Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add holon-run/uxc --skill uxc-skill-creatorgit clone --depth 1 https://github.com/holon-run/uxcWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/holon-run/uxc/uxc-skill-creator)<a href="https://agentmods.dev/skills/holon-run/uxc/uxc-skill-creator"><img src="https://agentmods.dev/badge/skills/holon-run/uxc/uxc-skill-creator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/holon-run/uxc/uxc-skill-creator"><img src="https://agentmods.dev/badge/skills/holon-run/uxc/uxc-skill-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 85 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.00760 |
| Opus 5 | $0.00023 | $0.00380 |
| Sonnet 5 | $0.00009 | $0.00152 |
| Haiku 4.5 | $0.00005 | $0.00076 |
Grade A, and why
uxc-skill-creator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UXC Skill Creator
Use this skill to design and standardize provider wrapper skills built on top of uxc.
Prerequisites
uxcskill is available as the base execution contract.- Target wrapper skill scope is clear (provider endpoint, core operations, auth model, write risk).
Output Contract
A wrapper skill created with this skill should include:
SKILL.mdagents/openai.yamlreferences/usage-patterns.mdscripts/validate.sh
Optional files are allowed only when they add real reusable value.
Core Workflow
- Start from user-provided host input:
- record the raw host the user gives
- normalize endpoint candidates (scheme/no-scheme, path variants)
- Discover protocol and valid path before drafting skill text:
- search official docs/repo to confirm endpoint shape and auth model
- probe candidates with
uxc <endpoint> -h - confirm one working endpoint + protocol as the wrapper target
- Detect authentication requirement explicitly:
- run host help or a minimal read call and inspect envelope/error code
- if auth-protected, record required model (api key or oauth) and scopes
- verify local mapping path with
uxc auth binding match <endpoint>when OAuth/binding is used
- Fix the wrapper interface:
- provider endpoint (
<host>) - fixed link command name (
<provider>-<protocol>-cli) - auth mode (none, api key, oauth)
- provider endpoint (
- Write
SKILL.mdas a thin execution policy:- link-first command flow
- help-first discovery flow
- JSON envelope parsing and safe-write guardrails
- Add provider-specific
references/usage-patterns.md:- minimal read and write examples
- key=value and bare JSON positional input examples
- Add
scripts/validate.shwith strict checks:- required files
- frontmatter fields
- command style constraints
- banned legacy patterns
- Add
agents/openai.yamlfor skill UI metadata. - Run validation and iterate until clean.
Hard Rules
- Default to link-first (
command -v <link_name>thenuxc link <link_name> <host>). - Default to help-first (
<link_name> -h,<link_name> <operation> -h). - Use protocol-aware link naming:
- format:
<provider>-<protocol>-cli - examples:
notion-mcp-cli,github-openapi-cli
- format:
- Prefer
key=value; allow bare JSON positional payload. - Keep JSON output as automation path; do not rely on
--text. - Do not use legacy default examples (
list/describe/call/removed flags). - Do not use dynamic link renaming at runtime.
- Do not assume protocol/path/auth from host string alone; verify by search + probe.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 86 lines · 46 tokens per session scan A 7dc1cf54a9ae
uxc-skill-creator is a skill published in the GitHub repository holon-run/uxc (113 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 760 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
lap
LAP CLI -- compile, search, and manage API specs for AI agents. Use when working with API specifications (OpenAPI, GraphQL, AsyncAPI, Protobuf, Postman), compiling specs to LAP format, searching the LAP registry, generating skills from API specs, or publishing APIs. Commands: init, compile, search, get, skill…
lap
LAP CLI -- compile, search, and manage API specs for AI agents. Use when working with API specifications (OpenAPI, GraphQL, AsyncAPI, Protobuf, Postman), compiling specs to LAP format, searching the LAP registry, generating skills from API specs, or publishing APIs. Commands: init, compile, search, get, skill…
linear
Linear project management — issues, cycles, and projects via GraphQL API.
api-design-patterns
Comprehensive API design patterns covering REST, GraphQL, gRPC, versioning, authentication, and modern API best practices.
pipefy-api-fallback
Use this skill when an MCP tool fails AND the introspection skill could not resolve the problem. This is the last-resort fallback (Tier 3): call the Pipefy GraphQL API directly using curl or httpx, authenticating with the Service Account (OAuth2) or a Personal Access Token (PAT) available as env var. Follow the 3-tier…
handoff
Create, validate, list, and load local Portable Handoff capsules for context transfer, continuing work in a new chat, compacting current work, or loading prior work. Use whenever the user asks for a handoff, context transfer, continuation briefing, or portable work-state summary.