-cli must be active).${AGENTS_SKILLS_ROOT}/anytype-skill/commands/auth.md.http://127.0.0.1:31009/v1 (desktop) or http://127.0.0.1:31012/v1 (CLI)Authorization: Bearer <api_key>Anytype-Version: 2025-11-08application/jsonoffset and limit query params (default limit=100)Check which Anytype instance is running:
curl -s -o /dev/null -w "%{http_code}" http://127.0.0.1:31009/v1/spaces 2>/dev/null || \
curl -s -o /dev/null -w "%{http_code}" http://127.0.0.1:31012/v1/spaces 2>/dev/null
Use whichever returns a response (even 401 means it's up).
If no API key is available, follow ${AGENTS_SKILLS_ROOT}/anytype-skill/commands/auth.md to obtain one via the challenge-response flow.
Based on the user's request, read and follow the relevant command doc:
${AGENTS_SKILLS_ROOT}/anytype-skill/commands/auth.md — Authentication & API keys${AGENTS_SKILLS_ROOT}/anytype-skill/commands/search.md — Global and space-scoped search${AGENTS_SKILLS_ROOT}/anytype-skill/commands/spaces.md — Space CRUD${AGENTS_SKILLS_ROOT}/anytype-skill/commands/objects.md — Object CRUD${AGENTS_SKILLS_ROOT}/anytype-skill/commands/files.md — Native file upload, download, and delete${AGENTS_SKILLS_ROOT}/anytype-skill/commands/types.md — Type CRUD + templates${AGENTS_SKILLS_ROOT}/anytype-skill/commands/properties.md — Property CRUD${AGENTS_SKILLS_ROOT}/anytype-skill/commands/tags.md — Tag CRUD on select/multi-select properties${AGENTS_SKILLS_ROOT}/anytype-skill/commands/lists.md — List views, add/remove objects${AGENTS_SKILLS_ROOT}/anytype-skill/commands/members.md — Space membersUse curl via Bash to make the request. Always include auth and version headers.
Format the JSON response for readability. Summarize key fields rather than dumping raw JSON unless the user asks for it.
After completion, ask the user: "Any feedback on this run? (skip to finish)" If provided, capture it:
python3 "${AGENTS_SKILLS_ROOT}/_shared/trace_capture.py" capture \
--skill "anytype-skill" --gate "run_retrospective" --gate-type "retrospective" \
--outcome "approved" --feedback "<user's feedback>"
Autonomous code refactoring agent that rewrites messy functions, splits large files, removes duplication, improves naming, enforces structure, and preserves behavior.
Generate API integration test suites from Harnessy regression artifacts using a QA profile plus optional delivery-profile adapters.
Generate browser integration suites from Harnessy regression artifacts using a QA profile plus optional delivery-profile adapters for fixtures, routes, and helper imports.
End-to-end product development orchestrator with human-in-the-loop reviews.
Safe repo pull/push workflow that targets the repository integration branch, uses deterministic planning, and keeps PRs moving with a bounded autonomous resolution loop.
Plan, verify, and explicitly install skill and script runtime dependencies from Harnessy manifests.