Agent skill

Apikeys UI

by LeoYeAI in LeoYeAI/openclaw-master-skills

Vault-backed API Keys management for OpenClaw. An agent skill from LeoYeAI/openclaw-master-skills.

MITAuto-check passed

Install Apikeys UI

skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill apikeys-ui -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LeoYeAI/openclaw-master-skills apikeys-ui --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/api-key-ui-tab .claude/skills/apikeys-ui && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
apikeys-ui
GitHub stars
2.2k
Token cost
~3.8k tokens
SKILL.md length
1,442 words
Files
10
Skills in repo
1,235
Repo updated
First seen
Licence
MIT

At a glance

Vault-backed API Keys management for OpenClaw. An agent skill from LeoYeAI/openclaw-master-skills.

  • Works in 11 steps: Vault-Backed Storage → One-Click Migration → Dynamic Key Discovery → …
  • SKILL.md covers Status: ✅ Active, Features, Architecture and Key Design Decisions, plus 1 more section
  • Runs TypeScript scripts from its folder; needs OPENAI_API_KEY and ANTHROPIC_API_KEY

What it does

Apikeys UI is an agent skill from LeoYeAI/openclaw-master-skills. Vault-backed API Keys management for OpenClaw. Secure file-based secret storage with one-click migration from plaintext config, dynamic key discovery, vault key selector for skills, manual secret creation, and plugin-registered settings tab.

Its SKILL.md is about 3.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files (for example `INSTALL_INSTRUCTIONS.md`, `_meta.json` and `reference/apikeys-controller.ts`).

The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.

Example prompts

  • “/apikeys-ui”

Requirements

  • Node.js
  • A credential in OPENAI_API_KEY
  • A credential in ANTHROPIC_API_KEY

Workflow steps

11 steps, taken from the step headings in SKILL.md.

  1. Vault-Backed Storage
  2. One-Click Migration
  3. Dynamic Key Discovery
  4. Vault Status Banner
  5. Key Status Badges
  6. Vault-Only Keys Section
  7. Manual "+ Add Secret" Form
  8. Restart Notification Banner
  9. Skills Vault Key Selector
  10. Skills Expanded by Default
  11. Auth Profiles Display

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (TypeScript), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • OPENAI_API_KEY
    • ANTHROPIC_API_KEY
    • GOOGLE_API_KEY
    • GEMINI_API_KEY
    • BRAVE_API_KEY
    • ELEVENLABS_API_KEY
    • DEEPGRAM_API_KEY
    • OPENROUTER_API_KEY
    • GROQ_API_KEY
    • FIREWORKS_API_KEY
    • MISTRAL_API_KEY
    • XAI_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Apikeys UI loads about 3.8k tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 1,442 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~63
When it runs · the whole SKILL.md, loaded when a task matches
~3.8k

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.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated 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); files beside SKILL.md are not scanned.

SKILL.md

The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 1,442 words, ~3,819 tokens.

Download SKILL.mdSave it as .claude/skills/apikeys-ui/SKILL.md (or your agent's skills folder). This skill also uses 9 other files; get the full folder from GitHub.
name
apikeys-ui
description
Vault-backed API Keys management for OpenClaw. Secure file-based secret storage with one-click migration from plaintext config, dynamic key discovery, vault key selector for skills, manual secret creation, and plugin-registered settings tab.
version
3.0.0
author
OpenClaw Community

Vault Enhancements w/ UI v3.0.0

Vault-backed API key management for the OpenClaw Control dashboard. Keys are stored in a secure file (~/.openclaw/secrets.json, mode 0600) and referenced via OpenClaw's built-in Secrets System. The AI agent never sees your keys.

