Agent Protocol
borghei/Claude-Skills
Design AI agent communication protocols: MCP tool schemas, A2A, function calling, and inter- agent messaging.
Design tools, scripts, and CLIs that an agent will call, so the interface teaches its own use instead of a wall of prose and examples.
Install Agent Interface Design
$ npx skills add Neeeophytee/finding-unknowns-skills --skill agent-interface-design -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Neeeophytee/finding-unknowns-skills agent-interface-design --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/Neeeophytee/finding-unknowns-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agent-interface-design .claude/skills/agent-interface-design && 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 "agent-interface-design" agent skill from https://github.com/Neeeophytee/finding-unknowns-skills/tree/main/skills/agent-interface-design into .claude/skills/agent-interface-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-interface-design", 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/Neeeophytee/finding-unknowns-skills/tree/main/skills/agent-interface-designType 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 Neeeophytee/finding-unknowns-skills --skill agent-interface-design -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Neeeophytee/finding-unknowns-skills agent-interface-design --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Neeeophytee/finding-unknowns-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/agent-interface-design .agents/skills/agent-interface-design && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agent-interface-design" agent skill from https://github.com/Neeeophytee/finding-unknowns-skills/tree/main/skills/agent-interface-design into .agents/skills/agent-interface-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-interface-design", 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 Neeeophytee/finding-unknowns-skills --skill agent-interface-design -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Neeeophytee/finding-unknowns-skills agent-interface-design --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Neeeophytee/finding-unknowns-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/agent-interface-design .cursor/skills/agent-interface-design && 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 "agent-interface-design" agent skill from https://github.com/Neeeophytee/finding-unknowns-skills/tree/main/skills/agent-interface-design into .cursor/skills/agent-interface-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-interface-design", 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/Neeeophytee/finding-unknowns-skills.git --path skills/agent-interface-design--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 Neeeophytee/finding-unknowns-skills --skill agent-interface-design -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Neeeophytee/finding-unknowns-skills agent-interface-design --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Neeeophytee/finding-unknowns-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/agent-interface-design .gemini/skills/agent-interface-design && 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 "agent-interface-design" agent skill from https://github.com/Neeeophytee/finding-unknowns-skills/tree/main/skills/agent-interface-design into .gemini/skills/agent-interface-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-interface-design", 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 Neeeophytee/finding-unknowns-skills agent-interface-designInstalls 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 Neeeophytee/finding-unknowns-skills --skill agent-interface-design -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Neeeophytee/finding-unknowns-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/agent-interface-design .github/skills/agent-interface-design && 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 "agent-interface-design" agent skill from https://github.com/Neeeophytee/finding-unknowns-skills/tree/main/skills/agent-interface-design into .github/skills/agent-interface-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-interface-design", 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 Neeeophytee/finding-unknowns-skills --skill agent-interface-design -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Neeeophytee/finding-unknowns-skills agent-interface-design --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Neeeophytee/finding-unknowns-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/agent-interface-design .opencode/skills/agent-interface-design && 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 "agent-interface-design" agent skill from https://github.com/Neeeophytee/finding-unknowns-skills/tree/main/skills/agent-interface-design into .opencode/skills/agent-interface-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-interface-design", 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
agent-interface-design- GitHub stars
- 343
- Token cost
- ~650 tokens
- SKILL.md length
- 369 words
- Files
- 1
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- MIT
At a glance
Design tools, scripts, and CLIs that an agent will call, so the interface teaches its own use instead of a wall of prose and examples.
- Works in 6 steps: Find out how the tool is actually being… → Push meaning into the parameters → Put behavioral instruction in the tool's… → …
- Building an MCP server
- SKILL.md covers Steps and Guardrails
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Agent Interface Design is an agent skill from Neeeophytee/finding-unknowns-skills. Design tools, scripts, and CLIs that an agent will call, so the interface teaches its own use instead of a wall of prose and examples. Use when building an MCP server or tool definition, writing an agent-facing script, or when an agent keeps misusing a tool it already has.
Its SKILL.md is about 650 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 AI & LLM Engineering, covering API design and Structured output and tool calling. It works with Model Context Protocol. The repository describes itself as: 14 installable skills for Claude Code, OpenAI Codex, and Hermes: find unknowns, clarify requirements, manage context, test assumptions, and verify bug fixes with regression… The licence is MIT.
