spectredeath/em-cubed/python-prolog-pipeline

Claude Code and agent skill by spectredeath/em-cubed

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Multi-surface pipeline combining Python for execution or evaluation, Prolog for logical rule verification, and

Install

npx vskill@latest install spectredeath/em-cubed/python-prolog-pipeline

SKILL.md

The same SKILL.md was published earlier as spectredeath/em-cubed/python-prolog-pipeline.

Purpose

Demonstrates a multi-surface skill with Python orchestration and Prolog validation. Each surface code block runs independently when the skill is executed.

Description

This skill provides graph pathfinding with two surface implementations:

  • Python: BFS pathfinding with graph traversal
  • Prolog: Declarative path finding with logical rules

When executed via the SkillExecutor, the caller chooses which surface to run. Both surfaces implement the same graph algorithm in their native paradigm.

Examples

Input: {"edges": [["a","b"], ["b","c"], ["c","d"]], "start": "a", "end": "d"}
Output: {"path": ["a","b","c","d"], "count": 4}

Implementation

Python Code
python
# Graph pathfinding with Python orchestration and Prolog logic
# This demonstrates a true multi-surface pipeline
edges = skill_input.get("edges", [])
start = skill_input.get("start", "")
end = skill_input.get("end", "")
if not edges or not start or not end:
result = {"error": "Missing input data"}
else:
prolog = context["surfaces"]["prolog"]
# 1. Reset and load rules into Prolog
prolog.execute_sync("retractall(edge(_, _)).")
prolog.execute_sync("path(X, X, [X]).")
prolog.execute_sync("path(X, Y, [X|Rest]) :- edge(X, Z), path(Z, Y, Rest).")
# 2. Assert facts from Python input
for src, tgt in edges:
prolog.execute_sync(f"edge({src}, {tgt}).")
# 3. Query Prolog for the path
query = f"path({start}, {end}, Path)"
res = prolog.execute_sync(query)
if res.get("status") == "ok" and res.get("result"):
# Take the first path found
found_path = res["result"][0]["Path"]
result = {
"path": found_path,
"count": len(found_path),
"method": "python-orchestrated-prolog-inference"
}
else:
result = {"path": None, "count": 0, "error": "No path found"}
result
`
### Prolog Code

% Graph pathfinding in Prolog (declarative) % Facts are asserted at runtime, then path rules apply

% Assert edges from input (done by executor wrapper)

% Path finding rules path(Start, End, [Start|Rest]) :- edge(Start, Next), path(Next, End, Rest). path(End, End, [End]).

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/spectredeath/em-cubed/python-prolog-pipeline/badge)](https://verified-skill.com/skills/spectredeath/em-cubed/python-prolog-pipeline)

Something wrong with this skill or its page? Tell us.