Status: ✅ Active

ComponentStatus
Vault File Storage✅ Working
Secret References (SecretRef)✅ Working
Dynamic Key Discovery✅ Working
One-Click Migration✅ Working
Plugin-Registered Tab✅ Working
Vault Status Banner✅ Working
Key Status Badges✅ Working
Vault-Only Keys Section✅ Working
Manual "+ Add Secret" Form✅ Working
Restart Notification Banner✅ Working
Skills Vault Key Selector✅ Working
Skills Inline Key Creation✅ Working
Auth Profiles Display✅ Working

Features

1. Vault-Backed Storage

Keys are stored in ~/.openclaw/secrets.json (file permissions 0600). When you save a key, the UI:

  1. Writes the value to the vault file
  2. Configures the file secret provider in openclaw.json (if not already present)
  3. Replaces the plaintext config value with a SecretRef object
  4. Shows a restart notification — user must restart gateway for changes to take effect

Config before migration:

json
{
  "env": {
    "OPENAI_API_KEY": "sk-proj-abc123..."
  }
}

Config after migration:

json
{
  "env": {
    "OPENAI_API_KEY": { "source": "file", "provider": "default", "id": "/OPENAI_API_KEY" }
  },
  "secrets": {
    "providers": {
      "default": { "source": "file", "path": "~/.openclaw/secrets.json", "mode": "json" }
    },
    "defaults": { "file": "default" }
  }
}

Vault file (~/.openclaw/secrets.json):

json
{
  "OPENAI_API_KEY": "sk-proj-abc123..."
}
2. One-Click Migration

The "🔒 Migrate to Vault" button appears when plaintext keys are detected. It:

  • Scans openclaw.json for all plaintext API key values
  • Moves each to the vault file
  • Replaces with SecretRef objects in config
  • Auto-configures the file provider if needed
  • Reports what was migrated
3. Dynamic Key Discovery

The UI automatically scans the entire config for API keys — no hardcoded list.

Detection patterns: apiKey, api_key, token, secret, *_KEY, *_TOKEN, *_SECRET

Where it looks:

  • env.* — Environment variables
  • skills.entries.*.apiKey — Skill-specific keys
  • messages.tts.*.apiKey — TTS provider keys
  • Any nested config path

Known providers get friendly names, descriptions, and "Get key ↗" links:

ProviderEnv Key
AnthropicANTHROPIC_API_KEY
OpenAIOPENAI_API_KEY
Google / GeminiGOOGLE_API_KEY / GEMINI_API_KEY
Brave SearchBRAVE_API_KEY
ElevenLabsELEVENLABS_API_KEY
DeepgramDEEPGRAM_API_KEY
OpenRouterOPENROUTER_API_KEY
GroqGROQ_API_KEY
FireworksFIREWORKS_API_KEY
MistralMISTRAL_API_KEY
xAI (Grok)XAI_API_KEY
PerplexityPERPLEXITY_API_KEY
GitHubGITHUB_TOKEN
Hume AIHUME_API_KEY / HUME_SECRET_KEY
4. Vault Status Banner

Top of the page shows:

  • 🔒 Vault Active (green) — All keys in vault, provider configured
  • ⚠️ X Plaintext Keys Detected (yellow) — Migration recommended
5. Key Status Badges

Each key row shows:

  • VAULT (green) — Stored in secure vault file
  • PLAINTEXT (yellow) — Still in config as raw string
  • NOT SET (grey) — Not configured
6. Vault-Only Keys Section

Keys stored in the vault that aren't referenced by any config path are displayed in a dedicated "Vault-Only Keys" card. These are keys created manually or by skills that don't have a corresponding env/config entry. Each shows:

  • 🔒 icon with the key name (monospace)
  • Masked value preview
  • Delete button
7. Manual "+ Add Secret" Form

The Vault tab header includes a "+ Add Secret" button that expands an inline form:

  • KEY_NAME input (monospace, UPPER_SNAKE_CASE recommended)
  • Secret value input (password field)
  • Save / Cancel buttons
  • Writes to vault with envEntry: false — no config entry created, no restart triggered
  • Key appears immediately in the "Vault-Only Keys" section
8. Restart Notification Banner

When a vault write triggers a config change, a yellow warning banner appears:

⚠ New secrets require a gateway restart to take effect. [Restart Now]

The banner persists until the user clicks "Restart Now" or refreshes. This replaces the previous auto-reload behavior that caused unexpected gateway restarts.

