create-skill
Use when creating or modifying skills. Defines skill file structure, naming conventions, and integration patterns.
What this skill does
# Creating Agent Skills ## Overview Skills in for Agents provide reusable workflows and guidelines. This skill documents how to properly create new skills. ## Required File Structure These skills are designed to be Agentic Terminal User Interface (ATUI) agnostic. They live in the dotfolders for the agentic application examples include. ``` .claude/ .codex/ .gemini/ .opencode/ ``` Henceforth, we will use .atui/ as shorthand Every skill must have: ``` .atui/skills/skill-name/ ├── SKILL.md (REQUIRED - main skill file with frontmatter) ├── supporting-file.md (optional) └── templates/ (optional) ``` ## SKILL.md Requirements ### 1. YAML Frontmatter (REQUIRED) Every SKILL.md **must** start with YAML frontmatter: ```yaml --- name: skill-name description: Brief description of what this skill does and when to use it --- ``` **Frontmatter Rules:** - `name`: Lowercase letters, numbers, hyphens only (max 64 chars) - `description`: Explain WHAT it does + WHEN to use it (max 1024 chars) - Critical: ATUIs use description for automatic skill discovery ### 2. Main Content After frontmatter, elicit the human to add the skill instructions in markdown: ## Skill Naming Conventions **DO:** - ✅ Use lowercase letters - ✅ Use hyphens for word separation - ✅ Make names descriptive but concise - ✅ Keep under 64 characters **DON'T:** - ❌ Use uppercase letters - ❌ Use underscores - ❌ Use spaces - ❌ Use special characters **Examples:** - ✅ `create-skill` - ✅ `test-driven-development` - ✅ `write-commit-message` - ❌ `Create_Skill` - ❌ `test driven development` ## Description Best Practices The description is **critical** for skill discovery and invocation. **Purpose**: Help Claude decide whether to READ the skill, not to contain the rules themselves. **Format**: "Use when [specific trigger]. Defines [what's inside]." **Guidelines:** 1. **Start with trigger**: Begin with "Use when [action/situation]" 2. **Be concise**: Keep under 200 characters if possible 3. **Specific triggers**: Include clear conditions for when to invoke ## Supporting Files Skills can include additional files referenced from SKILL.md: ```markdown For Python testing: See [PYTHON.md](PYTHON.md) For JavaScript testing: See [JAVASCRIPT.md](JAVASCRIPT.md) ``` **Common Supporting Files:** - Language-specific guides (`PYTHON.md`, `JAVASCRIPT.md`) - Templates (`TEMPLATE.md`, `templates/spec-template.md`) - Examples (`EXAMPLES.md`) - Scripts (`scripts/helper.py`) Additionally register skills to the projects AGENTS.md file. ## Creation Checklist When creating a new skill: - [ ] Create directory: `.atui/skills/skill-name/` - [ ] Create `SKILL.md` with YAML frontmatter - [ ] Add `name` field (lowercase, hyphens, max 64 chars) - [ ] Add `description` field (WHAT + WHEN, max 1024 chars) - [ ] Ask human to add more details and and supporting files - [ ] Reference supporting files with relative paths - [ ] Test skill discovery with `/help` - [ ] Regiser skill to AGENTS.md ## Allows follow these practices ✅ **Always include frontmatter** - SKILL.md must start with YAML frontmatter ✅ **Write clear descriptions** - Description must explain WHAT and WHEN ✅ **Use correct filename** - Must be `SKILL.md` (uppercase) ✅ **Use proper naming** - Use lowercase letters and hyphens for separation ✅ **Be specific** - Clearly define when to use the skill ✅ **Keep content generic** - Do not make guidelines specific to the current project but Make SKILL.md and supporting files reusable across projects ✅ **Separate language specifics** - Put language/tech-specific details in separate files (PYTHON.md, RUST.md, etc.) ✅ **Provide complete templates** - Include full templates, not partial ones ✅ **Prioritize clear descriptions** - Avoid examples or use generic examples only when necessary for clarity ✅ **Work in small steps** - Only implement what was requested, collaborate incrementally in small steps with the user ✅ **Use positive framing** - Describe what to do rather than what not to do when writing guidelines but use negatives when it provides extra clarity ## Skill Integration Skills can reference other skills: ```markdown **Use the `specifying-requirements` skill for writing specifications.** **Use the `test-driven-development` skill for writing tests.** ``` This creates workflows that combine multiple skills. ## Testing Your Skill After creating a skill: 1. Run `/help` to verify it's discovered 2. Check the description appears correctly 3. Test invoking the skill in context 4. Verify supporting files load correctly ## Reference Official documentation: https://code.claude.com/docs/en/skills.md
Related in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.