Crap Analyzer
swingerman/engineer
A skill your agent uses to produce a risk-based refactor + test plan for recently-changed code on a diff/branch/PR by computing CRAP (complexity × untested) on changed methods.
Performs symbolic execution to detect potential errors by exploring execution paths, solving path constraints, and generating test inputs.
$ npx skills add ArabelaTso/Skills-4-SE --skill symbolic-execution-assistant -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ArabelaTso/Skills-4-SE symbolic-execution-assistant --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/symbolic-execution-assistant .claude/skills/symbolic-execution-assistant && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "symbolic-execution-assistant" agent skill from https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/symbolic-execution-assistant into .claude/skills/symbolic-execution-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "symbolic-execution-assistant", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/symbolic-execution-assistantType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ArabelaTso/Skills-4-SE --skill symbolic-execution-assistant -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ArabelaTso/Skills-4-SE symbolic-execution-assistant --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/symbolic-execution-assistant .agents/skills/symbolic-execution-assistant && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "symbolic-execution-assistant" agent skill from https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/symbolic-execution-assistant into .agents/skills/symbolic-execution-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "symbolic-execution-assistant", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ArabelaTso/Skills-4-SE --skill symbolic-execution-assistant -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ArabelaTso/Skills-4-SE symbolic-execution-assistant --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/symbolic-execution-assistant .cursor/skills/symbolic-execution-assistant && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "symbolic-execution-assistant" agent skill from https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/symbolic-execution-assistant into .cursor/skills/symbolic-execution-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "symbolic-execution-assistant", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ArabelaTso/Skills-4-SE.git --path skills/symbolic-execution-assistant--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ArabelaTso/Skills-4-SE --skill symbolic-execution-assistant -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ArabelaTso/Skills-4-SE symbolic-execution-assistant --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/symbolic-execution-assistant .gemini/skills/symbolic-execution-assistant && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "symbolic-execution-assistant" agent skill from https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/symbolic-execution-assistant into .gemini/skills/symbolic-execution-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "symbolic-execution-assistant", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ArabelaTso/Skills-4-SE symbolic-execution-assistantInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ArabelaTso/Skills-4-SE --skill symbolic-execution-assistant -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/symbolic-execution-assistant .github/skills/symbolic-execution-assistant && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "symbolic-execution-assistant" agent skill from https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/symbolic-execution-assistant into .github/skills/symbolic-execution-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "symbolic-execution-assistant", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ArabelaTso/Skills-4-SE --skill symbolic-execution-assistant -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ArabelaTso/Skills-4-SE symbolic-execution-assistant --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/symbolic-execution-assistant .opencode/skills/symbolic-execution-assistant && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "symbolic-execution-assistant" agent skill from https://github.com/ArabelaTso/Skills-4-SE/tree/main/skills/symbolic-execution-assistant into .opencode/skills/symbolic-execution-assistant/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "symbolic-execution-assistant", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
symbolic-execution-assistantPerforms symbolic execution to detect potential errors by exploring execution paths, solving path constraints, and generating test inputs.
Symbolic Execution Assistant is an agent skill from ArabelaTso/Skills-4-SE. Performs symbolic execution to detect potential errors by exploring execution paths, solving path constraints, and generating test inputs. Use when you need to analyze code for bugs like null dereferences, division by zero, buffer overflows, or assertion violations. Also use to generate test inputs that exercise different code paths, find edge cases, or explore all reachable program states. Supports Python, Java, and C/C++ through manual symbolic execution techniques and integration with tools like KLEE, angr…
Its SKILL.md is about 3.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/constraint_solving.md`, `references/path_exploration.md` and `references/tool_integration.md`).
It sits in Testing & QA, covering Test generation. It works with Java, Python and C++. The repository describes itself as: A curated list of 180+ useful Claude Skills for Software Engineering and resources for customizing AI for SE workflows. The licence is Apache-2.0.
7 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 4f38503. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
pipFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Symbolic Execution Assistant loads about 3.5k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 143 tokens; SKILL.md has 671 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from ArabelaTso/Skills-4-SE at commit 4f38503, republished under its Apache-2.0 licence (© ArabelaTso). 671 words, ~3,455 tokens.
.claude/skills/symbolic-execution-assistant/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.Perform symbolic execution analysis to detect errors and generate test inputs by exploring program paths with symbolic variables.
Symbolic execution executes code with symbolic values (representing any possible value) instead of concrete values. This allows exploring multiple execution paths simultaneously and detecting errors that might only occur with specific inputs.
Key Concepts:
Select the function and determine what to analyze for.
