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.
Add or repair an editable shared Python-package dependency across consuming projects, including clone-local configuration and verification.
Install Wire Shared Package
$ npx skills add flonat/flonat-research --skill wire-shared-package -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install flonat/flonat-research wire-shared-package --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/flonat/flonat-research.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/wire-shared-package .claude/skills/wire-shared-package && 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 "wire-shared-package" agent skill from https://github.com/flonat/flonat-research/tree/main/skills/wire-shared-package into .claude/skills/wire-shared-package/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wire-shared-package", 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/flonat/flonat-research/tree/main/skills/wire-shared-packageType 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 flonat/flonat-research --skill wire-shared-package -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install flonat/flonat-research wire-shared-package --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/flonat/flonat-research.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/wire-shared-package .agents/skills/wire-shared-package && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "wire-shared-package" agent skill from https://github.com/flonat/flonat-research/tree/main/skills/wire-shared-package into .agents/skills/wire-shared-package/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wire-shared-package", 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 flonat/flonat-research --skill wire-shared-package -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install flonat/flonat-research wire-shared-package --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/flonat/flonat-research.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/wire-shared-package .cursor/skills/wire-shared-package && 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 "wire-shared-package" agent skill from https://github.com/flonat/flonat-research/tree/main/skills/wire-shared-package into .cursor/skills/wire-shared-package/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wire-shared-package", 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/flonat/flonat-research.git --path skills/wire-shared-package--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 flonat/flonat-research --skill wire-shared-package -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install flonat/flonat-research wire-shared-package --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/flonat/flonat-research.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/wire-shared-package .gemini/skills/wire-shared-package && 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 "wire-shared-package" agent skill from https://github.com/flonat/flonat-research/tree/main/skills/wire-shared-package into .gemini/skills/wire-shared-package/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wire-shared-package", 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 flonat/flonat-research wire-shared-packageInstalls 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 flonat/flonat-research --skill wire-shared-package -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/flonat/flonat-research.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/wire-shared-package .github/skills/wire-shared-package && 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 "wire-shared-package" agent skill from https://github.com/flonat/flonat-research/tree/main/skills/wire-shared-package into .github/skills/wire-shared-package/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wire-shared-package", 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 flonat/flonat-research --skill wire-shared-package -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install flonat/flonat-research wire-shared-package --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/flonat/flonat-research.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/wire-shared-package .opencode/skills/wire-shared-package && 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 "wire-shared-package" agent skill from https://github.com/flonat/flonat-research/tree/main/skills/wire-shared-package into .opencode/skills/wire-shared-package/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wire-shared-package", 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
wire-shared-package- GitHub stars
- 145
- Token cost
- ~1.7k tokens
- SKILL.md length
- 590 words
- Files
- 1
- Skills in repo
- 83
- Repo updated
- First seen
- Licence
- MIT
At a glance
Add or repair an editable shared Python-package dependency across consuming projects, including clone-local configuration and verification.
- Works in 5 steps: Discover → Wire Tier 1 Projects → Document Tier 2 Projects → …
- Multiple repositories must import the same local package source
- SKILL.md covers When to Use, Phase 1: Discover, Phase 2: Wire Tier 1 Projects and Phase 3: Document Tier 2…, plus 5 more sections
- Calls uv
What it does
Wire Shared Package is an agent skill from flonat/flonat-research. Add or repair an editable shared Python-package dependency across consuming projects, including clone-local configuration and verification. Use when multiple repositories must import the same local package source. Not for one project's ordinary environment setup; use $python-env.
Its SKILL.md is about 1.7k 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. It works with Python. The repository describes itself as: Shareable Claude Code + Codex infrastructure for PhD researchers — skills, agents, hooks, and rules for academic workflows. The licence is MIT.