When your agent uses it
- Building an MCP server
- Tool definition
- Writing an agent-facing script
- An agent keeps misusing a tool it already has
Example prompts
- “/agent-interface-design”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Find out how the tool is actually being misused before redesigning it. Read transcripts, logs, or the user's complaint. Misuse is an…
- Push meaning into the parameters
- Put behavioral instruction in the tool's own description, at the point of use, and only there. The same guidance restated in a global…
- Treat the urge to add a usage example as a diagnostic: it usually means a parameter is underspecified. Fix the interface first. Keep an…
- Decide what is resident and what is discoverable. Tools needed on most turns belong in context; tools needed rarely should be findable on…
- Finish by naming the mistake the design still permits, and say whether it is cheap enough to live with or needs an explicit guardrail.
What it can do on your machine
Read from SKILL.md and the folder at commit ca5696a. 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.
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
Agent Interface Design loads about 650 tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 369 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 Neeeophytee/finding-unknowns-skills at commit ca5696a, republished under its MIT licence (© Neeeophytee). 369 words, ~650 tokens.
Download SKILL.mdSave it as
.claude/skills/agent-interface-design/SKILL.md (or your agent's skills folder).- name
- agent-interface-design
- description
- Design tools, scripts, and CLIs that an agent will call, so the interface teaches its own use instead of a wall of prose and examples. Use when building an MCP server or tool definition, writing an agent-facing script, or when an agent keeps misusing a tool it already has.
Agent interface design
Examples teach one path and quietly fence off the others: shown three ways to call a tool, a model tends to produce those three. A well-designed interface teaches the whole space at once. The parameters say what is possible, the description says what is expected, and there is very little left to write.
Steps
- Find out how the tool is actually being misused before redesigning it. Read transcripts, logs, or the user's complaint. Misuse is an interface symptom first and a documentation symptom second, and the fix is usually a rename or a type, not a paragraph.
- Push meaning into the parameters:
- Enumerate instead of accepting free text. A status of
pending | in_progress | completedteaches the whole state machine without a sentence of prose. - Name for intent rather than implementation, so the right call is the one that reads correctly.
- Make invalid states unrepresentable wherever the type system allows it. A parameter that cannot express a mistake needs no warning about that mistake.
- Enumerate instead of accepting free text. A status of
- Put behavioral instruction in the tool's own description, at the point of use, and only there. The same guidance restated in a global preamble is how a codebase grows contradictions.
- Treat the urge to add a usage example as a diagnostic: it usually means a parameter is underspecified. Fix the interface first. Keep an example only for a format that genuinely cannot be guessed, such as a bespoke query syntax.
- Decide what is resident and what is discoverable. Tools needed on most turns belong in context; tools needed rarely should be findable on demand so they cost nothing until they're wanted.
- Finish by naming the mistake the design still permits, and say whether it is cheap enough to live with or needs an explicit guardrail.
Show full SKILL.md (72 more words)Show less
Guardrails
- A description that has to explain what a parameter means is a parameter that needs a better name.
- Irreversible and high-stakes operations are the exception to all of the above: there, explicit constraint and confirmation beat elegance.
- Never redesign a signature without first finding every existing caller.
- Terseness is not the goal; expressiveness is. Cutting a description that carried real behavior is a worse outcome than a description that ran long.
© Neeeophytee, 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/agent-interface-design of Neeeophytee/finding-unknowns-skills.
Open the folder on GitHubat commit ca5696a
Compare with similar skills
Agent Interface Design 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 |
|---|---|---|---|---|---|---|
| Agent Interface Design this skillNeeeophytee/finding-unknowns-skills | 343 | — | ~650 | Automated safety check: Pass | MIT | |
| Agent Protocolborghei/Claude-Skills | 881 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Ax Gendosco/aithy | 107 | — | ~5.4k | Automated safety check: Pass | Apache-2.0 | |
| Agent Tool Builderomer-metin/skills-for-antigravity | 162 | — | ~705 | Automated safety check: Pass | Apache-2.0 | |
| MCP Server Builder with mcp-usemcp-use/mcp-use | 11k | — | ~923 | Automated safety check: Pass | Apache-2.0 | |
| Perfupraullenchai/Rapid-MLX | 3.9k | — | ~1.6k | Automated safety check: Notes | Custom licence |
Similar skills
Ax Gen
dosco/aithy
This skill helps an LLM generate correct AxGen code using @ax-llm/ax.