9. Skills Vault Key Selector

On the Skills tab, skills that declare a primaryEnv get a vault key selector instead of a raw password input:

When unlinked:

  • Dropdown shows all vault keys with 🔒 icons
  • "Select vault key for ENV_NAME…" placeholder
  • Selecting a key writes a SecretRef to skills.entries.<key>.apiKey in config
  • "+ Add new vault key…" option opens inline creation form

When linked:

  • Shows 🔒 KEY_NAME with an "Unlink" button
  • Unlink removes the SecretRef from config

Inline key creation:

  • KEY_NAME + Secret value fields
  • "Save & Link" creates the vault key and links it to the skill in one step
  • Key also appears in the Vault tab's vault-only keys section
10. Skills Expanded by Default

All skill groups (workspace, built-in, managed) render expanded (<details open>) for better discoverability. Previously workspace and built-in were collapsed by default.

11. Auth Profiles Display

Auth profile keys (from auth-profiles.json) that are stored in the vault are listed with their status. Backend RPCs support listing, error reset, and deletion.

Architecture

Security Model
┌──────────────────────────────────────────────────────────┐
│  Browser                                                  │
│  ┌──────────────────────────────────────────────────┐    │
│  │  Vault Tab                                        │    │
│  │  ┌──────────────────────────────────────────┐    │    │
│  │  │ OpenAI: [••••••••••] [Save] [✕]  🟢VAULT │    │    │
│  │  │ Anthropic: [        ] [Save]     ⚪NOT SET│    │    │
│  │  │ + Add Secret  [KEY_NAME] [value] [Save]   │    │    │
│  │  └──────────────────────────────────────────┘    │    │
│  │                                                   │    │
│  │  Skills Tab                                       │    │
│  │  ┌──────────────────────────────────────────┐    │    │
│  │  │ whisper-api: 🔒 OPENAI_API_KEY  [Unlink] │    │    │
│  │  │ sag:         [Select vault key ▾]         │    │    │
│  │  └──────────────────────────────────────────┘    │    │
│  └──────────────────────────────────────────────────┘    │
│                           │                               │
│                           ▼ (direct RPC, not via agent)   │
└───────────────────────────┼───────────────────────────────┘
                            │
                    ┌───────▼───────┐
                    │   Gateway     │
                    │ secrets.write │
                    │ skills.update │
                    └──┬─────────┬──┘
                       │         │
              ┌────────▼──┐  ┌──▼────────────┐
              │ secrets.   │  │ openclaw.json  │
              │ json       │  │ (SecretRef     │
              │ (0600)     │  │  objects only) │
              └────────────┘  └────────────────┘
Backend RPCs
MethodDescription
secrets.statusVault file status, key count, plaintext count
secrets.listList secret IDs with masked values
secrets.writeStore key in vault + optionally update config with SecretRef. envEntry param (default true) controls whether an env block entry is created. Returns restartNeeded flag instead of auto-reloading.
secrets.deleteRemove from vault + config
secrets.migrateBatch-migrate all plaintext keys to vault
secrets.authProfiles.listList auth profile keys with vault status
secrets.authProfiles.resetErrorsReset auth profile error state
secrets.authProfiles.deleteDelete an auth profile
skills.updateUpdated with vaultKeyId param — writes a SecretRef to skills.entries.<key>.apiKey or unlinks (empty string)
Skills-Status Integration

SkillStatusEntry includes a vaultKeyId field that reads the raw config JSON (not the runtime-resolved config where SecretRefs are replaced with resolved strings). This is done via extractVaultKeyIdFromConfig() which reads and caches openclaw.json directly, checking for SecretRef objects in skills.entries.<key>.apiKey.