Questions to ask:
Example:
def calculate_discount(price, customer_type):
"""Calculate discount based on customer type."""
if customer_type == "premium":
discount = price * 0.2
elif customer_type == "regular":
discount = price * 0.1
else:
discount = 0
final_price = price - discount
return final_priceAnalysis goals:
Replace concrete inputs with symbolic variables.
Manual Symbolic Execution:
Input: price = α (symbolic), customer_type = β (symbolic)
Initial constraints: α ∈ ℝ, β ∈ String
Initial state: { price: α, customer_type: β }Using Python with Z3:
from z3 import *
# Create symbolic variables
price = Real('price')
customer_type = String('customer_type')
# Create solver
solver = Solver()Using Java with Symbolic PathFinder (SPF):
// Annotate symbolic inputs
public static void calculate_discount(double price, String customer_type) {
// SPF will make these symbolic via configuration
}Using C with KLEE:
#include <klee/klee.h>
int main() {
float price;
char customer_type[20];
klee_make_symbolic(&price, sizeof(price), "price");
klee_make_symbolic(customer_type, sizeof(customer_type), "customer_type");
calculate_discount(price, customer_type);
return 0;
}Trace through code, tracking constraints for each branch.
Manual Execution Example:
State 0: { price: α, customer_type: β }
Path constraint: (none)
Branch 1: customer_type == "premium"
State 1a: { discount: α * 0.2, final_price: α - (α * 0.2) }
Path constraint: β = "premium"
Branch 2: customer_type == "regular"
State 1b: { discount: α * 0.1, final_price: α - (α * 0.1) }
Path constraint: β ≠ "premium" ∧ β = "regular"
Branch 3: else
State 1c: { discount: 0, final_price: α }
Path constraint: β ≠ "premium" ∧ β ≠ "regular"Path Tree Visualization:
[Initial State]
price = α
customer_type = β
|
+----------------+----------------+
| | |
β = "premium" β = "regular" else
| | |
discount=α*0.2 discount=α*0.1 discount=0
Path 1 Path 2 Path 3For detailed path tree construction techniques, see references/path_exploration.md.
Look for states where errors could occur.
Common Error Patterns:
| Error Type | Check For | Example Constraint |
|---|---|---|
| Division by zero | denominator == 0 | x / y where y = 0 |
| Null dereference | variable == null | obj.method() where obj = null |
| Buffer overflow | index >= array.length | arr[i] where i ≥ len(arr) |
| Assertion violation | assertion condition false | assert x > 0 where x ≤ 0 |
| Integer overflow | result > MAX_INT | a + b > 2³¹-1 |
| Negative array index | index < 0 | arr[i] where i < 0 |
Example with Division by Zero:
def safe_divide(a, b):
if b != 0:
return a / b
else:
return NoneSymbolic execution:
State 0: { a: α, b: β }
Branch 1: b != 0
Path constraint: β ≠ 0
Result: α / β (safe)
Branch 2: b == 0
Path constraint: β = 0
Result: None (safe)
ERROR CHECK: Division by zero?
Constraint: β = 0 AND execution reaches "a / b"
Result: NO (the if-check prevents it)Example with Null Dereference:
public int getLength(String str) {
if (str != null) {
return str.length();
}
return 0;
}Symbolic execution:
State 0: { str: α }
Branch 1: str != null
Path constraint: α ≠ null
Result: α.length() (safe)
Branch 2: str == null
Path constraint: α = null
Result: 0 (safe)
ERROR CHECK: Null dereference?
Constraint: α = null AND execution reaches str.length()
Result: NO (protected by null check)Use constraint solver to find concrete values that exercise each path or trigger errors.
Manual Constraint Solving:
For simple constraints, solve manually:
Path 1 constraint: β = "premium"
Solution: price = 100, customer_type = "premium"
Path 2 constraint: β ≠ "premium" ∧ β = "regular"
Solution: price = 100, customer_type = "regular"
Path 3 constraint: β ≠ "premium" ∧ β ≠ "regular"
Solution: price = 100, customer_type = "guest"Using Z3 Solver (Python):
from z3 import *
# Define symbolic variables
price = Real('price')
customer_type = String('customer_type')
# Solve for Path 1: premium customer
solver = Solver()
solver.add(customer_type == StringVal("premium"))
solver.add(price > 0) # Add reasonable constraints
if solver.check() == sat:
model = solver.model()
print(f"Test input for Path 1: price={model[price]}, customer_type={model[customer_type]}")
# Solve for Path 2: regular customer
solver2 = Solver()
solver2.add(customer_type == StringVal("regular"))
solver2.add(price > 0)
if solver2.check() == sat:
model = solver2.model()
print(f"Test input for Path 2: price={model[price]}, customer_type={model[customer_type]}")Using Z3 for Error Detection:
# Check for division by zero
a = Int('a')
b = Int('b')
solver = Solver()
solver.add(b == 0) # Error condition: divisor is zero
solver.add(a > 0) # Additional context
if solver.check() == sat:
model = solver.model()
print(f"ERROR: Division by zero possible with a={model[a]}, b={model[b]}")For comprehensive constraint solving techniques, see references/constraint_solving.md.
