Inference Logoinference.sh

Creating Skills

create skills directly on inference.sh — no CLI or local tooling required.


the web editor

go to my skills and click create skill.

the editor has four sections:

info

fieldwhat it does
nameunique identifier (kebab-case, e.g. code-review). immutable after creation
descriptionwhat this skill does and when to use it. the agent sees this to decide whether to load the skill — make it specific
categoryoptional grouping for the registry (e.g. "development", "writing")
repo urllink to source repo if the skill lives elsewhere too

instructions

the core content agents load when they call skill_get. write this in markdown — it can include:

  • step-by-step instructions
  • rules and guidelines
  • reference information
  • examples and templates
  • links to supporting files (e.g. [see API reference](references/api-docs.md))

this is the body of the SKILL.md file in the agent skills standard.

files

supporting files organized by purpose:

prefixwhat goes here
references/domain docs, API specs, technical references
scripts/executables the agent can run (.py, .sh, .js)
examples/example outputs showing expected format
templates/templates for the agent to fill in
assets/images, data files, other resources

agents load these on demand via skill_get("my-skill", "references/api-docs.md"). keep large reference material here instead of inlining it in the instructions — only what's needed gets loaded.

metadata

fieldwhat it does
licensee.g. MIT, Apache-2.0
allowed toolswhich tools the agent may use while executing this skill (e.g. Read, Grep, Bash)
compatibilitywhich agents this skill works with (e.g. "Claude Code", "any")

the SKILL.md format

under the hood, the editor produces a spec-compliant SKILL.md file. if you're curious what that looks like:

yaml
1---2name: code-review3description: guidelines for reviewing pull requests4allowed-tools: Read, Grep5license: MIT6---78# code review guidelines910when reviewing a pull request, check for:11121. security vulnerabilities (injection, XSS, auth bypass)132. performance issues (N+1 queries, unnecessary allocations)143. code style consistency with the existing codebase1516[see full checklist](references/checklist.md)

the frontmatter contains metadata fields. the markdown body after --- is what gets loaded as instructions. you never need to write this by hand — the web editor assembles it from your form fields.

for full spec details, see agentskills.io.


versioning

every time you save changes, a new version is created. the skill's URL always serves the latest version — agents automatically get updates without reconfiguration.

previous versions are listed in the versions section of the editor for reference.


visibility

settingwho can see it
privateonly you and your team
publicanyone — listed in the skill registry

set visibility in the editor's visibility section or from your skills list.


tips

write good descriptions. the description is what the agent sees in the tool listing. a vague "docs" tells the agent nothing. "API documentation for the payment service, including endpoints, authentication, and error codes" gives the agent enough to decide when to load it.

keep skills focused. one skill per topic. instead of one massive "everything" skill, split into code-review, security-checklist, and api-reference. the agent loads only what it needs.

use supporting files for bulk. put large reference docs, API specs, and detailed examples in references/ or examples/. the main instructions should be a concise guide that references these files when the agent needs detail.

link between files. in your instructions, use relative paths like [see reference](references/api-docs.md). the agent can load these via skill_get — same paths work on the filesystem for local agents.

we use cookies

we use cookies to ensure you get the best experience on our website. for more information on how we use cookies, please see our cookie policy.

by clicking "accept", you agree to our use of cookies.
learn more.