New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Customize an Installed Capability

by holaboss-ai in holaboss-ai/holaOS

Edits an already-installed workspace capability's manifest to add an MCP server, a skill, an integration or agent guidance, then reinstalls it so the change takes effect on the next run.

Custom licenceAuto-check passedAgent Workflows

Install Customize an Installed Capability

skills CLI
$ npx skills add holaboss-ai/holaOS --skill customize-capability -a claude-code

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

GitHub CLI
$ gh skill install holaboss-ai/holaOS customize-capability --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/holaboss-ai/holaOS.git skills-src && mkdir -p .claude/skills && cp -r skills-src/runtime/harnesses/src/embedded-skills/customize-capability .claude/skills/customize-capability && 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
customize-capability
GitHub stars
11k
Token cost
~815 tokens
SKILL.md length
358 words
Files
1
Skills in repo
30
Repo updated
First seen
Licence
Custom licence

At a glance

Edits an already-installed workspace capability's manifest to add an MCP server, a skill, an integration or agent guidance, then reinstalls it so the change takes effect on the next run.

  • Works in 5 steps: Identify the capability id from the… → Read the current state → Apply the change (see "Adding an MCP… → …
  • Adding a new MCP server's tools to an existing capability
  • SKILL.md covers Workflow, Adding an MCP server and After installing
  • Needs SOME_TOKEN

What it does

A capability's source of truth is its capability.yaml manifest; re-installing reads that manifest and upserts the capability in place without ever creating a duplicate. The skill identifies the capability id from the request, edits the manifest directly if it already exists on disk, or, if the capability came from a catalog install, first reconstructs its current skills, integrations and agent_prompt so nothing is lost before adding the requested change on top.

For the common case of adding an MCP server, it adds an mcp block naming a unique server id, either a remote HTTP or SSE endpoint with a url or a local subprocess with a command, and a tools list naming exactly which tools to expose; authentication goes in headers for a remote server or environment for a local one, and either can reference a runtime environment variable instead of a hard-coded secret. After editing, the capability_install tool re-reads and upserts the manifest, rejecting a malformed one with a precise error, and the user is told the new tools only appear on their next message, since the runtime compiles MCP servers at the start of a run.

When your agent uses it

  • Adding a new MCP server's tools to an existing capability
  • Adding a skill or integration to a capability already installed from the catalog
  • Updating a capability's agent guidance without losing its existing configuration

Example prompts

  • “Add an MCP server for our internal ticketing API to the support capability.”
  • “Give the research capability a local MCP server that reads from our document store.”
  • “Update the writing capability's agent prompt without dropping its current skills.”

Requirements

  • A workspace with the capability_install tool

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Identify the capability id from the user's request.
  2. Read the current state
  3. Apply the change (see "Adding an MCP server" for the common case).
  4. Call the capability_install tool with capability_id: .
  5. Tell the user the change takes effect on the next agent run: the runtime

What it can do on your machine

Read from SKILL.md and the folder at commit 4684714. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml).

    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:

    • SOME_TOKEN

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

Context cost

Customize an Installed Capability loads about 815 tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 358 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~60
When it runs · the whole SKILL.md, loaded when a task matches
~815

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 358 words (~815 tokens).

“Modify a capability that is already installed in this workspace. The most common request is giving it an MCP server so its agent gains new tools, but the same flow covers adding skills, integrations, or guidance.”

— opening of SKILL.md by holaboss-ai, Custom licence
name
customize-capability

Read the full SKILL.md on GitHub

Files

Just SKILL.md in runtime/harnesses/src/embedded-skills/customize-capability of holaboss-ai/holaOS.

Open the folder on GitHubat commit 4684714

Compare with similar skills

Customize an Installed Capability 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.

Customize an Installed Capability compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Customize an Installed Capability this skillholaboss-ai/holaOS11k—~815Automated safety check: PassCustom licence
MCP Server Builderanthropics/skills180k64 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official38k11 repos~3.1kAutomated safety check: PassApache-2.0
Fastmcp Client CLIPrefectHQ/fastmcp28k1 repos~823Automated safety check: PassApache-2.0
Crush Configurationcharmbracelet/crush29k—~3.7kAutomated safety check: PassCustom licence

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 64 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed

  • Fastmcp Client CLI

    PrefectHQ/fastmcp

    Query and invoke tools on MCP servers using fastmcp list and fastmcp call.

