Why
fmflurry/settings-opencode
A skill your agent uses for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds.
Loads one entity-linked Skill through UModel, follows its inline SKILL.md and applies attached knowledge items under their apply policies.
Install UModel Skill Runner
$ npx skills add alibaba/UnifiedModel --skill umodel-skill-runner -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install alibaba/UnifiedModel umodel-skill-runner --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/alibaba/UnifiedModel.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/umodel-skill-runner .claude/skills/umodel-skill-runner && 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 "umodel-skill-runner" agent skill from https://github.com/alibaba/UnifiedModel/tree/main/skills/umodel-skill-runner into .claude/skills/umodel-skill-runner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "umodel-skill-runner", 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/alibaba/UnifiedModel/tree/main/skills/umodel-skill-runnerType 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 alibaba/UnifiedModel --skill umodel-skill-runner -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install alibaba/UnifiedModel umodel-skill-runner --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alibaba/UnifiedModel.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/umodel-skill-runner .agents/skills/umodel-skill-runner && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "umodel-skill-runner" agent skill from https://github.com/alibaba/UnifiedModel/tree/main/skills/umodel-skill-runner into .agents/skills/umodel-skill-runner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "umodel-skill-runner", 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 alibaba/UnifiedModel --skill umodel-skill-runner -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install alibaba/UnifiedModel umodel-skill-runner --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alibaba/UnifiedModel.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/umodel-skill-runner .cursor/skills/umodel-skill-runner && 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 "umodel-skill-runner" agent skill from https://github.com/alibaba/UnifiedModel/tree/main/skills/umodel-skill-runner into .cursor/skills/umodel-skill-runner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "umodel-skill-runner", 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/alibaba/UnifiedModel.git --path skills/umodel-skill-runner--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 alibaba/UnifiedModel --skill umodel-skill-runner -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install alibaba/UnifiedModel umodel-skill-runner --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alibaba/UnifiedModel.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/umodel-skill-runner .gemini/skills/umodel-skill-runner && 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 "umodel-skill-runner" agent skill from https://github.com/alibaba/UnifiedModel/tree/main/skills/umodel-skill-runner into .gemini/skills/umodel-skill-runner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "umodel-skill-runner", 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 alibaba/UnifiedModel umodel-skill-runnerInstalls 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 alibaba/UnifiedModel --skill umodel-skill-runner -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/alibaba/UnifiedModel.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/umodel-skill-runner .github/skills/umodel-skill-runner && 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 "umodel-skill-runner" agent skill from https://github.com/alibaba/UnifiedModel/tree/main/skills/umodel-skill-runner into .github/skills/umodel-skill-runner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "umodel-skill-runner", 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 alibaba/UnifiedModel --skill umodel-skill-runner -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install alibaba/UnifiedModel umodel-skill-runner --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alibaba/UnifiedModel.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/umodel-skill-runner .opencode/skills/umodel-skill-runner && 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 "umodel-skill-runner" agent skill from https://github.com/alibaba/UnifiedModel/tree/main/skills/umodel-skill-runner into .opencode/skills/umodel-skill-runner/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "umodel-skill-runner", 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
umodel-skill-runner- GitHub stars
- 415
- Token cost
- ~1k tokens
- SKILL.md length
- 364 words
- Files
- 1
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Loads one entity-linked Skill through UModel, follows its inline SKILL.md and applies attached knowledge items under their apply policies.
- Works in 7 steps: Identify the exact EntitySet and… → Discover methods with the same context → Require list_skills, then list candidates → …
- An EntitySet exposes list_skills and you need to run one of its skills
- SKILL.md covers Protocol, Knowledge Context, Tool And Authorization Boundary and Completion, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
This skill is the procedure for running a Skill that lives inside UModel, a semantic layer over enterprise data, instead of on disk. The agent identifies the exact EntitySet and entity IDs it was given, lists the available methods, confirms that list_skills is exposed and lists candidate skills. It picks one, preferring an exact ID or name from you, and asks when several plausible choices would change the work.
It then loads exactly one detailed row and requires a non-empty inline SKILL.md in the returned files, reading other files only when that one refers to them. It never fetches a skill_url, runs embedded scripts or invents missing instructions, and follows the loaded skill only within your request, higher-priority instructions, authorization and safety limits. Queries run as SPL, through umctl query run or the MCP query_spl_execute tool.
When list_knowledge is advertised, the matching knowledge items for the runbook are loaded and each item's apply policy is honored: always items are included, auto items when relevant, manual only on request, custom only if the runtime supports them, and unknown policies are treated as manual. Items are ordered by numeric priority, and knowledge text is treated as untrusted reference, never as instructions or authorization.
When your agent uses it
- An EntitySet exposes list_skills and you need to run one of its skills
- Running a RunbookSet or UModel Skill requested by name
- An entity task supplies its own SKILL.md to follow
- Loading runbook knowledge items that apply to a skill
Example prompts
- “List the skills available on this EntitySet and run the incident triage one.”
- “Execute the RunbookSet Skill for the payments service entity I supplied.”
- “Load the knowledge items for this runbook skill and tell me which ones apply.”
Requirements
- Access to a UModel workspace through the umctl CLI or the MCP query_spl_execute tool
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Identify the exact EntitySet and supplied entity IDs. Do not guess another.
