vs-architect
Generate diverse solution variants with probability estimates using Verbalized Sampling (arXiv 2510.01171).
Skill by dimkurilo
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.
About
Use cases: data, research
Reviews
Write a reviewNo 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.
More from dimkurilo/opencode-skills
- 0.589score
multi-model-orchestration
dimkurilo
Coordinate 2+ AI models (DeepSeek V4 Flash, Qwen 3.8 Max, GLM 5.2, GPT-5.5) for parallel review, cross-validation, or bulk work via Orca orchestration.
SkillBFreshness: B★ 7Claude Code +9 - 0.589score
project-bootstrap
dimkurilo
Use when пользователь начинает новый проект, хочет расширить существующий, говорит "создай структуру", "разверни агента", "настрой проект", описывает новую…
SkillBFreshness: B★ 7Claude Code +9 - 0.580score
wave-spec
dimkurilo
Use when starting a sprint/wave that must not skip planning — user says "wave-spec", "spec first", "составь спеку/план", "interview then plan", or begins…
SkillBFreshness: B★ 7Claude Code +9
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
- Repository
- github.com/dimkurilo/opencode-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from dimkurilo
- 0.589score
multi-model-orchestration
dimkurilo
Coordinate 2+ AI models (DeepSeek V4 Flash, Qwen 3.8 Max, GLM 5.2, GPT-5.5) for parallel review, cross-validation, or bulk work via Orca orchestration.
SkillBFreshness: B★ 7Claude Code +9 - 0.589score
project-bootstrap
dimkurilo
Use when пользователь начинает новый проект, хочет расширить существующий, говорит "создай структуру", "разверни агента", "настрой проект", описывает новую…
SkillBFreshness: B★ 7Claude Code +9 - 0.580score
wave-spec
dimkurilo
Use when starting a sprint/wave that must not skip planning — user says "wave-spec", "spec first", "составь спеку/план", "interview then plan", or begins…
SkillBFreshness: B★ 7Claude Code +9
Cite this page
vs-architect skill. Agent Mart. https://agentmart.dev/skills/dimkurilo-vs-architect (last updated 2026-10-24)