Skill40.2k repo starsupdated 6d ago

skillify

Skillify extracts repeatable workflows discovered during a Claude Code session into reusable skill drafts for the OMC framework. Use this skill when a multi-step process involving debugging, design decisions, or operational effort emerges as something worth codifying rather than rediscovering later, provided it passes the quality gate: it cannot be found via a quick search, is specific to the codebase or workflow, and required genuine problem-solving effort. The skill formalizes inputs, ordered steps, success criteria, constraints, and verification evidence into a properly formatted YAML-frontmatter skill file stored in project or user-level directories.

View source Repository: oh-my-claudecode

Install in Claude Code

Copy

git clone --depth 1 https://github.com/Yeachan-Heo/oh-my-claudecode /tmp/skillify && cp -r /tmp/skillify/skills/skillify ~/.claude/skills/skillify

Then start a new Claude Code session; the skill loads automatically.

Definition

SKILL.md

# Skillify

Use this skill when the current session uncovered a repeatable workflow that should become a reusable OMC skill.

## Goal
Capture a successful multi-step workflow as a concrete skill draft instead of rediscovering it later.

## Quality Gate
Before extracting a skill, all three should be true:
- "Could someone Google this in 5 minutes?" → No.
- "Is this specific to this codebase, project, or workflow?" → Yes.
- "Did this take real debugging, design, or operational effort to discover?" → Yes.

Prefer skills that encode decision-making heuristics, constraints, pitfalls, and verification steps. Avoid generic snippets, boilerplate, or library usage examples that belong in normal documentation.

## Workflow
1. Identify the repeatable task the session accomplished.
2. Extract:
- inputs
- ordered steps
- success criteria
- constraints / pitfalls
- verification evidence
- best target location for the skill
3. Decide whether the workflow belongs as:
- a repo built-in skill
- a user/project learned skill
- documentation only
4. When drafting a learned skill file, output a complete skill file that starts with YAML frontmatter.
- Never emit plain markdown-only skill files.
- Do **not** write plain markdown without frontmatter.
- Minimum frontmatter:
```yaml
---
name: <skill-name>
description: <one-line description>
triggers:
- <trigger-1>
- <trigger-2>
---
```
- Write learned/user/project skills to flat file-backed paths:
- `${CLAUDE_CONFIG_DIR:-~/.claude}/skills/omc-learned/<skill-name>.md`
- `.omc/skills/<skill-name>.md`
- Remember that uncommitted skills are still worktree-local until committed or copied to a user-level directory.
5. Draft the rest of the skill file with clear triggers, steps, success criteria, and pitfalls.
6. Point out anything still too fuzzy to encode safely.

## Rules
- Only capture workflows that are actually repeatable.
- Keep the skill practical and scoped.
- Prefer explicit success criteria over vague prose.
- If the workflow still has unresolved branching decisions, note them before drafting.
- Keep `omc-learned` as the storage directory name for compatibility; do not present it as the public invocation name.

## Output
- Proposed skill name
- Target location
- Draft workflow structure or complete skill file
- Verification or quality-gate notes
- Open questions, if any