oma-skill-creation — Claude Code skill: what it does, how to install
oma-skill-creation is a Claude Code skill for building and refining OMA skills in SSL-lite format for Claude Code and Codex. It runs during authoring, routing reviews, and contract validation.
MIT ★ 1,472 updated 2026-11-05
/plugin marketplace add first-fluke/oh-my-agent
/plugin install oma@oh-my-agentWhat oma-skill-creation does
The skill standardizes authoring and updating .agents/skills/{name}/SKILL.md under the SSL-lite format. It structures each skill around four core sections: Scheduling, Structural Flow, Logical Operations, and References. Execution contracts stay locked to a single canonical path, stripping procedural duplication across intermediate steps.
Work relies on resources/ssl-lite-template.md and the acceptance criteria in resources/validation-checklist.md. Automated verification runs via CLI tools: oma skill lint --skill <name>, git diff --check, and oma skill audit. Bulky reference tables get separated into conditional resources rather than loaded inline.
The contract caps SKILL.md at 500 body lines. Reducing file count alone does not justify token reduction claims; actual context usage must be measured. The skill handles agent instructions, so it will not install third-party plugins or write core application code.
What it helps with
- author four-section SKILL.md definitions following the SSL-lite template
- move heavy context into conditional reference files
- validate execution contracts and routing with
oma skill lint - eliminate duplicate procedural instructions across skill entry points
Example prompts for the agent
- Create an OMA skill for PR triage in
.agents/skills/pr-triage/SKILL.mdusing the standard skeleton - Audit execution paths and run oma skill lint on our deployment skill
- Trim
.agents/skills/api-client/SKILL.mdunder 500 lines and extract tables to conditional references
How to install oma-skill-creation
1Plugin marketplace
/plugin marketplace add first-fluke/oh-my-agent/plugin install oma@oh-my-agentThis installs the whole oma plugin with all its skills
2Skills CLI (Vercel)
npx skills add first-fluke/oh-my-agent --skill oma-skill-creation -a claude-code3Manually: put the files in place
~/.claude/skills/oma-skill-creation/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/oma-skill-creation/
1Skills CLI (Vercel)
npx skills add first-fluke/oh-my-agent --skill oma-skill-creation -a codex2Manually: put the files in place
.agents/skills/oma-skill-creation/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add first-fluke/oh-my-agent --skill oma-skill-creation -a cursor2Manually: put the files in place
.cursor/skills/oma-skill-creation/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install first-fluke/oh-my-agent skills/oma-skill-creation2Manually: put the files in place
.github/skills/oma-skill-creation/SKILL.md1Skills CLI (Vercel)
npx skills add first-fluke/oh-my-agent --skill oma-skill-creation -a gemini-cli2Platform CLI
gemini skills install https://github.com/first-fluke/oh-my-agent --path skills/oma-skill-creationManually: put the files in place
.devin/skills/oma-skill-creation/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about oma-skill-creation
How to install oma-skill-creation in Claude Code?
Run /plugin marketplace add first-fluke/oh-my-agent in Claude Code, followed by /plugin install oma@oh-my-agent.
What size limits does the skill enforce?
The target SKILL.md body must stay within 500 lines. Detailed tables and optional documentation must reside in external resources loaded conditionally.
When should you avoid using oma-skill-creation?
It does not handle installing third-party skills, building Codex plugins, writing product requirements, or general application coding.
Source text
SKILL.md · MIT
---
name: oma-skill-creation
description: Create or revise OMA skills and their references. Use for skill
routing, execution contracts, conditional loading, and authoring validation.
---
# OMA Skill Authoring
## Scheduling
### Goal
Create or revise a usable OMA skill with clear routing, one execution path, domain-specific recovery, and proportionate context.
### Intent signature
- Create, update, audit, or normalize an OMA skill, its resources, or the SSL-lite format.
- Decide whether content belongs inline, in a conditional resource, or should be removed.
### When to use
- Authoring `.agents/skills/{name}/SKILL.md` and supporting resources.
- Reviewing skill routing, execution contracts, reference loading, or duplicated instructions.
### When NOT to use
- Installing third-party skills -> skill installer; creating a Codex plugin -> plugin tooling.
- Application implementation -> the owning specialist; project requirements -> `oma-pm`.
