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

Authoring Platform MCP Skills

by speakeasy-api in speakeasy-api/gram

A skill your agent uses when adding, editing, reviewing, testing, or locating a reviewed skill distributed with the Platform MCP plugin; triggers include "Platform MCP skill", "platformmcpskills"…

AGPL-3.0Auto-check passedAgent Workflows

Install Authoring Platform MCP Skills

skills CLI
$ npx skills add speakeasy-api/gram --skill authoring-platform-mcp-skills -a claude-code

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

GitHub CLI
$ gh skill install speakeasy-api/gram authoring-platform-mcp-skills --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/speakeasy-api/gram.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/authoring-platform-mcp-skills .claude/skills/authoring-platform-mcp-skills && 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
authoring-platform-mcp-skills
GitHub stars
273
Token cost
~2.2k tokens
SKILL.md length
947 words
Files
1
Skills in repo
40
Repo updated
First seen
Licence
AGPL-3.0

At a glance

A skill your agent uses when adding, editing, reviewing, testing, or locating a reviewed skill distributed with the Platform MCP plugin; triggers include "Platform MCP skill", "platformmcpskills"…

  • Works in 9 steps: Create… → Use a canonical lowercase kebab-case… → Include name and description frontmatter → …
  • Locating a reviewed skill distributed with the Platform MCP plugin
  • SKILL.md covers What belongs in a Platform MCP…, Source and output map, Add or edit a distributed skill and Review checklist, plus 3 more sections
  • Calls mise

What it does

Authoring Platform MCP Skills is an agent skill from speakeasy-api/gram. Use when adding, editing, reviewing, testing, or locating a reviewed skill distributed with the Platform MCP plugin; triggers include "Platform MCP skill", "platformmcpskills", "add a catalog workflow", "bundle a skill with Platform MCP", and "where should this Platform skill live?".

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol. The repository describes itself as: Securely scale AI usage across your organization. A single stack to Connect, Secure, Observe and Distribute agents, MCPs, and Skills within your company. The licence is AGPL-3.0.

When your agent uses it

  • Locating a reviewed skill distributed with the Platform MCP plugin
  • Triggers include Platform MCP skill
  • Platformmcpskills
  • Add a catalog workflow

Example prompts

  • “Platform MCP skill”
  • “platformmcpskills”
  • “add a catalog workflow”
  • “/authoring-platform-mcp-skills”

Workflow steps

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

  1. Create server/internal/plugins/platform_mcp_skills//SKILL.md.
  2. Use a canonical lowercase kebab-case directory name, at most 64 characters. The frontmatter name must exactly match the directory.
  3. Include name and description frontmatter
  4. Write for an agent using authenticated Platform MCP tools. An explicitly reviewed workflow may also use local discovery after informed…
  5. Anchor the skill in a common dashboard outcome. Preserve the dashboard's explicit target selection, secure handoffs, confirmations, and…
  6. Keep authority explicit: package installation grants no access; live OAuth, entitlement, membership, org:admin, generation, and revocation…
  7. Separate reads, user choices, secure browser handoffs, confirmation, mutation, and post-mutation verification. Never treat…
  8. Never ask for or expose API keys, passwords, tokens, OAuth codes, client secrets, secret headers, or MCP credentials. Present only…
  9. For bounded feedback, ask for consent and use send_platform_mcp_feedback; do not add the hooks-backed speakeasy-skill-feedback sidecar.

What it can do on your machine

Read from SKILL.md and the folder at commit b4c4904. 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

    Shell commands in SKILL.md call:

    • mise

    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 no API keys, tokens, secrets or passwords.

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

Context cost

Authoring Platform MCP Skills loads about 2.2k tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 947 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~79
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

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 speakeasy-api/gram at commit b4c4904, republished under its AGPL-3.0 licence (© speakeasy-api). 947 words, ~2,221 tokens.

Download SKILL.mdSave it as .claude/skills/authoring-platform-mcp-skills/SKILL.md (or your agent's skills folder).
name
authoring-platform-mcp-skills
description
Use when adding, editing, reviewing, testing, or locating a reviewed skill distributed with the Platform MCP plugin; triggers include "Platform MCP skill", "platform_mcp_skills", "add a catalog workflow", "bundle a skill with Platform MCP", and "where should this Platform skill live?".

