MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
Diagnose why pi-flows, the Anthropic-messages bridge, model resolution, a pi install, a peer, a plugin/bridge, or a build/reload is broken in the pi-agent-dashboard.
MITAuto-check passed
Install Doctor
$ npx skills add BlackBeltTechnology/pi-agent-dashboard --skill doctor -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install BlackBeltTechnology/pi-agent-dashboard doctor --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboard.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/extension/.pi/skills/doctor .claude/skills/doctor && rm -rf skills-srcUse ~/.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/
Install the "doctor" agent skill from https://github.com/BlackBeltTechnology/pi-agent-dashboard/tree/develop/packages/extension/.pi/skills/doctor into .claude/skills/doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doctor", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/BlackBeltTechnology/pi-agent-dashboard/tree/develop/packages/extension/.pi/skills/doctorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add BlackBeltTechnology/pi-agent-dashboard --skill doctor -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install BlackBeltTechnology/pi-agent-dashboard doctor --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboard.git skills-src && mkdir -p .agents/skills && cp -r skills-src/packages/extension/.pi/skills/doctor .agents/skills/doctor && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "doctor" agent skill from https://github.com/BlackBeltTechnology/pi-agent-dashboard/tree/develop/packages/extension/.pi/skills/doctor into .agents/skills/doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doctor", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add BlackBeltTechnology/pi-agent-dashboard --skill doctor -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install BlackBeltTechnology/pi-agent-dashboard doctor --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboard.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/packages/extension/.pi/skills/doctor .cursor/skills/doctor && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "doctor" agent skill from https://github.com/BlackBeltTechnology/pi-agent-dashboard/tree/develop/packages/extension/.pi/skills/doctor into .cursor/skills/doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doctor", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/BlackBeltTechnology/pi-agent-dashboard.git --path packages/extension/.pi/skills/doctor--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add BlackBeltTechnology/pi-agent-dashboard --skill doctor -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install BlackBeltTechnology/pi-agent-dashboard doctor --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboard.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/packages/extension/.pi/skills/doctor .gemini/skills/doctor && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "doctor" agent skill from https://github.com/BlackBeltTechnology/pi-agent-dashboard/tree/develop/packages/extension/.pi/skills/doctor into .gemini/skills/doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doctor", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install BlackBeltTechnology/pi-agent-dashboard doctorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add BlackBeltTechnology/pi-agent-dashboard --skill doctor -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboard.git skills-src && mkdir -p .github/skills && cp -r skills-src/packages/extension/.pi/skills/doctor .github/skills/doctor && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "doctor" agent skill from https://github.com/BlackBeltTechnology/pi-agent-dashboard/tree/develop/packages/extension/.pi/skills/doctor into .github/skills/doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doctor", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add BlackBeltTechnology/pi-agent-dashboard --skill doctor -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install BlackBeltTechnology/pi-agent-dashboard doctor --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboard.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/packages/extension/.pi/skills/doctor .opencode/skills/doctor && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "doctor" agent skill from https://github.com/BlackBeltTechnology/pi-agent-dashboard/tree/develop/packages/extension/.pi/skills/doctor into .opencode/skills/doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "doctor", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
doctor- GitHub stars
- 315
- Token cost
- ~1.1k tokens
- SKILL.md length
- 488 words
- Files
- 31
- Skills in repo
- 70
- Repo updated
- First seen
- Licence
- MIT
At a glance
Diagnose why pi-flows, the Anthropic-messages bridge, model resolution, a pi install, a peer, a plugin/bridge, or a build/reload is broken in the pi-agent-dashboard.