When your agent uses it
- Multiple repositories must import the same local package source
Example prompts
- “/wire-shared-package”
Requirements
- Python 3
- Pre-approved tools (allowed-tools): Read, Write, Edit, Glob, Grep, Bash(uv*), Bash(ls*), Bash(mkdir*), AskUserQuestion
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit da27600. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
ReadWriteEditGlobGrepBash(uv*)Bash(ls*)Bash(mkdir*)AskUserQuestion
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
uv
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.
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
Wire Shared Package loads about 1.7k tokens when it runs. Until then it costs about 75 tokens; SKILL.md has 590 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 flonat/flonat-research at commit da27600, republished under its MIT licence (© flonat). 590 words, ~1,711 tokens.
Download SKILL.mdSave it as
.claude/skills/wire-shared-package/SKILL.md (or your agent's skills folder).- name
- wire-shared-package
- description
- Add or repair an editable shared Python-package dependency across consuming projects, including clone-local configuration and verification. Use when multiple repositories must import the same local package source. Not for one project's ordinary environment setup; use $python-env.
- allowed-tools
- Read, Write, Edit, Glob, Grep, Bash(uv*), Bash(ls*), Bash(mkdir*), AskUserQuestion
- argument-hint
- <package-path> [--downstream project1,project2,...] [--tier 1|2]
Wire Shared Package
Wire a shared Python package as an editable local dependency across multiple research projects. Handles pyproject.toml creation, CLAUDE.md documentation, and Atlas infrastructure tracking.
When to Use
- A shared package exists and needs to be wired into downstream projects
- "Add collusion-sim as a dependency to these projects"
- "Wire up the shared package"
- "Set up cross-project dependency"
- After creating a shared package with
computational-experimentsscaffold mode
Phase 1: Discover
Identify the shared package:
- Read its
pyproject.tomlto get name, version, and what it provides - Read its
CLAUDE.mdorREADME.mdfor module inventory - Confirm it installs cleanly:
uv pip install -e ".[dev]"
- Read its
Identify downstream projects:
- If not specified, ask which projects should depend on this package
- For each project, classify the dependency tier:
| Tier | Meaning | Action |
|---|---|---|
| 1 — Direct | Uses the package's core modules in active code | Full wiring: pyproject.toml + CLAUDE.md + Atlas |
| 2 — Partial | Will use specific modules when code work begins | CLAUDE.md note + Atlas only (no pyproject.toml yet) |
| 3 — Pattern only | Borrows design patterns, no code dependency | Atlas note only |
- Check prerequisites for each downstream project:
- Does it have a
pyproject.toml? (Tier 1 projects need one) - Does it have a
CLAUDE.md? (all tiers need one) - Does it have an Atlas topic file? (locate via
project_pathin frontmatter)
- Does it have a
Phase 2: Wire Tier 1 Projects
For each Tier 1 downstream project:
2a. Create or update pyproject.toml
If no pyproject.toml exists, create one:
[project]
name = "{project-kebab-name}"
version = "0.1.0"
description = "{one-line from CLAUDE.md}"
requires-python = ">=3.11"
dependencies = [
"{shared-package-name}",
]
[project.optional-dependencies]
dev = [
"pytest>=8.0",
"ruff>=0.3",
]
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"
[tool.hatch.build.targets.wheel]
packages = ["src/{project_underscored_name}"]
[tool.ruff]
line-length = 99
target-version = "py311"
[tool.uv.sources]
{shared-package-name} = { path = "{relative-path-to-package}", editable = true }If pyproject.toml already exists, add the dependency to [project] dependencies and add the [tool.uv.sources] entry.
Key: The [tool.uv.sources] section tells uv to resolve the package from a local path instead of PyPI. The relative path must be correct from the downstream project to the shared package (typically ../package-name).