Convert solved constraints into executable test cases.
Test Case Template:
import pytest
class TestCalculateDiscount:
# Path 1: Premium customer
def test_premium_customer(self):
"""Test premium customer path."""
# Generated from constraint: customer_type = "premium"
result = calculate_discount(100, "premium")
assert result == 80 # 100 - 20% discount
# Path 2: Regular customer
def test_regular_customer(self):
"""Test regular customer path."""
# Generated from constraint: customer_type = "regular"
result = calculate_discount(100, "regular")
assert result == 90 # 100 - 10% discount
# Path 3: Other customer type
def test_other_customer(self):
"""Test other customer type path."""
# Generated from constraint: customer_type ∉ {"premium", "regular"}
result = calculate_discount(100, "guest")
assert result == 100 # No discountJava Test Cases:
import org.junit.Test;
import static org.junit.Assert.*;
public class TestCalculateDiscount {
@Test
public void testPremiumCustomer() {
// Path 1: Premium customer
double result = calculateDiscount(100.0, "premium");
assertEquals(80.0, result, 0.01);
}
@Test
public void testRegularCustomer() {
// Path 2: Regular customer
double result = calculateDiscount(100.0, "regular");
assertEquals(90.0, result, 0.01);
}
@Test
public void testOtherCustomer() {
// Path 3: Other customer
double result = calculateDiscount(100.0, "guest");
assertEquals(100.0, result, 0.01);
}
}Document discovered paths, errors, and generated tests.
Report Template:
# Symbolic Execution Report: calculate_discount
## Function Analyzed
`calculate_discount(price, customer_type)`
## Paths Discovered
- **Path 1**: Premium customer (customer_type = "premium")
- Constraint: β = "premium"
- Behavior: 20% discount applied
- Test input: price=100, customer_type="premium"
- **Path 2**: Regular customer (customer_type = "regular")
- Constraint: β ≠ "premium" ∧ β = "regular"
- Behavior: 10% discount applied
- Test input: price=100, customer_type="regular"
- **Path 3**: Other customer types
- Constraint: β ∉ {"premium", "regular"}
- Behavior: No discount
- Test input: price=100, customer_type="guest"
## Errors Detected
None. All paths are safe.
## Generated Test Cases
3 test cases generated (see test_calculate_discount.py)
## Coverage
- Branch coverage: 100% (all 3 branches)
- Path coverage: 100% (all 3 paths)
## Recommendations
- Consider validating customer_type against known values
- Add explicit error handling for negative pricesZ3 Theorem Prover:
pip install z3-solverangr (Binary Analysis Framework):
pip install angrCrosshair (Symbolic Testing):
pip install crosshair-toolSymbolic PathFinder (SPF):
JDart:
KLEE:
# Uses LLVM bitcode
clang -emit-llvm -c program.c -o program.bc
klee program.bcSymbolic Execution Engine (SEE):
For detailed tool setup and usage, see references/tool_integration.md.
Path explosion occurs when the number of paths grows exponentially.
Mitigation Strategies:
Bounded Execution: Limit search depth
# Limit loop iterations
for i in range(min(len(array), 10)): # Max 10 iterations
process(array[i])Path Pruning: Eliminate infeasible paths early
if not is_feasible(path_constraint):
prune_path()State Merging: Combine similar states
# Merge states with same program counter
if state1.pc == state2.pc:
merged_state = merge(state1, state2)Selective Exploration: Focus on critical paths
# Prioritize paths with error conditions
if contains_error_check(path):
explore_first(path)Concolic Execution: Mix concrete and symbolic execution
# Start with concrete value, switch to symbolic when needed
x = 5 # Concrete initially
if complex_condition(x):
x = make_symbolic(x) # Switch to symbolic1. Bug Detection
2. Test Generation
3. Security Analysis
4. Equivalence Checking
For detailed information on specific topics:
© ArabelaTso, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 3 other files (references) in skills/symbolic-execution-assistant of ArabelaTso/Skills-4-SE.