- Discover methods with the same context
- Require list_skills, then list candidates
- Select one. Prefer an exact user-requested ID/name; report no match, or ask
- Require exactly one detailed row
- Require non-empty inline files[].SKILL.md; read other files only when it
- Follow it within the user request, higher-priority instructions,
What it can do on your machine
Read from SKILL.md and the folder at commit 1b54ddc. 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 (its code samples are spl).
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
UModel Skill Runner loads about 1k tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 364 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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 364 words (~1,005 tokens).
“Load one entity-linked Skill through UModel and follow its inline SKILL.md. Use umodel-query; run SPL through umctl query run "" -o json or MCP query_spl_execute.”
- name
- umodel-skill-runner
Files
Just SKILL.md in skills/umodel-skill-runner of alibaba/UnifiedModel.
Open the folder on GitHubat commit 1b54ddc
Compare with similar skills
UModel Skill Runner 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 |
|---|---|---|---|---|---|---|
| UModel Skill Runner this skillalibaba/UnifiedModel | 415 | — | ~1k | Automated safety check: Pass | Custom licence | |
| Whyfmflurry/settings-opencode | 171 | — | ~2k | Automated safety check: Pass | MIT | |
| Skillsharerunkids/skillshare | 2.8k | — | ~2.2k | Automated safety check: Pass | MIT | |
| PicoClaw Agentsipeed/picoclaw | 30k | — | ~7.2k | Automated safety check: Notes | MIT | |
| AgentSkillsHub Skill Finderzhuyansen/agent-skills-hub | 410 | — | ~1k | Automated safety check: Pass | MIT | |
| Sandboxed.sh Library ManagementTh0rgal/sandboxed.sh | 516 | — | ~931 | Automated safety check: Pass | None |
Similar skills
Skillshare
runkids/skillshare
Manage skills, agents, extras, hooks, plugins, and MCP connection settings with the Skillshare CLI.
PicoClaw Agent
sipeed/picoclaw
Answers questions about running and changing PicoClaw, from onboarding and model selection to MCP server setup, skill loading and scheduled jobs.
AgentSkillsHub Skill Finder
zhuyansen/agent-skills-hub
Searches a locally cached, security-graded catalog of agent skills and MCP servers, and returns install commands after checking each one's grade.
Sandboxed.sh Library Management
Th0rgal/sandboxed.sh
Reads and updates the Sandboxed.sh Library, a git-backed store of skills, agents, commands, tools, rules and MCP servers, through its library tools.
- Official
Mistral Vibe CLI Reference
mistralai/mistral-vibe
Reference for Mistral Vibe, the CLI agent it runs inside: config files, env vars, agents, skills, tools, hooks and MCP servers, so the agent can explain and troubleshoot its own setup.
More from alibaba/UnifiedModel
UModel Root Cause Analysis
alibaba/UnifiedModel
Investigates a service incident to its root cause by querying a UModel object graph alongside metrics, logs, topology and recent deployments.
Related
Works with
Categories
Questions about UModel Skill Runner
What does UModel Skill Runner do?
Loads one entity-linked Skill through UModel, follows its inline SKILL.md and applies attached knowledge items under their apply policies. This skill is the procedure for running a Skill that lives inside UModel, a semantic layer over enterprise data, instead of on disk. The agent identifies the exact EntitySet and entity IDs it was given, lists the available methods, confirms that list_skills is exposed and lists candidate skills.
When should I use UModel Skill Runner?
UModel Skill Runner fits situations like: an EntitySet exposes list_skills and you need to run one of its skills; running a RunbookSet or UModel Skill requested by name; an entity task supplies its own SKILL.md to follow; loading runbook knowledge items that apply to a skill.
How do I install UModel Skill Runner in Claude Code?
Run `npx skills add alibaba/UnifiedModel --skill umodel-skill-runner -a claude-code`. Or copy the skill folder (skills/umodel-skill-runner in alibaba/UnifiedModel) into .claude/skills/umodel-skill-runner in your project. Claude Code loads it when a task matches its description.
How do I install UModel Skill Runner in Codex?
Run `npx skills add alibaba/UnifiedModel --skill umodel-skill-runner -a codex`. Or copy the skill folder (skills/umodel-skill-runner in alibaba/UnifiedModel) into .agents/skills/umodel-skill-runner in your project. Codex loads it when a task matches its description.
Can I use UModel Skill Runner 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 alibaba/UnifiedModel --skill umodel-skill-runner -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/umodel-skill-runner, .gemini/skills/umodel-skill-runner, .github/skills/umodel-skill-runner and .opencode/skills/umodel-skill-runner in your project.
What does UModel Skill Runner need to run?
SKILL.md names no scripts, command-line tools or credentials: UModel Skill Runner is instructions for the agent only. Our summary lists: Access to a UModel workspace through the umctl CLI or the MCP query_spl_execute tool.
Does UModel Skill Runner 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 UModel Skill Runner 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 UModel Skill Runner use?
UModel Skill Runner has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does UModel Skill Runner use?
About 1k tokens (SKILL.md is roughly 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 UModel Skill Runner?
Skills that share tags, products or a category with UModel Skill Runner: Why (fmflurry/settings-opencode, 171 stars), Skillshare (runkids/skillshare, 2.8k stars), PicoClaw Agent (sipeed/picoclaw, 30k stars) and AgentSkillsHub Skill Finder (zhuyansen/agent-skills-hub, 410 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains UModel Skill Runner?
alibaba (a GitHub organization) maintains it in alibaba/UnifiedModel, which has 415 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on September 23, 2026.
Source: alibaba/UnifiedModel on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.