Authoring Platform MCP skills

Platform MCP skills are first-party Speakeasy AI Control Plane (AICP) product assets, not project-owned Skill rows and not repository-agent guidance. Their single source is server/internal/plugins/platform_mcp_skills/<skill-name>/SKILL.md. The plugin generator embeds every valid directory there into every Platform MCP package.

What belongs in a Platform MCP skill

Prefer repeatable AICP workflows that a person commonly performs manually in the Speakeasy dashboard and that the authenticated Platform MCP can complete safely. Good candidates combine multiple reviewed tools into a recognizable outcome, preserve the same choices and confirmations as the dashboard, and verify the resulting live state.

Examples include selecting a reviewed MCP Catalogue entry, configuring it for an explicit project, completing secure setup, and adding the ready MCP to that project's Default plugin. A thin restatement of one tool, an internal engineering procedure, or a workflow outside the Platform MCP's reviewed capabilities does not belong here.

Use product language in every distributed skill: Speakeasy AI Control Plane, AI Control Plane, or AICP. Never expose the internal codename “Gram” in frontmatter, instructions, examples, prompts, or user-facing messages. Internal Go/TypeScript symbols and HTTP headers may retain existing contract names, but the skill must describe them in AICP terms.

Source and output map

PurposePath
Authoring source shipped to usersserver/internal/plugins/platform_mcp_skills/<skill-name>/SKILL.md
Generator and validationserver/internal/plugins/generate.go (loadPlatformMCPSkills, emitPlatformMCPSkills)
Package testsserver/internal/plugins/generate_test.go
Claude package outputspeakeasy/skills/<skill-name>/SKILL.md
Portable Agent Plugin outputagent-plugins/speakeasy/skills/<skill-name>/SKILL.md
Contributor guidance only.agents/skills/authoring-platform-mcp-skills/SKILL.md (this file)

Do not put a user-facing Platform workflow under .agents/skills/: that directory teaches contributors and coding agents how to work on this repository. It is not copied into the customer Platform Plugin.

Add or edit a distributed skill

  1. Create server/internal/plugins/platform_mcp_skills/<skill-name>/SKILL.md.
  2. Use a canonical lowercase kebab-case directory name, at most 64 characters. The frontmatter name must exactly match the directory.
  3. Include name and description frontmatter:
markdown
---
name: inspect-platform-state
description: Inspect an explicit AICP project's Platform MCP state before proposing a bounded repair.
---
  1. Write for an agent using authenticated Platform MCP tools. An explicitly reviewed workflow may also use local discovery after informed consent for its actual effects (including health-check connections and stdio process launches before filtering), with a sanitized manual-inventory alternative. Never promise side-effect-free discovery, read credential files, transfer credentials or edit local configuration. The executing client must first successfully call list_projects through its own Speakeasy connection; dashboard install intent and another client's authentication are insufficient. All management mutations still require authenticated Platform MCP tools. Name real tools exactly; verify them in server/internal/platformmcp/tool_*.go and their registration in server/internal/platformmcp/tools.go rather than inventing APIs.
  2. Anchor the skill in a common dashboard outcome. Preserve the dashboard's explicit target selection, secure handoffs, confirmations, and evidence checks rather than inventing a shortcut with weaker controls.
  3. Keep authority explicit: package installation grants no access; live OAuth, entitlement, membership, org:admin, generation, and revocation checks remain authoritative.
  4. Separate reads, user choices, secure browser handoffs, confirmation, mutation, and post-mutation verification. Never treat copy/download/install intent as runtime evidence.
  5. Never ask for or expose API keys, passwords, tokens, OAuth codes, client secrets, secret headers, or MCP credentials. Present only server-returned non-secret setup/provider URLs.
  6. For bounded feedback, ask for consent and use send_platform_mcp_feedback; do not add the hooks-backed speakeasy-skill-feedback sidecar.

Adding the directory is sufficient for distribution. Do not add another go:embed directive, skill-name constant, or renderer branch. The embedded registry loads every platform_mcp_skills/*/SKILL.md and emits the same bytes into Claude and portable Agent Plugin packages.

