Install
$ agentstack add skill-ariaxhan-the-agent-library-create-portable-skill ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Create Portable Skill
Create skills that another agent can actually use. A skill is a packaged workflow, not a rule, essay, prompt dump, or product pitch.
1. Classify the candidate
Before writing files, decide what the artifact is:
| Type | Definition | Destination | |---|---|---| | Packaged skill | Multi-step workflow, concrete output, portable dependencies | skills// | | Draft skill | Real workflow but incomplete body, name, trigger, or bundled files | skills// with explicit draft status | | Kit | Installable system made of hooks, templates, multiple files, or multiple skills | kits/ | | Rule/pattern | Principle, invariant, hook pattern, or one-step guardrail | rules/ or docs, not skills/ | | Reference | Background methodology a skill can point to | reference/ | | Reject | Too vague, too local, not a workflow, no crisp trigger | Do not catalog |
If it could be one bullet in a rules file, do not make it a skill.
2. Apply the skill bar
A packaged skill must pass all five:
- Workflow: at least three ordered moves, or one staged judgment process with a clear start and end.
- Non-obvious know-how: sequence, traps, tradeoffs, or templates an agent would not reliably infer.
- Concrete output: writes, changes, submits, audits, or produces a named artifact.
- Sharp trigger:
description:names real user phrasings and when to use it. - Portable package: no private paths, secrets, project-only state, or hidden local helper dependencies.
3. Name it plainly
Use lowercase hyphen-case. Prefer verb-led names that say the output:
- Good:
write-project-vision-handoff,critique-vision-handoff,hunt-research-sources - Bad: clever names, metaphors, acronyms, or one-word vibes
Folder name and frontmatter name: must match exactly.
4. Write the trigger first
The frontmatter description: is the discovery surface. It must include:
- What the skill does
- When to use it
- Real user phrasings when possible
- The concrete output
Use third person and be specific. The body loads only after the skill triggers, so do not hide trigger logic in the body.
5. Package the folder
Minimum:
skills//
SKILL.md
agents/openai.yaml
Add bundled files only when they directly support execution:
reference/for templates, output formats, checklists, or long examplesscripts/for deterministic repeatable operationsassets/for templates or media used in outputs
Do not add README, changelog, installation guide, or extra docs inside the skill folder.
6. Validate
Check:
SKILL.mdstarts with YAML frontmatter.- Frontmatter has only
name:anddescription:. name:matches folder.- Referenced files exist.
- Private names, absolute user paths, secrets, and project-only assumptions are removed.
agents/openai.yamlhas a short display name, short description, default prompt, and invocation policy.
7. Update the catalog
Add the skill to exactly one primary category. If it is draft, local-wrapper, kit, rule, reference, or reject, say that honestly. The catalog is a shelf, not a dream board.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ariaxhan
- Source: ariaxhan/the-agent-library
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.