    28k GitHub starsUsed in 1 repo~823 tokens
    Agent WorkflowsAuto-check passed

  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Context Mode Output Sandbox

    mksglu/context-mode

    Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.

    26k GitHub stars~4.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from holaboss-ai/holaOS

All 30 skills in this repo

  • Interface Design for Dashboards and Apps

    holaboss-ai/holaOS

    Pushes an agent past generic defaults when designing dashboards, admin panels, SaaS apps and tools, with attention to structure, type, navigation and how data is shown.

    11k GitHub starsUsed in 3 repos~6k tokens
    Auto-check passed

  • Dashboard Builder for holaOS

    holaboss-ai/holaOS

    Builds the visual layer of a holaOS dashboard app with TanStack Start and @holaboss/ui, starting from a bundled reference instead of a blank page.

    11k GitHub stars~6.3k tokensUpdated 1 mo ago
    Auto-check passed

  • Capability Creator

    holaboss-ai/holaOS

    Bundles one or more existing skills and the integrations they need into a single named, installable capability.

    11k GitHub stars~385 tokensUpdated 1 mo ago
    Auto-check passed

  • Efficient Embedded Browser Loop

    holaboss-ai/holaOS

    Guidelines for driving a workspace's embedded browser with the fewest tool calls, smallest state reads and no needless screenshots or waits.

    11k GitHub stars~736 tokensUpdated 1 mo ago
    Auto-check passed

  • Browser QA Repro Loop

    holaboss-ai/holaOS

    Validates or debugs a workflow in the embedded browser with a reproducible, evidence-first loop that separates product failures from wait or locator problems.

    11k GitHub stars~712 tokensUpdated 1 mo ago
    Auto-check passed

  • holaOS MCP Configurator

    holaboss-ai/holaOS

    Adds, removes or updates MCP servers in a holaOS workspace by editing workspace.yaml in the mcp_registry format, with rules for headers, local servers and tool allowlists.

    11k GitHub stars~874 tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about Customize an Installed Capability

What does Customize an Installed Capability do?

Edits an already-installed workspace capability's manifest to add an MCP server, a skill, an integration or agent guidance, then reinstalls it so the change takes effect on the next run. yaml manifest; re-installing reads that manifest and upserts the capability in place without ever creating a duplicate. The skill identifies the capability id from the request, edits the manifest directly if it already exists on disk, or, if the capability came from a catalog install, first reconstructs its current skills, integrations and agent_prompt so nothing is lost before adding the requested change on top.

When should I use Customize an Installed Capability?

Customize an Installed Capability fits situations like: adding a new MCP server's tools to an existing capability; adding a skill or integration to a capability already installed from the catalog; updating a capability's agent guidance without losing its existing configuration.

How do I install Customize an Installed Capability in Claude Code?

Run `npx skills add holaboss-ai/holaOS --skill customize-capability -a claude-code`. Or copy the skill folder (runtime/harnesses/src/embedded-skills/customize-capability in holaboss-ai/holaOS) into .claude/skills/customize-capability in your project. Claude Code loads it when a task matches its description.

How do I install Customize an Installed Capability in Codex?

Run `npx skills add holaboss-ai/holaOS --skill customize-capability -a codex`. Or copy the skill folder (runtime/harnesses/src/embedded-skills/customize-capability in holaboss-ai/holaOS) into .agents/skills/customize-capability in your project. Codex loads it when a task matches its description.

Can I use Customize an Installed Capability 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 holaboss-ai/holaOS --skill customize-capability -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/customize-capability, .gemini/skills/customize-capability, .github/skills/customize-capability and .opencode/skills/customize-capability in your project.

What does Customize an Installed Capability need to run?

Going by SKILL.md and its folder, Customize an Installed Capability needs credentials named SOME_TOKEN. Our summary lists: A workspace with the capability_install tool.

Does Customize an Installed Capability 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 Customize an Installed Capability 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 Customize an Installed Capability use?

Customize an Installed Capability has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Customize an Installed Capability use?

About 815 tokens (SKILL.md is roughly 3.3k 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 Customize an Installed Capability?

Skills that share tags, products or a category with Customize an Installed Capability: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Fastmcp Client CLI (PrefectHQ/fastmcp, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Customize an Installed Capability?

holaboss-ai (a GitHub organization) maintains it in holaboss-ai/holaOS, which has 11,451 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on August 21, 2026.

Source: holaboss-ai/holaOS on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.