### Expected inputs
Skill purpose, triggers, boundaries, execution model, and existing commands/resources or user edits to preserve.
### Expected outputs
A four-section SKILL.md, only necessary supporting resources, and validation results with unresolved limitations.
### Dependencies
`resources/ssl-lite-template.md` for the skeleton and `resources/validation-checklist.md` for acceptance criteria. Use native file tools and available `oma skill` validators. Follow repository rules for source ownership and generated copies.
## Structural Flow
### Transitions
- New skill: compare 1–3 analogous skills, then use the template.
- Existing skill: preserve working domain detail and change only the requested scope.
- Repeated instructions: retain one authoritative location and a short reference where independently invoked entry points need it.
- Long or conditional detail: move to a named resource with a load condition. Do not move a duplicate merely to keep it elsewhere.
- Machine-checkable artifacts: declare structured `outputs:` as documented in the template.
### Failure and recovery
| Failure | Recovery |
|---|---|
| Overbroad routing | Narrow triggers and add a concrete When NOT to use cross-route |
| Vague execution | Add actual objects, paths, command flags, and evidence to the canonical path |
| Repeated procedure in multiple sections | Keep the canonical procedure; retain only distinct branches or state transitions elsewhere |
| Required tool unavailable | Use the documented fallback; otherwise report which result cannot be verified |
| Conflicting source and generated copies | Use the repository's generation flow; do not hand-edit protected definitions |
### Exit
A completed skill has valid structure, useful routing, executable steps, recoverable failures, valid references, and applicable validation evidence. Missing tools or unresolved assumptions must remain explicit.
## Logical Operations
### Canonical workflow path
1. Read the target, its invoked resources, and relevant repository rules. Identify which entry points run independently and which content the runtime already injects.
2. Select command-heavy, judgment-heavy, or reference-heavy behavior. Use the template's minimal skeleton and optional sections only where they add information.
3. Write the canonical procedure once. Preserve exact command/output contracts, failure mechanisms, side effects, and harmful-action limits; remove generic restatements and redundant examples.
4. Index resources once under References with load conditions. Keep source-adjacent evidence one hop from SKILL.md where possible.
5. Run `oma skill lint --skill <name>` and `git diff --check`. If routing descriptions changed, run `oma skill audit`. Apply the content checks in `resources/validation-checklist.md` that automated lint does not cover.
6. Report the changes, checks, and remaining limits. Do not claim reduced token usage merely from removing duplicate files; measure the context actually loaded when making that claim.
### Resource scope and effects
Skill work reads and may change local definitions/resources and generated vendor copies through the authorized repository flow. User data and credentials are not skill examples. Commits and publishing require the corresponding authorization.
### Guardrails
1. Keep YAML `name` and a routing-grade `description`. Preserve the four top-level headings: Scheduling, Structural Flow, Logical Operations, References.
2. Keep one canonical command/workflow path, an Intent signature, When to use/When NOT to use, input/output expectations, failure recovery, and relevant effects/guardrails. Section titles beyond these are optional when their information is already represented.
3. Entry, Scenes, Actions, and tool/scope tables must add distinct information. Do not repeat a procedure to fill the template.
4. Keep SKILL.md under 500 body lines. Load supporting resources conditionally; do not create README/changelog/install documents inside a skill merely to explain the skill.
5. Keep parsed output/schema examples. Do not prescribe decorative report layouts or add generic self-review loops; use runnable validators and explicit evidence requirements.
6. Process bulk data through deterministic tools and return summaries/artifact paths instead of streaming raw data into context.
7. Preserve unrelated user edits. Apply the shared execution policy to clarification, authorization, and verification.
## References
- Prompt behavior and model comparisons: `resources/prompt-evaluation.md` (routing, injection, authorization, or review-contract changes)
- Skeleton and optional sections: `resources/ssl-lite-template.md` (authoring or restructuring)
- Acceptance criteria: `resources/validation-checklist.md` (validation)
- Context loading: `references/_shared/core/context-loading.md` (resource/injection decisions)
- Quality principles: `references/_shared/core/quality-principles.md` (domain verification requirements)
- Eval fixtures: `web/docs/guide/skill-eval.md` (when measuring held-out task utility with `oma skill eval` or `oma skill optimize`)
© First Fluke · MIT · first-fluke/oh-my-agent