Restart Behavior

No auto-restart on vault save. Previously, secrets.write called reloadSecrets() which could trigger a gateway restart. Now:

  • Vault-only saves (envEntry: false) don't touch config — no restart needed
  • Config-touching saves return restartNeeded: true — UI shows a restart banner
  • Skills vault linking writes to config via writeConfigFile() — triggers the config file watcher which causes a gateway restart (inherent to the config watcher system)
Show full SKILL.md (575 more words)Show less
OpenClaw Secrets System Integration

This skill uses OpenClaw's built-in Secrets System (src/secrets/):

  • File provider: { source: "file", path: "~/.openclaw/secrets.json", mode: "json" }
  • SecretRef format: { source: "file", provider: "default", id: "/<KEY_NAME>" }
  • Runtime resolution: prepareSecretsRuntimeSnapshot() resolves all refs at gateway startup
  • Security: File permissions checked (0600), ownership verified, path guards

The secrets system also supports env and exec providers for advanced setups (e.g., environment variables, external vault commands). The file provider is the default for this UI.

Files Modified (Source Locations in OpenClaw Repo)
FilePurpose
src/gateway/server-methods/secrets.tsVault RPCs (status, list, write, delete, migrate, authProfiles)
src/gateway/server-methods/skills.tsSkills update with vaultKeyId param
src/gateway/server-methods/plugins-ui.tsPlugin view registration
src/gateway/protocol/schema/agents-models-skills.tsvaultKeyId in SkillsUpdateParamsSchema
src/agents/skills-status.tsvaultKeyId field on SkillStatusEntry, raw config reader
ui/src/ui/controllers/apikeys.tsVault-aware state, addVaultSecret, loadVaultOnlyKeys
ui/src/ui/controllers/skills.tsVaultKeyEntry type, loadVaultKeys, linkSkillToVaultKey, addVaultKeyAndLink
ui/src/ui/views/apikeys.tsVault UI (banners, badges, migration, add form, vault-only keys, restart banner)
ui/src/ui/views/skills.tsVault key selector dropdown, inline creation, expanded groups
ui/src/ui/app.tsState properties (vault, restart, skill key management)
ui/src/ui/app-render.tsProp wiring for vault and skills
ui/src/ui/app-settings.tsTab load triggers for vault keys
ui/src/ui/types.tsvaultKeyId on SkillStatusEntry
ui/src/ui/navigation.tsVault tab (lock icon), removed 1password/discord standalone tabs
Reference Files
apikeys-ui/
├── SKILL.md                              # This file
├── INSTALL_INSTRUCTIONS.md               # Step-by-step installation (legacy)
└── reference/
    ├── apikeys-controller.ts             # UI controller (vault tab)
    ├── apikeys-views.ts                  # UI view (vault tab)
    ├── secrets-rpc.ts                    # Backend vault RPCs
    ├── skills-controller.ts              # UI controller (skills vault integration)
    ├── skills-views.ts                   # UI view (vault key selector)
    ├── skills-status.ts                  # Backend skill status with vaultKeyId
    └── skills-rpc.ts                     # Backend skills update RPC

Key Design Decisions

  1. No auto-restart on save — secrets.write no longer calls reloadSecrets(). A restart banner with "Restart Now" button lets the user decide when to restart.

  2. Vault-only keys — Keys created with envEntry: false don't appear in config. A separate secrets.list call finds all vault entries and shows orphan keys in a dedicated section.

  3. Raw config reading for vaultKeyId — The runtime resolves SecretRefs to strings, so loadConfig() returns resolved values. extractVaultKeyIdFromConfig() reads the raw JSON file directly (with mtime caching) to detect SecretRef objects.

  4. Skills expanded by default — All <details> groups render open for better UX. Collapsed-by-default hid skills that needed configuration.

  5. Skills use vault references, not plaintext — Skills with primaryEnv get a vault key selector dropdown instead of a password input. Linking writes a SecretRef to skills.entries.<key>.apiKey in config.