2b. Update CLAUDE.md
Add a "Shared Package Dependency" section under ## Setup:
### Shared Package Dependency
- **`{package-name}`** installed as editable dependency from `{relative-path}/`
- Provides: {list key modules this project uses}
- Install: `uv pip install -e ".[dev]"` (resolves {package-name} via `[tool.uv.sources]`)
- Project-specific code goes in `src/{project_name}/` — shared simulation code stays in {package-name}2c. Verify install
cd "{project-path}" && uv pip install -e ".[dev]"Then verify imports:
uv run python -c "from {package_module} import {key_class}; print('OK')"Phase 3: Document Tier 2 Projects
For each Tier 2 downstream project, add to CLAUDE.md under ## Setup:
### Shared Package Dependency (Tier 2)
- **`{package-name}`** at `{relative-path}/` — provides {what this project will use}
- When code work begins, add `{package-name}` as editable dependency via `[tool.uv.sources]` in `pyproject.toml`
- This project will extend the framework with {project-specific extensions}No pyproject.toml changes — the dependency is documented but not yet wired.
Phase 4: Track in Atlas
For each downstream project that has an Atlas topic file, add a ## Shared Infrastructure section between the Description and Key References sections:
## Shared Infrastructure
- **`{package-name}`** (Tier {N} — {direct reuse|partial reuse|pattern only}): {what components are used}
- Location: `{theme}/{package-dir}/`
{if Tier 1:}
- Install: editable dependency via `pyproject.toml` `[tool.uv.sources]`Placement: After ## Description (or ## Portfolio Bridge if present), before ## Key References.
Finding the right topic file: Search Atlas by project_path frontmatter field:
grep -rl "project_path.*{project-folder}" ~/vault/atlas/Show full SKILL.md (215 more words)Show less
Phase 5: Update Shared Package Documentation
If the shared package has a CLAUDE.md or README.md, update its downstream project table to reflect all wired projects:
## Downstream Projects
| Project | Tier | Uses |
|---------|------|------|
| {Project Name} | {1/2/3} | {components used} |Anti-Patterns
- Never wire a dependency that doesn't install cleanly. Verify
uv pip install -e .on the shared package first. - Never create
pyproject.tomlfor Tier 2 projects. They don't have active code yet — premature wiring creates broken installs. - Never use absolute paths in
[tool.uv.sources]. Always use relative paths from the downstream project. - Never skip the Atlas update. The whole point is cross-project tracking.
- Never put the shared package's code in a downstream project. Shared code stays in the shared package; project-specific code goes in the project's own
src/.
Verification
After completing all phases:
- All Tier 1 projects install without errors
- Key imports from the shared package work in each Tier 1 project
- Every downstream project's CLAUDE.md mentions the dependency
- Every downstream project's Atlas topic has a
## Shared Infrastructuresection - The shared package's documentation lists all downstream projects
Quick check: grep -rl "{package-name}" ~/vault/atlas/ should return all expected topic files.
Defaults
| Setting | Default | Override |
|---|---|---|
| Build backend | hatchling | Specify in args |
| Python version | >=3.11 | Match shared package |
| Source layout | src/ | Match shared package |
| Relative path | ../package-name | Auto-detect from directory structure |
| Atlas section placement | After Description, before Key References | — |
© flonat, MIT. 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 skills/wire-shared-package of flonat/flonat-research.
Open the folder on GitHubat commit da27600
Compare with similar skills
Wire Shared Package 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 |
|---|---|---|---|---|---|---|
| Wire Shared Package this skillflonat/flonat-research | 145 | — | ~1.7k | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 62 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server BuildershareAI-lab/learn-claude-code | 78k | 5 repos | ~1.2k | Automated safety check: Pass | MIT | |
| Fastmcp Client CLIPrefectHQ/fastmcp | 28k | 1 repos | ~823 | Automated safety check: Pass | Apache-2.0 | |
| Mem0 CLI Memory Commandsmem0ai/mem0 | 67k | — | ~1.4k | Automated safety check: Notes | Apache-2.0 | |
| MemPalace Setup and OperationMemPalace/mempalace | 59k | — | ~2.2k | Automated safety check: Pass | MIT |
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.