Show full SKILL.md (400 more words)Show less

Review checklist

  • Directory and frontmatter names match and are canonical kebab-case.
  • Description states the user outcome and when the workflow applies.
  • The outcome is a common AICP dashboard workflow, not a wrapper around one tool or an internal engineering task.
  • Shipped text uses Speakeasy AI Control Plane, AI Control Plane, or AICP—never the internal codename.
  • Every named Platform MCP tool exists, is registered, and the sequence respects its contract.
  • Exact project and target selection stay explicit; the skill does not infer scope.
  • Mutations require the same confirmation expected by the server/onboarding flow.
  • OAuth and secret entry stay in the server-returned secure browser handoff.
  • Fresh readiness is checked before distribution; final live state is rechecked afterward.
  • No organization/project identifiers, customer data, credentials, fixed environment URL, or tenant configuration is embedded.
  • Claude and Agent Plugin outputs contain byte-identical skill content and no hooks runtime or skill-feedback sidecar.
  • Do not bump platformMCPGeneratorVersion for skill text alone: embedded skill bytes already participate in the Platform package fingerprint. Bump it only for a rollout-significant generator behavior change that emitted-byte fingerprinting cannot represent.

Validation

Run focused package tests through repository-pinned tooling:

bash
mise exec -- go test ./server/internal/plugins -run 'TestGeneratePluginPackagesIncludesPlatformMCPOnlyWhenEnabled|TestGeneratePlatformMCPPluginPackageDirectDownloadsShareDefinition' -count=1

Then run the normal server gates for the complete change:

bash
hk fix
mise lint:server

For a new skill, extend TestGeneratePluginPackagesIncludesPlatformMCPOnlyWhenEnabled (or a focused neighboring test) to assert the skill appears in both package layouts with identical bytes. Add assertions for the workflow's required tool names and forbidden credential/hook material.

Initial reference skill

server/internal/plugins/platform_mcp_skills/add-mcp-from-catalog/SKILL.md mirrors the common AICP dashboard workflow represented by Platform MCP onboarding:

  1. verify authenticated discovery;
  2. search the reviewed catalog and list eligible projects;
  3. obtain exact project and candidate choices;
  4. inspect and register privately with non-secret configuration only;
  5. use secure setup/authorization handoffs;
  6. explicitly confirm identity-provider attachment when required;
  7. force fresh readiness;
  8. explicitly confirm and add the ready MCP to the selected project's existing Default plugin;
  9. recheck and report live evidence.

Use it as the pattern for authority boundaries and evidence, not as a template for unrelated workflows.

Common mistakes

  • Editing generated package output instead of platform_mcp_skills/.
  • Putting the shipped workflow in .agents/skills/, which only reaches repository contributors.
  • Reusing ordinary PluginInfo.Skills; Platform MCP skills require the reviewed generator path and package metadata.
  • Hardcoding one skill in Go, forcing every new skill to modify the generator.
  • Claiming install, OAuth intent, or a stale status proves authorization/readiness.
  • Asking the user to paste secrets into chat instead of using the secure server-returned handoff.

© speakeasy-api, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/authoring-platform-mcp-skills of speakeasy-api/gram.

Open the folder on GitHubat commit b4c4904

Compare with similar skills

Authoring Platform MCP Skills 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.

Authoring Platform MCP Skills compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Authoring Platform MCP Skills this skillspeakeasy-api/gram273—~2.2kAutomated safety check: PassAGPL-3.0
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k4 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official38k11 repos~3.1kAutomated safety check: PassApache-2.0
Crush Configurationcharmbracelet/crush29k—~3.7kAutomated safety check: PassCustom licence
Context Mode Output Sandboxmksglu/context-mode26k—~4.1kAutomated 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 63 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 4 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

  • 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 today
    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 today
    Agent WorkflowsAuto-check passed

  • Warp GUI to Agent CLI Migration

    warpdotdev/warp

    Migrates the compatible subset of settings and global file-based MCP servers from the Warp desktop app into Warp Agent CLI without exposing credentials or state.

    65k GitHub starsUsed in 1 repo~2.1k tokens
    Agent WorkflowsAuto-check passed

More from speakeasy-api/gram

All 40 skills in this repo

  • Gram Playwright CLI

    speakeasy-api/gram

    A skill your agent uses when automating the Speakeasy dashboard in a browser, capturing screenshots, inspecting pages.