Agent Tool Builder
omer-metin/skills-for-antigravity
Tools are how AI agents interact with the world. An agent skill from omer-metin/skills-for-antigravity.
MCP Server Builder with mcp-use
mcp-use/mcp-use
Builds, modifies, debugs, migrates and verifies TypeScript MCP servers and MCP Apps with the mcp-use framework, treating the installed package's types as the source of truth.
Perfup
raullenchai/Rapid-MLX
Autonomous performance optimization: research, PoC, benchmark, implement, review, PR
Tool Use Data Synthesis
sunny-glow/Auto-BenchMax
Synthesize training data for ANY tool-use / agentic benchmark, in ANY repo.
More from Neeeophytee/finding-unknowns-skills
All 14 skills in this repoAssumption Test
Neeeophytee/finding-unknowns-skills
Test a consequential technical assumption with a small, falsifiable experiment before committing to an approach.
Blindspot Pass
Neeeophytee/finding-unknowns-skills
Surface the user's unknown unknowns before work starts. An agent skill from Neeeophytee/finding-unknowns-skills.
Brainstorm Prototypes
Neeeophytee/finding-unknowns-skills
Generate several genuinely different throwaway variations (designs, approaches, drafts) for the user to react to.
Change Quiz
Neeeophytee/finding-unknowns-skills
After a working session, produce a report on what changed plus a quiz the user must pass before merging.
Context Audit
Neeeophytee/finding-unknowns-skills
Audit the instructions an agent already carries — CLAUDE.md, AGENTS.md, skills, tool descriptions — for contradictions, over-constraint, and duplication, then propose a cut list.
Implementation Notes
Neeeophytee/finding-unknowns-skills
Keep a running implementation-notes.md during a build, logging every deviation from the plan and every discovered edge case.
Related
Works with
Questions about Agent Interface Design
What does Agent Interface Design do?
Design tools, scripts, and CLIs that an agent will call, so the interface teaches its own use instead of a wall of prose and examples. Agent Interface Design is an agent skill from Neeeophytee/finding-unknowns-skills. Design tools, scripts, and CLIs that an agent will call, so the interface teaches its own use instead of a wall of prose and examples.
When should I use Agent Interface Design?
Agent Interface Design fits situations like: building an MCP server; tool definition; writing an agent-facing script; an agent keeps misusing a tool it already has.
How do I install Agent Interface Design in Claude Code?
Run `npx skills add Neeeophytee/finding-unknowns-skills --skill agent-interface-design -a claude-code`. Or copy the skill folder (skills/agent-interface-design in Neeeophytee/finding-unknowns-skills) into .claude/skills/agent-interface-design in your project. Claude Code loads it when a task matches its description.
How do I install Agent Interface Design in Codex?
Run `npx skills add Neeeophytee/finding-unknowns-skills --skill agent-interface-design -a codex`. Or copy the skill folder (skills/agent-interface-design in Neeeophytee/finding-unknowns-skills) into .agents/skills/agent-interface-design in your project. Codex loads it when a task matches its description.
Can I use Agent Interface Design 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 Neeeophytee/finding-unknowns-skills --skill agent-interface-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-interface-design, .gemini/skills/agent-interface-design, .github/skills/agent-interface-design and .opencode/skills/agent-interface-design in your project.
What does Agent Interface Design need to run?
SKILL.md names no scripts, command-line tools or credentials: Agent Interface Design is instructions for the agent only.
Does Agent Interface Design 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 Agent Interface Design 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 Agent Interface Design use?
Agent Interface Design 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 Agent Interface Design use?
About 650 tokens (SKILL.md is roughly 2.6k 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 Agent Interface Design?
Skills that share tags, products or a category with Agent Interface Design: Agent Protocol (borghei/Claude-Skills, 881 stars), Ax Gen (dosco/aithy, 107 stars), Agent Tool Builder (omer-metin/skills-for-antigravity, 162 stars) and MCP Server Builder with mcp-use (mcp-use/mcp-use, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agent Interface Design?
Neeeophytee (a GitHub user) maintains it in Neeeophytee/finding-unknowns-skills, which has 343 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on September 28, 2026.
Source: Neeeophytee/finding-unknowns-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.