Fastmcp Client CLI
PrefectHQ/fastmcp
Query and invoke tools on MCP servers using fastmcp list and fastmcp call.
Mem0 CLI Memory Commands
mem0ai/mem0
Adds, searches, lists, updates and deletes memories on the Mem0 platform from the terminal with the mem0 command, including a JSON mode built for agents.
MemPalace Setup and Operation
MemPalace/mempalace
Installs and configures MemPalace as a private local palace, a shared-brain hub or a client of an existing hub, including MCP registration and version-correct initialization.
Google Antigravity SDK
google-antigravity/antigravity-sdk-python
Design, implement, and debug autonomous AI agents and multi-agent systems using the Google Antigravity (AGY) SDK.
More from flonat/flonat-research
All 83 skills in this repoLatex Posters
flonat/flonat-research
Create a large-format academic poster in LaTeX using beamerposter, tikzposter, or baposter.
Skill Creator
flonat/flonat-research
Create, revise, and evaluate reusable AI workflow skills, including trigger-quality tests.
DOCX
flonat/flonat-research
Create, read, edit, or convert Microsoft Word documents while preserving professional document structure.
PDF
flonat/flonat-research
Read, create, combine, split, rotate, OCR, watermark, secure, or extract content from PDF files.
Init Project Orchestration
flonat/flonat-research
Create or migrate project-level agents, repeatable project workflows, and planning state from one client-neutral contract, then render repository-scoped adapters for both Claude Code and Codex.
Pre Commit Audit
flonat/flonat-research
Deliver a fast pre-commit safety scan: file size, anonymity (author / affiliation strings in tex/bib), hardcoded secrets, and invisible-Unicode carriers.
Related
Works with
Categories
Questions about Wire Shared Package
What does Wire Shared Package do?
Add or repair an editable shared Python-package dependency across consuming projects, including clone-local configuration and verification. Wire Shared Package is an agent skill from flonat/flonat-research. Add or repair an editable shared Python-package dependency across consuming projects, including clone-local configuration and verification.
When should I use Wire Shared Package?
Wire Shared Package fits situations like: multiple repositories must import the same local package source.
How do I install Wire Shared Package in Claude Code?
Run `npx skills add flonat/flonat-research --skill wire-shared-package -a claude-code`. Or copy the skill folder (skills/wire-shared-package in flonat/flonat-research) into .claude/skills/wire-shared-package in your project. Claude Code loads it when a task matches its description.
How do I install Wire Shared Package in Codex?
Run `npx skills add flonat/flonat-research --skill wire-shared-package -a codex`. Or copy the skill folder (skills/wire-shared-package in flonat/flonat-research) into .agents/skills/wire-shared-package in your project. Codex loads it when a task matches its description.
Can I use Wire Shared Package 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 flonat/flonat-research --skill wire-shared-package -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/wire-shared-package, .gemini/skills/wire-shared-package, .github/skills/wire-shared-package and .opencode/skills/wire-shared-package in your project.
What does Wire Shared Package need to run?
Going by SKILL.md and its folder, Wire Shared Package needs the command-line tools its instructions call (uv). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read, Write, Edit, Glob, Grep, Bash(uv*), Bash(ls*), Bash(mkdir*), AskUserQuestion.
Does Wire Shared Package access the network?
SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Wire Shared Package 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 Wire Shared Package use?
Wire Shared Package 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 Wire Shared Package use?
About 1.7k tokens (SKILL.md is roughly 6.8k 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 Wire Shared Package?
Skills that share tags, products or a category with Wire Shared Package: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), Fastmcp Client CLI (PrefectHQ/fastmcp, 28k stars) and Mem0 CLI Memory Commands (mem0ai/mem0, 67k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Wire Shared Package?
flonat (a GitHub user) maintains it in flonat/flonat-research, which has 145 GitHub stars. The repository holds 83 skills in this directory. The repository was last updated on September 29, 2026.
Source: flonat/flonat-research on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.