    273 GitHub stars~3.4k tokensUpdated today
    Auto-check passed

  • Transactional Email

    speakeasy-api/gram

    A skill your agent uses when adding, changing, restyling, reviewing, validating, or previewing a Speakeasy transactional email, in Go or in LMX/MJML — a template<name.go, a TemplateKey constant, a…

    273 GitHub stars~4.7k tokensUpdated today
    Auto-check passed

  • Admin Shadcn

    speakeasy-api/gram

    A skill your agent uses when adding, changing, or styling UI in client/admin (the Speakeasy admin dashboard) that touches shadcn/ui — a button, dialog, table, sidebar, badge, select, tabs, tooltip…

    273 GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Clickhouse

    speakeasy-api/gram

    A skill your agent uses when changing or reviewing Speakeasy ClickHouse schemas, migrations, queries, inserts, access principals, bootstrap SQL, Cloud compatibility, partial migration failures, or…

    273 GitHub stars~3.2k tokensUpdated today
    Auto-check passed

  • Feature Flag

    speakeasy-api/gram

    A skill your agent uses when gating a feature behind a flag, dogfooding or gradually rolling out a change, choosing between productfeatures and PostHog feature flags, adding or checking a product…

    273 GitHub stars~2.6k tokensUpdated today
    Auto-check passed

  • Frontend

    speakeasy-api/gram

    A skill your agent uses when building, designing, redesigning, or reviewing any UI in the dashboard React frontend (client/dashboard, including the inlined Speakeasy Elements code) — a new page…

    273 GitHub stars~10k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Authoring Platform MCP Skills

What does Authoring Platform MCP Skills do?

A skill your agent uses when adding, editing, reviewing, testing, or locating a reviewed skill distributed with the Platform MCP plugin; triggers include "Platform MCP skill", "platformmcpskills"…. Authoring Platform MCP Skills is an agent skill from speakeasy-api/gram.".

When should I use Authoring Platform MCP Skills?

Authoring Platform MCP Skills fits situations like: locating a reviewed skill distributed with the Platform MCP plugin; triggers include Platform MCP skill; platformmcpskills; add a catalog workflow.

How do I install Authoring Platform MCP Skills in Claude Code?

Run `npx skills add speakeasy-api/gram --skill authoring-platform-mcp-skills -a claude-code`. Or copy the skill folder (.agents/skills/authoring-platform-mcp-skills in speakeasy-api/gram) into .claude/skills/authoring-platform-mcp-skills in your project. Claude Code loads it when a task matches its description.

How do I install Authoring Platform MCP Skills in Codex?

Run `npx skills add speakeasy-api/gram --skill authoring-platform-mcp-skills -a codex`. Or copy the skill folder (.agents/skills/authoring-platform-mcp-skills in speakeasy-api/gram) into .agents/skills/authoring-platform-mcp-skills in your project. Codex loads it when a task matches its description.

Can I use Authoring Platform MCP Skills 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 speakeasy-api/gram --skill authoring-platform-mcp-skills -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/authoring-platform-mcp-skills, .gemini/skills/authoring-platform-mcp-skills, .github/skills/authoring-platform-mcp-skills and .opencode/skills/authoring-platform-mcp-skills in your project.

What does Authoring Platform MCP Skills need to run?

Going by SKILL.md and its folder, Authoring Platform MCP Skills needs the command-line tools its instructions call (mise).

Does Authoring Platform MCP Skills 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 Authoring Platform MCP Skills 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 Authoring Platform MCP Skills use?

Authoring Platform MCP Skills is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Authoring Platform MCP Skills use?

About 2.2k tokens (SKILL.md is roughly 8.9k 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 Authoring Platform MCP Skills?

Skills that share tags, products or a category with Authoring Platform MCP Skills: 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 Crush Configuration (charmbracelet/crush, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Authoring Platform MCP Skills?

speakeasy-api (a GitHub organization) maintains it in speakeasy-api/gram, which has 273 GitHub stars. The repository holds 40 skills in this directory. The repository was last updated on October 10, 2026.

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