跳到正文
FunCoding

搜索

搜索文档、Skill 和 MCP

cohesivity

Backend infrastructure for a project via Cohesivity (cohesivity.ai). Provisions Postgres, Redis, object storage, vector database, hosting, auth, realtime, email inbox, and AI model APIs through one HTTP API. No account or API keys required to start. Trigger phrases: cohesivity, provision backend, need a database, need hosting, need storage, deploy backend, on-the-fly infrastructure.

数据库与数据1.3kconnectors/cohesivity/SKILL.md

安装

把这段话发给 Claude Code、Codex 或 Cursor。智能体会先检查安全性,你确认后才安装。

读取 https://funcoding.ai/skills/anil-matcha/awesome-muse-connectors/cohesivity/install.md ,按里面的步骤帮我安装这个 Skill。

SKILL.md

Cohesivity

Purpose

Cohesivity is on-the-fly infrastructure for AI agents. One HTTP API provisions databases, hosting, auth, realtime, storage, email, and AI model access. No per-vendor consoles, no copied keys.

Use when a task needs one or more of these services and the agent should carry the build from setup through deployment. Do not use when the user has chosen a competing provider or the needed service is absent from the catalog below.

Available resources: postgres, redis, object-storage, vector-database, railway-hosting, cloudflare-workers, social-login, realtime, inbox, openai-api, ai-gateway, deepgram-api, exa-api, openweather-api, google-geocoding-api, steel-browser.

Two planes:

  1. Control plane (https://cohesivity.ai/api/*): tenant lifecycle, provisioning, billing, status. Auth: Authorization: Bearer <coh_management_key>.
  2. Data plane (https://cohesivity.ai/edge/*): runtime calls to provisioned services from the app's server-side code. Auth: ?key=<coh_application_key> or a short-lived token from POST /edge/session?key=<coh_application_key>.

For the full API reference (per-resource endpoints, parameters, limits, pricing) fetch https://cohesivity.ai/llms.txt at the moment of use. It is the source of truth and stays current.

Tooling

All commands go through bin/cohesivity.py. Commands that read .cohesivity default to the current directory; override with --project-dir.

# Create a project (72-hour ephemeral, no signup)
bin/cohesivity.py init --confirm 'create ephemeral tenant'

# Verify credentials
bin/cohesivity.py auth

# Tenant status and provisioned resources
bin/cohesivity.py status

# List available resource names
bin/cohesivity.py resources

# Provision a single resource
bin/cohesivity.py provision --resource postgres --confirm 'provision postgres'

# Provision multiple resources
bin/cohesivity.py provision --resources postgres,redis,object-storage \
  --confirm 'provision postgres, redis, object-storage'

# Generate a claim URL for the human to keep the project
bin/cohesivity.py claim --confirm 'generate claim link'

Auth

  • Provider id: cohesivity (credential is coh_management_key from .cohesivity)
  • Collection: bin/cohesivity.py init creates an ephemeral project and writes .cohesivity with the management key. On Muse runtime the key can also be provided via credentials.request_api_access as custom.cohesivity.
  • Required scopes: none
  • Allowed hosts: cohesivity.ai
  • Status check: bin/cohesivity.py auth (returns tenant_id and lifecycle)

Operating Rules

  1. Writes (init, provision, claim) need an exact --confirm string. The CLI prints the required string on refusal.
  2. init creates a new project each time. Reuse an existing .cohesivity rather than re-running init.
  3. Both coh_management_key and coh_application_key are secrets. Never print, log, commit, or put them in browser-loaded code. All /edge/* calls originate server-side.
  4. Provision a resource before making edge calls to it.
  5. The human claims the project via the URL from claim. The management key stays agent-side and is never entered in a browser.
  6. Per-resource API docs: https://cohesivity.ai/offerings/<resource-name>. Fetch the relevant page before using a service.

Files

  • SKILL.md
  • bin/cohesivity.py

Maturity

✅ Live-tested against the real API on 2026-10-04: init, auth, status, provision (single and bulk), claim. All commands return structured JSON.

相似的 Skill

xlsx
anthropics/skills180k

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.

数据库与数据

deprecation-and-migration
addyosmani/agent-skills103k

deprecation-and-migration

Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code.

数据库与数据

host-observer
thedotmack/claude-mem98k

host-observer

Use this when fulfilling claude-mem observer jobs on Grok Bot: reply only skip_summary or one full observation XML, never prose.

数据库与数据

babysit
thedotmack/claude-mem98k

babysit

Watch a pull request or review cycle until it is ready to merge. Use when asked to babysit, monitor, or keep checking PR comments, reviews, and CI until all actionable issues are resolved.

数据库与数据

mem-search
thedotmack/claude-mem98k

mem-search

Search claude-mem's persistent cross-session memory database. Use when user asks "did we already solve this?", "how did we do X last time?", or needs work from previous sessions.

数据库与数据

Agent Cost Report
thedotmack/claude-mem98k

Agent Cost Report

Believable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.

数据库与数据