add
Create a new Clawness rule from a natural language description.
Skill by fullymiddleaged
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/fullymiddleaged-add
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/add
What's inside
- Skill name
add- Description
- Create a new Clawness rule from a natural language description. Describe what you want enforced and this will generate the YAML rule file with proper tags, triggers, and examples.
- License
- MIT
- Instructions
- 50 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Create a New Rule
Generate a Clawness rule from the user's description.
## Process
1. **Understand the intent** — The user describes a coding practice they
want enforced. Parse their description for:
- What domain this falls under (nextjs, react, python, etc.)
- Whether it should be mandatory (always enforced) or ranked
- The severity (error for "must do", warning for "should do", info for "consider")
2. **Generate the YAML** — Create a properly formatted rule:
```yaml
id: DOMAIN-DESCRIPTIVE-NNN
domain: detected_domain
severity: error|warning|info
tags: [relevant, search, keywords]
triggers: [code, tokens, that, signal, relevance]
when: Clear condition for when this rule applies.
rule: >
The actual instruction, written clearly and specifically.
violation: "Concrete example of what NOT to do"
correct: "Concrete example of what TO do"
```
3. **Tags and triggers are critical** — These drive retrieval. Include:
- The concepts involved (e.g., "caching", "auth", "state")
- The code tokens someone would use (e.g., "useEffect", "fetch", "router")
- The framework/library names (e.g., "nextjs", "prisma", "zod")
4. **Save the rule** — Determine the right location:
- If `.clawness/rules/` exists in the project, save there (project-scoped)
- Otherwise, save to the global rules directory
- Ask the user to confirm before writing
5. **Test it** — Run a test query to verify the rule would be retrieved
for the kind of prompt it should match.
## Example
User says: "Always use server actions for form mutations in Next.js"
→ Generates a rule with:
- domain: nextjs
- tags: [server-actions, forms, mutations, use-server]
- triggers: [form, submit, action, mutation, create, update, delete]
- Saves to the appropriate rules directoryFrom fullymiddleaged/Clawness, MIT.
More from fullymiddleaged/Clawness
- 0.619score
audit-rules
fullymiddleaged
Review one domain of the Clawness rule corpus for correctness against current official documentation, then record what was established as a version stamp…
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
bootstrap
fullymiddleaged
Author a starter set of Clawness rules for a project whose stack Clawness ships no corpus for (Ruby, PHP, Elixir, Haskell, C#, Swift, Dart, Scala, Clojure…
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
claude-md
fullymiddleaged
Shrink an oversized CLAUDE.md.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
eval-set
fullymiddleaged
Build and run a project-specific retrieval eval so changes to your rules or base prompt are scored, not eyeballed.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
messaging
fullymiddleaged
Write or rewrite the product's customer-facing copy — landing page, hero section, CTAs, onboarding, empty states, pricing, app-store and marketing pages —…
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
openclaw-audit
fullymiddleaged
Trim an OpenClaw workspace's base system prompt.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
refresh
fullymiddleaged
Bring this project's Clawness rules up to date with the framework version it actually runs.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
security-audit
fullymiddleaged
Run a stateful red team / blue team security audit on the current project or a specific module.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
user-docs
fullymiddleaged
Write user documentation for a project by scanning its codebase — its UI screens and its public API/CLI — inferring what someone can actually do with it, and…
SkillAFreshness: A★ 5Claude Code +9 - 0.616score
status
fullymiddleaged
Show the current Clawness configuration: which rules are loaded, which agents are available, and how the hook is configured.
SkillAFreshness: A★ 5Claude Code +9 - 0.616score
review
fullymiddleaged
Run an adversarial code review on staged changes or a specific file.
SkillAFreshness: A★ 5Claude Code +9 - 0.616score
perf
fullymiddleaged
Run a performance audit on the project or a specific module.
SkillAFreshness: A★ 5Claude Code +9
Signals
- Stars
- 5
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 27, 2026 (4 months ago)
- Last release
- Oct 4, 2026 (24 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/fullymiddleaged/Clawness
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from fullymiddleaged
- 0.619score
bootstrap
fullymiddleaged
Author a starter set of Clawness rules for a project whose stack Clawness ships no corpus for (Ruby, PHP, Elixir, Haskell, C#, Swift, Dart, Scala, Clojure…
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
claude-md
fullymiddleaged
Shrink an oversized CLAUDE.md.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
eval-set
fullymiddleaged
Build and run a project-specific retrieval eval so changes to your rules or base prompt are scored, not eyeballed.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
messaging
fullymiddleaged
Write or rewrite the product's customer-facing copy — landing page, hero section, CTAs, onboarding, empty states, pricing, app-store and marketing pages —…
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
openclaw-audit
fullymiddleaged
Trim an OpenClaw workspace's base system prompt.
SkillAFreshness: A★ 5Claude Code +9 - 0.619score
audit-rules
fullymiddleaged
Review one domain of the Clawness rule corpus for correctness against current official documentation, then record what was established as a version stamp…
SkillAFreshness: A★ 5Claude Code +9
Cite this page
add skill. Agent Mart. https://agentmart.dev/skills/fullymiddleaged-add (last updated 2026-10-24)