Open the folder on GitHubat commit 4f38503
Symbolic Execution Assistant next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Symbolic Execution Assistant this skillArabelaTso/Skills-4-SE | 253 | — | ~3.5k | Automated safety check: Pass | Apache-2.0 | |
| Crap Analyzerswingerman/engineer | 154 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Approval Testing Toolkitlexler/skill-factory | 239 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| TDD GuideLeoYeAI/openclaw-master-skills | 2.2k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Polyglot Test Agentboshi-xixixi/TraeSkill | 276 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Fory Version Bumpapache/fory | 4.6k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 |
swingerman/engineer
A skill your agent uses to produce a risk-based refactor + test plan for recently-changed code on a diff/branch/PR by computing CRAP (complexity × untested) on changed methods.
lexler/skill-factory
Writes snapshot-style approval tests in Python, JavaScript, TypeScript or Java, comparing output against an approved file instead of writing individual assertions.
LeoYeAI/openclaw-master-skills
Test-driven development skill for writing unit tests, generating test fixtures and mocks, analyzing coverage gaps, and guiding red-green-refactor workflows across Jest, Pytest, JUnit, Vitest, and…
boshi-xixixi/TraeSkill
Generates comprehensive, workable unit tests for any programming language using a multi-agent pipeline.
apache/fory
Bump Apache Fory release or post-release development versions across Java, Kotlin, Scala, Python, Rust, Go, C++, C, Dart, JavaScript, Swift, integration tests, examples, and source docs.
trailofbits/skills
Scans a codebase for vulnerabilities with CodeQL's data flow and taint tracking in run-all or important-only modes, including data extensions for project-specific sources and sinks.
ArabelaTso/Skills-4-SE
Generate prioritized CVE watchlists and actionable security recommendations for repositories.
ArabelaTso/Skills-4-SE
Automatically migrate Python web applications between frameworks (Flask → FastAPI, Django → FastAPI).
ArabelaTso/Skills-4-SE
Generate test cases using metamorphic testing by applying transformations based on metamorphic properties.
ArabelaTso/Skills-4-SE
Instruments programs to capture execution traces specifically for reproducing reported bugs, enabling consistent replay and diagnosis of failures.
ArabelaTso/Skills-4-SE
Automatically migrate Spring MVC applications to Spring Boot.
ArabelaTso/Skills-4-SE
Instrument programs (Python, C/C++, Java) to capture snapshots of key program states at runtime, including variables, memory, and call stacks.
Categories
Performs symbolic execution to detect potential errors by exploring execution paths, solving path constraints, and generating test inputs. Symbolic Execution Assistant is an agent skill from ArabelaTso/Skills-4-SE. Performs symbolic execution to detect potential errors by exploring execution paths, solving path constraints, and generating test inputs.
Symbolic Execution Assistant fits situations like: you need to analyze code for bugs like null dereferences; division by zero; buffer overflows; assertion violations.
Run `npx skills add ArabelaTso/Skills-4-SE --skill symbolic-execution-assistant -a claude-code`. Or copy the skill folder (skills/symbolic-execution-assistant in ArabelaTso/Skills-4-SE) into .claude/skills/symbolic-execution-assistant in your project. Claude Code loads it when a task matches its description.
Run `npx skills add ArabelaTso/Skills-4-SE --skill symbolic-execution-assistant -a codex`. Or copy the skill folder (skills/symbolic-execution-assistant in ArabelaTso/Skills-4-SE) into .agents/skills/symbolic-execution-assistant in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ArabelaTso/Skills-4-SE --skill symbolic-execution-assistant -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/symbolic-execution-assistant, .gemini/skills/symbolic-execution-assistant, .github/skills/symbolic-execution-assistant and .opencode/skills/symbolic-execution-assistant in your project.
Going by SKILL.md and its folder, Symbolic Execution Assistant needs the command-line tools its instructions call (pip). Our summary lists: Python 3.
SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Symbolic Execution Assistant is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.5k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 7.7k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Symbolic Execution Assistant: Crap Analyzer (swingerman/engineer, 154 stars), Approval Testing Toolkit (lexler/skill-factory, 239 stars), TDD Guide (LeoYeAI/openclaw-master-skills, 2.2k stars) and Polyglot Test Agent (boshi-xixixi/TraeSkill, 276 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
ArabelaTso (a GitHub user) maintains it in ArabelaTso/Skills-4-SE, which has 253 GitHub stars. The repository holds 170 skills in this directory. The repository was last updated on August 21, 2026.
Source: ArabelaTso/Skills-4-SE on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.