ic1558/skills/auto-workflow-creator
skills/auto-workflow-creator/SKILL.md
--- name: auto-workflow-creator description: Create a new skill from a workflow you just performed. Generates a valid 3-layer Anthropic-style skill — YAML frontmatter (name + description + triggers), imperative instruction body, and optional scripts/ subdirectory — and prints the registration commands per target runtime (Claude Code auto-discovers from ~/.claude/skills/; Codex needs an explicit [[skills.config]] entry in ~/.codex/config.toml; OpenCode needs a registry entry in ~/.opencode/openco
development
Updated Jun 3, 2026
$ install --global
skillsauthnpx skillsauth add ic1558/0luka skills/auto-workflow-creatorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 3, 2026, 5:01 AM37.3s2 files scanned
SKILL.md
- name:
- auto-workflow-creator
- description:
- Create a new skill from a workflow you just performed. Generates a valid 3-layer Anthropic-style skill — YAML frontmatter (name + description + triggers), imperative instruction body, and optional scripts/ subdirectory — and prints the registration commands per target runtime (Claude Code auto-discovers from ~/.claude/skills/; Codex needs an explicit [[skills.config]] entry in ~/.codex/config.toml; OpenCode needs a registry entry in ~/.opencode/opencode.json). Use when the user says "turn this into a skill", "make this a workflow", "save this as a reusable skill", "create a new skill", "/auto-workflow-creator", or after completing a process they will clearly want to repeat. Does NOT auto-edit cross-agent config files (cross-agent-respect): produces the entries and instructs the owning agent to register them.
- user_invocable:
- true
auto-workflow-creator
Interactive 3-layer skill generator. Turns a one-off workflow into a reusable, discoverable skill in one pass — without violating cross-agent config boundaries.
When to use
- User just completed a process they will want to repeat ("turn this into a skill").
- User asks to package an ad-hoc routine as a callable skill.
- A new domain workflow exists but is currently spread across chat turns / scripts / memory.
Do NOT use for:
- Editing an existing skill (use
skill-creatorfor that). - Generic code generation unrelated to skills.
The 3-layer contract this skill enforces
| Layer | What | Where |
|---|---|---|
| 1 — Description | YAML frontmatter name + description with explicit triggers | SKILL.md head |
| 2 — Instructions | Imperative Markdown body — when to use, steps, do/don't | SKILL.md body |
| 3 — Tools | Optional executable scripts referenced from Layer 2 | scripts/ subdir |
Skills that already conform to Layer 1+2 do not need Layer 3 (matches the Phase-1 finding: most wiki skills correctly carry illustrative inline blocks, not extractable scripts).
How
The tool is scripts/create_skill.py next to this SKILL.md. Run it via:
python3 ~/0luka/skills/auto-workflow-creator/scripts/create_skill.py --help
Two modes:
Flag-driven (one-shot):
python3 .../create_skill.py \
--name <slug> \
--description "<one-paragraph, includes explicit triggers>" \
--body-file /tmp/body.md \
--scripts \
--register claude
Interactive (guided):
python3 .../create_skill.py --interactive
Default output root is ~/obsidian-wiki/.skills/, which matches the declared
wiki/data skill source of truth. For an independent agent skill under
~/0luka/skills/, pass --output-root ~/0luka/skills.
What it produces
<output-root>/<name>/SKILL.mdwith valid frontmatter (name, description) and the body you provided.<output-root>/<name>/scripts/directory (if--scripts) with a stub<name>.py.- If
--register claudeand the new skill is outside~/.claude/skills/, it creates a symlink~/.claude/skills/<name> → <output-root>/<name>/so Claude Code auto-discovers it. This follows the SOT-symlink pattern documented inskill_registry_topology.md.
What it deliberately does NOT do (cross-agent-respect)
- Does NOT edit
~/.codex/config.tomldirectly. With--register codexit prints the[[skills.config]] path = "..."entry to copy/append, so the owning agent (Codex) registers it. - Does NOT edit
~/.opencode/opencode.jsondirectly. With--register opencodeit prints the registry entry for Rio/OpenCode to apply.
This preserves the contract from dispatch-route + cross-agent-respect: CLC stages cross-agent
changes, the owning agent applies them.
Verification after a skill is generated
python3 ~/0luka/tools/ops/skill-registry/skill_lint.py --root <output-root>should score the new skill asCONFORMS(Layer 1 description present, no bulky inline blocks unless scripts/ exists).- If
--register claudewas used:ls -la ~/.claude/skills/<name>resolves through the symlink. - In a fresh Claude Code session, the skill appears in
/skillslist (auto-discovery).
Out of scope
- Session-log mining (P3b — extract a workflow from chat history).
- Autonomous self-registration loop (P3c).
This is P3a only by design.
Related Skills
ic1558/skills/cost-control
tools
VerifiedTrustedCommunity
# Cost-Control Skill Enforce token discipline and model routing optimization (Flash vs Pro) via the Gemini CLI 0.40 Gemma local router for governed-agent workflows. ## Guidelines - **Preference for Local/RTK/File Tools:** Always prioritize local tools (ls, read_file, grep_search) and RTK for initial data gathering before calling model logic. - **Flash-First Routing:** - Route all routine code analysis, file reads, summarization, search, and classification tasks to `gemini-3.5-flash-preview` o
SKILL.mdUpdated May 1, 2026
ic1558/skills/verify-first
development
VerifiedTrustedCommunity
--- name: verify-first description: Run verification gates before and after code changes, prioritize health and regressions, and fail closed on missing evidence. Mandatory Read: YES --- # Verify First Mandatory Read: YES ## Workflow 1. Capture baseline verify results. 2. Apply minimal changes. 3. Re-run targeted and system-level verify commands. 4. Report explicit pass/fail evidence. ## Caps - Run deterministic verification commands. - Compare before/after outcomes. - Block claims without pr
SKILL.mdUpdated Apr 19, 2026
ic1558/vera
testing
VerifiedTrustedCommunity
Use this skill when you need to perform a READ-ONLY forensic validation of a completed task (evidence), verify compliance against a TaskSpec, or issue a formal verdict (PASS/FAIL) before GMX approval. Strictly forbids modification or execution.
SKILL.mdUpdated Apr 19, 2026
ic1558/vera-qs
testing
VerifiedTrustedCommunity
Use this skill to perform forensic validation of IFC models, specifically focusing on Material Layer Sets, Classification compliance, and Quantity field presence. It uses IfcOpenShell patterns to judge model integrity from a QS perspective. Strictly read-only and verdict-only.
SKILL.mdUpdated Apr 19, 2026