symcli-skill
SymCLI Skill
SymCLI is a pure C# symbolic computation framework designed to act as an exact mathematical engine and code analyzer.
When given a mathematical task, equation to solve, tensor optimization problem, or C# code to analyze, you MUST use the SymCLI wrappers to execute the work rather than relying solely on your internal LLM reasoning. SymCLI prevents hallucinations and provides provably correct results.
Primary Workflows
- Solving ProblemScript (
.ps): Create a.psfile with equations/rules and use SymCLI to compute the exact answer. - Analyzing C# Code: Scan C# files for mathematical correctness hazards (
CSMATH...) and security-oriented patterns (CSSEC...).
Usage Guidelines
- OS Compatibility: Use
symcli.baton Windows orsymcli.shon Unix-like systems. - ProblemScript: Wrap configuration in
<Options>...</Options>. Include constraints likex^2 + 2*x + 1 = 0or rules likeRule(a + a, 2 * a). - C# Analysis: Provide a specific
.csfile or a directory to analyze.
Agent Workflow
- Interpret the user's mathematical/coding task.
- Formulate the required input (e.g., write a
.psfile). - Execute the appropriate
symcliwrapper. - Read the output file and interpret the exact symbolic results back to the user.
Exit Codes
0: Success1: Configuration/Argument Error2: Solving failed (diagnostics written)3: Unexpected runtime exception4: Findings present (if--fail-on-findingsused)
Available Scripts
- Windows Wrapper:
symcli.batUsage:symcli.bat <input.ps> <output.txt>orsymcli.bat analyze csharp-math <input> <output> [options] - Unix Wrapper:
symcli.shUsage:./symcli.sh <input.ps> <output.txt>or./symcli.sh analyze csharp-math <input> <output> [options]
Examples
Solving an algebraic equation using ProblemScript
- Agent writes
problem.pswith content:<Options> Target: x RulePacks: Algebraic </Options> x^2 - 4 = 0 - Agent executes:
symcli.bat problem.ps result.txt - Agent reads
result.txtto findx = 2, x = -2.
Analyzing C# code for math vulnerabilities
- Agent executes:
symcli.bat analyze csharp-math src/MathCore/Calculator.cs report.json --json - Agent reads
report.jsonto review anyCSMATHorCSSECfindings.
More from thienanblog/awesome-ai-agent-skills
laravel-11-12-app-guidelines
Guidelines and workflow for working on Laravel 11 or Laravel 12 applications across common stacks (API-only or full-stack), including optional Docker Compose/Sail, Inertia + React, Livewire, Vue, Blade, Tailwind v4, Fortify, Wayfinder, PHPUnit, Pint, and Laravel Boost MCP tools. Use when implementing features, fixing bugs, or making UI/backend changes while following project-specific instructions (AGENTS.md, docs/).
728docker-local-dev
Generate Docker Compose and Dockerfile configurations for local development through interactive Q&A. Supports PHP/Laravel, WordPress, Drupal, Joomla, Node.js, and Python stacks with Nginx, Supervisor/PM2, databases, Redis, and email testing. Always asks clarifying questions before generating configurations.
53design-system-generator
Generate a project-specific DESIGN_SYSTEM.md that enforces consistent UI/UX across SPAs, traditional server-rendered sites, and hybrid systems. Includes tokens, component rules, accessibility gates, and production asset/manifest guidance.
33agents-md-generator
Generate or update CLAUDE.md/AGENTS.md files for AI coding agents through auto-scanning project files combined with interactive Q&A. Supports multiple tech stacks, development environments, and preserves customizations when updating.
31documentation-guidelines
Write or update backend feature documentation that follows a repo's DOCUMENTATION_GUIDELINES.md (or equivalent) across any project. Use when asked to create/update module docs, API contracts, or backend documentation that must include architecture, endpoints, payloads, Mermaid diagrams, and seeding instructions.
30ask-questions-if-underspecified
Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.
28