abstract-invariant-generator
Generates abstract invariants using domain abstraction — intervals, octagons, polyhedra, sign domains — to find invariants that concrete reasoning misses. Use when standard invariant inference fails, when the invariant involves relationships between multiple variables, or when verifying numerical code.
Install with Tessl CLI
npx tessl i github:santosomar/general-secure-coding-agent-skills --skill abstract-invariant-generator94
Quality
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Discovery
85%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong, technically precise description that clearly defines its specialized domain of abstract interpretation for invariant generation. It excels at completeness with explicit 'Use when' triggers and is highly distinctive. The main weakness is that trigger terms are heavily technical, which may not match how users naturally phrase requests for this type of analysis.
Suggestions
Add more natural user-facing trigger terms like 'prove loop bounds', 'static analysis', 'program verification', or 'prove variable ranges' to improve discoverability
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Generates abstract invariants using domain abstraction' with explicit techniques (intervals, octagons, polyhedra, sign domains) and a clear purpose 'to find invariants that concrete reasoning misses.' | 3 / 3 |
Completeness | Clearly answers both what ('Generates abstract invariants using domain abstraction') and when ('Use when standard invariant inference fails, when the invariant involves relationships between multiple variables, or when verifying numerical code') with explicit trigger conditions. | 3 / 3 |
Trigger Term Quality | Includes some relevant technical terms like 'invariants', 'numerical code', 'intervals', 'octagons', 'polyhedra', but these are specialized jargon. Missing more natural user phrases like 'prove loop bounds', 'verify program correctness', or 'static analysis'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly specialized niche focusing on abstract interpretation domains (intervals, octagons, polyhedra). The specific mention of 'domain abstraction' and failure conditions for 'standard invariant inference' creates clear differentiation from general verification or analysis skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill that efficiently teaches abstract invariant generation. It provides a clear domain selection table, a concrete 5-step algorithm, a detailed worked example comparing interval vs octagon domains, and explicit anti-patterns. The output format template ensures consistent, verifiable results.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, assuming Claude's competence with abstract interpretation concepts. Every section earns its place with no unnecessary explanations of basic concepts—it jumps straight into domain selection, algorithm steps, and worked examples. | 3 / 3 |
Actionability | Provides concrete, executable guidance with a clear algorithm (5 steps), a detailed worked example with iteration tables, domain selection criteria, and a specific output format template. The C code example and iteration tables are copy-paste ready for understanding. | 3 / 3 |
Workflow Clarity | The 5-step fixpoint iteration algorithm is clearly sequenced with explicit validation (step 5 widening/narrowing). The 'Do not' section provides error recovery guidance, and the 'Strength check' in the output format creates a feedback loop for domain adequacy. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear sections: domain table for quick reference, algorithm steps, worked example, decision guidance, anti-patterns, and output format. At ~100 lines, it's appropriately self-contained without needing external references. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.