Generalise — Security skill for Claude Code
Audit a lemma or definition for assumption-weakening opportunities — try mechanical weakenings, search the literature for the maximally-general form, auto-apply small safe changes, propose big changes.
How to install Generalise
Installs to ~/.claude/skills/cbirkbeck-mathlib-quality-generalise/SKILL.md
mkdir -p ~/.claude/skills/cbirkbeck-mathlib-quality-generalise && curl -fsSL https://raw.githubusercontent.com/CBirkbeck/mathlib-quality/HEAD/commands/generalise.md -o ~/.claude/skills/cbirkbeck-mathlib-quality-generalise/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Generalise does
name: generalise description: Audit a lemma or definition for assumption-weakening opportunities — try mechanical weakenings, search the literature for the maximally-general form, auto-apply small safe changes, propose big changes for user approval
/generalise — Weaken Assumptions to Maximise Generality
Given a single lemma or definition, find every way its hypotheses can be weakened. Combines two passes:
- Mechanical pass — drop unused hypotheses, swap typeclasses for weaker o
Alternatives in Security
- Security Scan Report — Generated: 2026-04-10 20:48 UTC Skills scanned: 134 Total findings: 836 Critical: 32 High: 50 Safe skills: 100 18.1k ★
- Memory Self Review — Mine recent agent history (claude-mem + usage stats) for recurring failures and repeated patterns, audit MEMOR 297 ★
- Curate Security Results — Run Security Tests & Curate Results — Public-Safe Snapshots 295 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Paper Trail Doctor
Audit the registry via the 19 mechanical invariants (I1-I19). Reports ERROR/WARN/INFO violations. Optional aut
Assumption Audit
Fundamental premise challenging with alternative framework generation
Universal Agent Skills
The world's most comprehensive, unified library of 279 production AI agent skills — featuring Garry Tan's GSta
Unity Audit
Full project health check — meta file integrity, missing references, assembly definition graph, code quality s
Appstore Approval Audit
Pass Apple review on the first try - a Claude Code skill that audits your iOS app (Swift, Expo/RN, Flutter) be
Audit Adapters
Read the AI Stack Expert agent definition at .claude/agents/ai-stack-expert.md to understand your role, expert
Related Agents
Us Bigmoney Analyzer
US stock big-money flow analyst. Scans recent insider transactions (Form 4 via Financial Datasets — LIVE again
Identification Critic
Applied econometrician specializing in causal identification. Reviews reduced-form strategies for assumption v
Bd Conclude
Writes the S8 conclusion. Answers S1's question directly, separates assumption dependence into parametric form