- Works in 3 steps: Symptom phrase (e.g. "flow won't show")… → Named capability (e.g. "check peers") →… → Full sweep (no hint, or "full") →…
- SKILL.md covers Modules, How to route, Fact provenance (server up or… and Two-tier self-update, plus 1 more section
- Runs TypeScript scripts from its folder
What it does
Doctor is an agent skill from BlackBeltTechnology/pi-agent-dashboard. Diagnose why pi-flows, the Anthropic-messages bridge, model resolution, a pi install, a peer, a plugin/bridge, or a build/reload is broken in the pi-agent-dashboard. Derives every fact live (works with the server down). Use on "flow won't show", "bridge waitingpeers", "pi version mismatch", "which pi is this using", "diagnose the dashboard", "doctor".
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 32 other files (for example `AGENTS.md`, `_lib/checks.ts` and `_lib/derive-tokens.ts`).
It works with Model Context Protocol. The repository describes itself as: Real-time web dashboard for pi coding-agent sessions. Multi-session view, live chat mirroring, integrated terminal, diff viewer, pi-flows execution, and mobile-first remote… The licence is MIT.
Example prompts
- “flow won”
- “bridge waitingpeers”
- “pi version mismatch”
- “/doctor”
Requirements
- Node.js
- Docker
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Symptom phrase (e.g. "flow won't show") → routeSymptom(modules, phrase)
- Named capability (e.g. "check peers") → read modules/peers.md directly.
- Full sweep (no hint, or "full") → buildSweepOrder(modules) orders
What it can do on your machine
Read from SKILL.md and the folder at commit 7a2d171. 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, from the files we listed), 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 no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Doctor loads about 1.1k tokens when it runs. Until then it costs about 90 tokens; SKILL.md has 488 words of instructions outside code blocks.
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 BlackBeltTechnology/pi-agent-dashboard at commit 7a2d171, republished under its MIT licence (© BlackBeltTechnology). 488 words, ~1,094 tokens.
Download SKILL.mdSave it as
.claude/skills/doctor/SKILL.md (or your agent's skills folder). This skill also uses 30 other files; get the full folder from GitHub.- name
- doctor
- description
- Diagnose why pi-flows, the Anthropic-messages bridge, model resolution, a pi install, a peer, a plugin/bridge, or a build/reload is broken in the pi-agent-dashboard. Derives every fact live (works with the server down). Use on "flow won't show", "bridge waiting_peers", "pi version mismatch", "which pi is this using", "diagnose the dashboard", "doctor".
- license
- MIT
doctor — modular diagnostic skill
This SKILL.md is a thin router. It owns NO capability knowledge. Every
diagnostic fact lives in a self-contained capability module under modules/,
read on demand. The router derives its symptom map and sweep order from each
module's front-matter (symptoms:, depends-on:) — so adding a module MD
auto-registers it with no edit here.
Modules
Each modules/<id>.md follows a uniform 5-part contract: SCOPE · KNOWLEDGE ·
CHECKS · FIX ROUTING · DERIVES-FROM (+ a <id>.knowledge.hash sidecar).
| id | scope |
|---|---|
env-node | Node runtime + OS/platform baseline |
pi-resolution | every pi install location, divergence + floor |
peers | pi-flows + anthropic peer, tier-1/tier-2, name-skew |
plugins-bridges | bridge registration (packages[] vs dashboardPluginBridges) + activation |
build-reload | three-component rebuild/reload gaps |
install-topology | npm-global / Electron / Docker / dev + topology fixes |
model-resolution | model:resolve handler, roles/preset, @role resolvability |
apple-tools | iMCP (Apple PIM) provisioning state for the apple-tools plugin |
oauth-redirect-base | which OAuth redirect base won + its tier (reverse-proxy redirect_uri_mismatch) |
mcp-builtin | pi built-in MCP + per-session pi-dashboard registration (adapter installed, shadowing entry, non-strict mcp.json) |
How to route
The router logic lives in _lib/router.ts (load modules, build the symptom
map, topo-sort the sweep DAG, plan short-circuit). Use it — do not hand-keep a
catalog.
