Skip to content
Agentmart
Submit a tool

vs-architect

Generate diverse solution variants with probability estimates using Verbalized Sampling (arXiv 2510.01171).

Skill by dimkurilo

IndexedMIT★ 7
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/dimkurilo-vs-architect

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Generate diverse solution variants with probability estimates using Verbalized Sampling (arXiv 2510.01171). Use when choosing between multiple approaches, debugging with unknown root cause, generating hypotheses or synthetic data, or when direct prompts produce repetitive mode-collapsed responses. Do NOT use for trivial scripts, factual queries, or stable production code.

Use cases: data, research

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/vs-architect

What's inside

Skill name
vs-architect
Description
Generate diverse solution variants with probability estimates using Verbalized Sampling (arXiv 2510.01171). Use when choosing between multiple approaches, debugging with unknown root cause, generating hypotheses or synthetic data, or when direct prompts produce repetitive mode-collapsed responses. Do NOT use for trivial scripts, factual queries, or stable production code.
License
MIT
Instructions
146 lines in SKILL.md · view on GitHub

Files (8)

  • .gitignore
  • README.md
  • README.ru.md
  • SKILL.md
  • hero-dark.svg · assets/
  • hero-light.svg · assets/
  • examples.md · references/
  • vs-theory.md · references/

SKILL.md (first lines)

# VS Architect — Agent Instructions

## Two-Phase Workflow

```
PHASE 1: VS Analysis
  Distribution prompt → k variants with probabilities → user selects

PHASE 2: Execution Prompt
  Selected variant → detailed implementation prompt (no VS)
```

---

## Step 0: Input Validation

- **Task context present** (3+ facts: task/constraints/what was tried/files/prompt) → proceed. Any format is valid.
- **No input or < 15 words** → ask: "Describe the task in detail: what needs to be done, constraints, what you've already tried."

---

## PHASE 1: VS Analysis

### Step 1: Classification

Classify the input along 4 axes (see `references/vs-theory.md`, Classification Axes section). Set UNKNOWN for missing axes.

Present classification to user and request confirmation before proceeding to Step 2:

```
TASK CLASSIFICATION:
- Complexity: [TRIVIAL | MODERATE | UNCERTAIN]
- Type: [CODE | STRATEGY | DIAGNOSTIC | CREATIVE | DATA]
- Variants: [FEW | MANY | SINGLE]
- Constraints: [YES | NO]

Confirm? If not — specify what to adjust.
```

### Step 2: Pattern Selection

Apply Decision Tree from `references/vs-theory.md`. Check rules strictly top-to-bottom; first match wins.

### Step 3: Execution Mode Selection

Apply Mode Mapping from `references/vs-theory.md`.

Additional rules:
- Complex mode → first tool call must be read-only (Assumption Checkpoint)
- 25+ tool calls → Business Outcome Verification pause
- ≥2 external systems with unverified API contracts → Pro
- Subagent task() calls → append 【思维模式要求】 injection

### Step 4: VS Prompt Construction

Use the template from `references/vs-theory.md` (Prompt Templates section) for the selected pattern.

Parameters:
- k (variant count): default 5. D → 5 (many rounds). B → 5. C → 3–5
- Probability threshold: B → p < 0.10 (diversity) or p > 0.5 (stability)
- Output format: headers + sections (human-readable), JSON (subagent)
- Language: preserve user's input language
- Do not use XML tags — headers are equally readable

---

## PHASE 2: Execution Prompt

### Step 5: Construction

After user selects a variant — build an execution prompt without VS:

```
Task: [selected variant from VS analysis]
Context: [what is already known, constraints]

What to do:
- [concrete steps]
- [which files/systems]
- [constraints]

Output format: [what is expected]

Agent1st: Mode: [mode], injection for subagent calls.
```

---

## Step 6: Output Format

```
## VS-ARCHITECT RESULT

### ANALYSIS
- Complexity: [...]
- Type: [...]
- Variants: [...]
- Constraints: [...]

### PHASE 1: VS ANALYSIS
Pattern: [A/B/C/D/E/F/G/none]
Mode: [...]

VS ANALYSIS PROMPT:
[generated prompt]

ACTION: Select the best variant and say "selecting variant N" — I will build the execution prompt.

### PHASE 2: EXECUTION PROMPT (after selection)
[to be built]

### EXECUTION
1. New DeepSeek V4 session: copy the VS prompt, get hypotheses, select
2. Current session: run VS prompt via subagent or direct dialogue
3. After selection: return — I will build the execution prompt
```

---

From dimkurilo/opencode-skills, MIT.

Signals

Stars
7
Forks
1
Open issues
0
Last commit (this folder)
Aug 4, 2026 (2 months ago)
Last release
Jul 16, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from dimkurilo

Cite this page

vs-architect skill. Agent Mart. https://agentmart.dev/skills/dimkurilo-vs-architect (last updated 2026-10-24)