  6. Inline key creation from skills — "+ Add new vault key…" in the skills dropdown creates a vault entry and links it in one step, reducing friction.

Changelog

v3.0.0
  • Manual "+ Add Secret" form in Vault tab header — create vault keys without config entries
  • Vault-Only Keys section — shows keys in vault not referenced by config
  • Restart notification banner — yellow warning with "Restart Now" button replaces auto-reload
  • Skills vault key selector — dropdown replaces raw password input for skills with primaryEnv
  • Skills inline key creation — "+ Add new vault key…" creates and links in one step
  • Skills expanded by default — all groups open, no more collapsed-by-default
  • vaultKeyId on SkillStatusEntry — reads raw config JSON to detect SecretRef objects
  • envEntry param on secrets.write — controls whether an env block entry is created
  • vaultKeyId param on skills.update — writes SecretRef or unlinks skill from vault key
v2.0.0
  • Vault-backed storage: Keys stored in ~/.openclaw/secrets.json (mode 0600) instead of plaintext config
  • SecretRef integration: Config values replaced with OpenClaw SecretRef objects pointing to vault
  • One-click migration: "Migrate to Vault" batch-migrates all plaintext keys
  • Vault status banner: Green (all secure) or yellow warning (plaintext detected)
  • Key badges: VAULT / PLAINTEXT / NOT SET per key
  • New RPCs: secrets.status, secrets.list, secrets.write, secrets.delete, secrets.migrate
  • Plugin UI registration: Moved from old nav to plugin architecture (settings group, position 1)
  • Auto-provider config: Saving a key auto-configures the file secret provider if not present
v1.1.0
  • Dynamic key discovery — scans entire config instead of hardcoded list
  • Auto-grouping by category (Environment / Skills / Other)
  • Common env keys shown even if not configured
v1.0.0
  • Initial release with hardcoded provider slots
  • Save/Clear functionality via config.patch

© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 9 other files in skills/api-key-ui-tab of LeoYeAI/openclaw-master-skills.

  • SKILL.md
  • INSTALL_INSTRUCTIONS.md
  • _meta.json
  • reference/apikeys-controller.ts
  • reference/apikeys-views.ts
  • reference/secrets-rpc.ts
  • reference/skills-controller.ts
  • reference/skills-rpc.ts
  • reference/skills-status.ts
  • reference/skills-views.ts

Open the folder on GitHubat commit e5199b5

Compare with similar skills

Apikeys UI 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.

Apikeys UI compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Apikeys UI this skillLeoYeAI/openclaw-master-skills2.2k—~3.8kAutomated safety check: PassMIT
Implementing API Key Security Controlsmukul975/Anthropic-Cybersecurity-Skills34k—~4kAutomated safety check: PassApache-2.0
Container Security Hardeningsickn33/agentic-awesome-skills47k1 repos~1kAutomated safety check: NotesMIT
Azure Security Keyvault Keys Javamicrosoft/skills3.1k5 repos~2.9kAutomated safety check: PassMIT
Azure Security Keyvault Keys Dotnetmicrosoft/skills3.1k5 repos~3.1kAutomated safety check: PassMIT
Security Scanaffaan-m/ECC276k5 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Implementing API Key Security Controls

    mukul975/Anthropic-Cybersecurity-Skills

    Implements secure API key generation with sufficient entropy, server-side hashing (SHA-256/bcrypt) instead of plaintext storage, per-key scoping to endpoints/IPs/rate limits, zero-downtime rotation…

    34k GitHub stars~4k tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed
  • Container Security Hardening

    sickn33/agentic-awesome-skills

    Harden Docker/container images and runtime deployments with secure base images, non-root users, CVE scanning, SBOM/signing, seccomp/AppArmor, and Kubernetes pod security controls.

    47k GitHub starsUsed in 1 repo~1k tokens
    SecurityAuto-check: notes
  • Official

    Azure Key Vault Keys Java SDK for cryptographic key management.