- Symptom phrase (e.g. "flow won't show") →
routeSymptom(modules, phrase)returns exactly one module id. Read that module MD and run its CHECKS. - Named capability (e.g. "check peers") → read
modules/peers.mddirectly. - Full sweep (no hint, or "full") →
buildSweepOrder(modules)orders modules env → pi → peers → plugins → build → runtime. Run in order; when a module fails,planSweep(modules, failed)marks every dependent modulesuppressedso a lower-layer failure (missing pi) is reported as the ROOT CAUSE and NOT re-reported as a broken bridge.
Fact provenance (server up or down)
Checks are shell-first: they read files + createRequire and work with the
dashboard server DOWN. When the server is reachable, _lib/server-tier.ts
(fetchHealth, fetchPiCoreVersions) enriches the report as an ADDITIVE tier.
Every reported fact is labelled file-derived or server-enriched
(_lib/provenance.ts) so a partial (server-down) run is never mistaken for a
clean bill.
Show full SKILL.md (175 more words)Show less
Two-tier self-update
- Tier 1 (derive-on-run) — versions, peer names, resolved paths, the recommended set are read from live sources every run; they can never rot.
- Tier 2 (knowledge-hash) — each module stores
<id>.knowledge.hashover the semantic tokens of itsderives-fromsources (_lib/knowledge-hash.ts). On run,checkDrift(id, liveTokens, hashPath)compares live vs stored; a mismatch flags that module's authored prose as possibly stale.
--regenerate <module>
When a module's hash drifts:
- Re-derive the module's tables from its live
derives-fromsources. - Propose edits to the module's authored prose for confirmation — never overwrite silently.
- After confirmation,
writeStoredHash(hashPath, liveHash)to clear the drift.
Regeneration is always confirmed. The AGENTS.md Documentation Update Protocol
maps each source-of-truth change to the single module to regenerate (peer
rename → peers; pi floor bump → pi-resolution; new install platform →
install-topology; new bridge slot → plugins-bridges).
Report format
For each module report: PASS / FAIL, the resolved path(s) + version(s) per
tier, the provenance of each fact, and — on FAIL — the matching FIX ROUTING
remediation for the detected install topology. Never report a version without
the resolved path it came from.
© BlackBeltTechnology, 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 30 other files in packages/extension/.pi/skills/doctor of BlackBeltTechnology/pi-agent-dashboard.
- SKILL.md
- AGENTS.md
- _lib/checks.ts
- _lib/derive-tokens.ts
- _lib/front-matter.ts
- _lib/index.ts
- _lib/knowledge-hash.ts
- _lib/provenance.ts
- _lib/regenerate.ts
- _lib/router.ts
- _lib/server-tier.ts
- modules/apple-tools.knowledge.hash
- modules/apple-tools.md
- modules/build-reload.knowledge.hash
- modules/build-reload.md
- modules/env-node.knowledge.hash
- modules/env-node.md
- modules/install-topology.knowledge.hash
- modules/install-topology.md
- … and 12 more
Open the folder on GitHubat commit 7a2d171
Compare with similar skills
Doctor 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Doctor this skillBlackBeltTechnology/pi-agent-dashboard | 315 | — | ~1.1k | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server BuildershareAI-lab/learn-claude-code | 78k | 4 repos | ~1.2k | Automated safety check: Pass | MIT | |
| MCP Integration for Pluginsanthropics/claude-plugins-official | 38k | 11 repos | ~3.1k | Automated safety check: Pass | Apache-2.0 | |
| Figma use_figma Plugin API Ruleswarpdotdev/warp | 65k | 4 repos | ~4.4k | Automated safety check: Pass | AGPL-3.0 | |
| Stitch to Remotion Walkthrough Videosgoogle-labs-code/stitch-skills | 8.5k | 6 repos | ~3.2k | Automated safety check: Notes | Apache-2.0 |
Similar skills
- Official
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.
- Official
MCP Integration for Plugins
anthropics/claude-plugins-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.
Figma use_figma Plugin API Rules
warpdotdev/warp
Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.