    3.1k GitHub starsUsed in 5 repos~2.9k tokens
    SecurityAuto-check passed
  • Official

    Azure Key Vault Keys SDK for .NET. An agent skill from microsoft/skills.

    3.1k GitHub starsUsed in 5 repos~3.1k tokens
    SecurityAuto-check passed
  • Security Scan

    affaan-m/ECC

    Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield.

    276k GitHub starsUsed in 5 repos~1.1k tokens
    Agent WorkflowsAuto-check passed
  • Quarkus Security

    affaan-m/ECC

    Quarkus security implementation patterns: JWT and OIDC authentication, @RolesAllowed RBAC and SecurityIdentity checks, Bean Validation and custom validators, parameterized Panache queries, BCrypt…

    276k GitHub starsUsed in 1 repo~3.1k tokens
    Backend & APIsAuto-check passed

More from LeoYeAI/openclaw-master-skills

All 1,235 skills in this repo
  • DevOps Pipeline Management

    LeoYeAI/openclaw-master-skills

    Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.

    2.2k GitHub stars~4.2k tokensUpdated 2 mo ago
    Auto-check: notes
  • Feishu Document Collaboration

    LeoYeAI/openclaw-master-skills

    Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.

    2.2k GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed
  • Files Memory System

    LeoYeAI/openclaw-master-skills

    Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.

    2.2k GitHub stars~3.8k tokensUpdated 2 mo ago
    Auto-check passed
  • GEO-Claw AI Visibility Agent

    LeoYeAI/openclaw-master-skills

    Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.

    2.2k GitHub stars~4.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Google Workspace CLI

    LeoYeAI/openclaw-master-skills

    Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.

    2.2k GitHub stars~2.6k tokensUpdated 2 mo ago
    Auto-check: notes
  • HealthFit Health Advisors

    LeoYeAI/openclaw-master-skills

    Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.

    2.2k GitHub stars~4.4k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Apikeys UI

What does Apikeys UI do?

Vault-backed API Keys management for OpenClaw. An agent skill from LeoYeAI/openclaw-master-skills. Apikeys UI is an agent skill from LeoYeAI/openclaw-master-skills. Vault-backed API Keys management for OpenClaw.

How do I install Apikeys UI in Claude Code?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill apikeys-ui -a claude-code`. Or copy the skill folder (skills/api-key-ui-tab in LeoYeAI/openclaw-master-skills) into .claude/skills/apikeys-ui in your project. Claude Code loads it when a task matches its description.

How do I install Apikeys UI in Codex?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill apikeys-ui -a codex`. Or copy the skill folder (skills/api-key-ui-tab in LeoYeAI/openclaw-master-skills) into .agents/skills/apikeys-ui in your project. Codex loads it when a task matches its description.

Can I use Apikeys UI in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill apikeys-ui -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/apikeys-ui, .gemini/skills/apikeys-ui, .github/skills/apikeys-ui and .opencode/skills/apikeys-ui in your project.

What does Apikeys UI need to run?

Going by SKILL.md and its folder, Apikeys UI needs TypeScript for the scripts in its folder and credentials named OPENAI_API_KEY, ANTHROPIC_API_KEY, GOOGLE_API_KEY and GEMINI_API_KEY. Our summary lists: Node.js; A credential in OPENAI_API_KEY; A credential in ANTHROPIC_API_KEY.

Does Apikeys UI access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Apikeys UI safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Apikeys UI use?

Apikeys UI is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Apikeys UI use?

About 3.8k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Apikeys UI?

Skills that share tags, products or a category with Apikeys UI: Implementing API Key Security Controls (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Container Security Hardening (sickn33/agentic-awesome-skills, 47k stars), Azure Security Keyvault Keys Java (microsoft/skills, 3.1k stars) and Azure Security Keyvault Keys Dotnet (microsoft/skills, 3.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Apikeys UI?

LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.

Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.