- Official
Stitch to Remotion Walkthrough Videos
google-labs-code/stitch-skills
Builds walkthrough videos from Stitch design projects using Remotion, with transitions, zoom effects and text overlays on each screen.
MCP Development
coollabsio/coolify
A skill your agent uses for Laravel MCP development. An agent skill from coollabsio/coolify.
More from BlackBeltTechnology/pi-agent-dashboard
All 70 skills in this repoBrowser
BlackBeltTechnology/pi-agent-dashboard
Browser automation via the agent-browser CLI. An agent skill from BlackBeltTechnology/pi-agent-dashboard.
CI Troubleshoot
BlackBeltTechnology/pi-agent-dashboard
Diagnose failed GitHub Actions runs for pi-agent-dashboard: the 11-file workflow taxonomy, affected-test selection, the release pipeline, known failure modes, and how to read gh run logs and…
Debug Dashboard
BlackBeltTechnology/pi-agent-dashboard
Diagnose problems in the running pi-agent-dashboard system: server.log, /api/health, bridge WebSocket connectivity, vitest triage, known-issue FAQ entries.
Implement
BlackBeltTechnology/pi-agent-dashboard
Disciplined implementation in pi-agent-dashboard: the rebuild matrix (extension→reload, server→restart, client→build+restart, openspec-apply→full rebuild) plus the project's code discipline rules.
Pi Dashboard
BlackBeltTechnology/pi-agent-dashboard
Monitor and control the pi-dashboard server. An agent skill from BlackBeltTechnology/pi-agent-dashboard.
Session To Guideline
BlackBeltTechnology/pi-agent-dashboard
Turn a pi session into a Markdown "how-we-did-it" collaboration guideline: reads the session's JSONL transcript and synthesizes a reusable playbook of which prompts worked, what had to be steered…
Related
Works with
Questions about Doctor
What does Doctor do?
Diagnose why pi-flows, the Anthropic-messages bridge, model resolution, a pi install, a peer, a plugin/bridge, or a build/reload is broken in the pi-agent-dashboard. Doctor is an agent skill from BlackBeltTechnology/pi-agent-dashboard. Diagnose why pi-flows, the Anthropic-messages bridge, model resolution, a pi install, a peer, a plugin/bridge, or a build/reload is broken in the pi-agent-dashboard.
How do I install Doctor in Claude Code?
Run `npx skills add BlackBeltTechnology/pi-agent-dashboard --skill doctor -a claude-code`. Or copy the skill folder (packages/extension/.pi/skills/doctor in BlackBeltTechnology/pi-agent-dashboard) into .claude/skills/doctor in your project. Claude Code loads it when a task matches its description.
How do I install Doctor in Codex?
Run `npx skills add BlackBeltTechnology/pi-agent-dashboard --skill doctor -a codex`. Or copy the skill folder (packages/extension/.pi/skills/doctor in BlackBeltTechnology/pi-agent-dashboard) into .agents/skills/doctor in your project. Codex loads it when a task matches its description.
Can I use Doctor 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 BlackBeltTechnology/pi-agent-dashboard --skill doctor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/doctor, .gemini/skills/doctor, .github/skills/doctor and .opencode/skills/doctor in your project.
What does Doctor need to run?
Going by SKILL.md and its folder, Doctor needs TypeScript for the scripts in its folder. Our summary lists: Node.js; Docker.
Does Doctor 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 Doctor 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 Doctor use?
Doctor is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Doctor use?
About 1.1k tokens (SKILL.md is roughly 4.4k 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 Doctor?
Skills that share tags, products or a category with Doctor: 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 Figma use_figma Plugin API Rules (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Doctor?
BlackBeltTechnology (a GitHub organization) maintains it in BlackBeltTechnology/pi-agent-dashboard, which has 315 GitHub stars. The repository holds 70 skills in this directory. The repository was last updated on October 10, 2026.
Source: BlackBeltTechnology/pi-agent-dashboard on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.