编程

Chatmosp Input Coordinator

试用

Entry skill of the chatMOSP system. Parses Chinese/English natural language input, recognizes three task types (MSR / KMC / parameter query), extracts metal, temperature, gas, partial pressure, steps, and size parameters, then dispatches parameter-builder, file-organizer, msr-generator, and kmc-simu

它能做什么

Entry skill of the chatMOSP system. Parses Chinese/English natural language input, recognizes three task types (MSR / KMC / parameter query), extracts metal, temperature, gas, partial pressure, steps, and size parameters, then dispatches parameter-builder, file-organizer, msr-generator, and kmc-simulator to complete the calculation. Triggers: user requests to run MSR or KMC, queries or adjusts parameters, or describes a metal catalysis system (Pd, Pt, Au, CO oxidation, water-gas shift, etc.).

技能文档

Language routing / 语言路由 Detect the user's language from the latest message.

  • If the user writes in English, continue with this English file and respond in English.
  • If the user writes in Chinese, read SKILL.md in this same directory and respond in Chinese. Always match the response language to the user's input language.

chatmosp-input-coordinator

1. Core Responsibilities

  1. Multilingual intent understanding — parse Chinese/English natural language input
  2. Task recognition — identify MSR / KMC / parameter-query task types
  3. Parameter extraction — extract metal, temperature, gas, partial pressure, steps, size
  4. Skill dispatch — chain parameter-builder → file-organizer → calculation engine
  5. Dialogue management — confirmation, clarification, error handling

2. Task Type Recognition

Three supported task types:

TypeMeaningTypical keywords
MSRMetal cluster structure generationcluster, structure, morphology, nanoparticle, MSR
KMCKinetic Monte Carlo simulationkinetic, simulation, TOF, steps, KMC, Monte Carlo
Parameter queryView or adjust parametersparameter documentation, show parameters, parameter setting

This ClawHub main test release supports only the legacy six-skill workflow above. If the user requests EKMC, slab KMC, Stepwise EKMC, server submission, or job monitoring, state that this main test release does not support those newer features and do not route to non-existent skills.

Confidence threshold: 0.70. Below threshold → actively ask user for clarification.

3. Parameter Extraction

3.1 Required parameters

ParameterRecognition rules
Metal elementPd / Pt / Au / Cu / Ni (Chinese & English names)
TemperatureSupports °C and K, auto-converts to K
PressurePa / kPa / MPa / atm
Gas speciesCO / O₂ / H₂ / N₂ / CO₂ / NO

3.2 Advanced parameters

  • Gas partial pressure: CO9 (CO pp = 9%), O18 (O₂ pp = 18%); multiple gases joined with _: CO9_O18
  • Cluster size: R50 (50 Å), R20 (default 20 Å)
  • Simulation steps: 200000000steps, 1e6 steps, one million steps

3.3 Extraction examples

User inputExtracted
Pd 在 CO 氧化环境下 200 摄氏度结构metal=Pd, T=473K, gases=[CO, O₂]
Pt structure under CO oxidation at 400 Celsiusmetal=Pt, T=673K, gases=[CO]
Run Pd MSR with CO9_O18 partial pressure at 473K, cluster size R50metal=Pd, T=473K, pp={CO:9,O₂:18}, R=50

4. Skill Dispatch

4.1 Routing table

MSR task        → parameter-builder → file-organizer → msr-generator
KMC task        → parameter-builder → file-organizer → kmc-simulator
Parameter query → parameter-builder

4.2 Cross-skill handoff (MUST follow)

  • MSR → KMC: After MSR completes, it produces ini.xyz. For KMC, kmc-simulator independently fetches the full KMC parameter set (nspecies, s1/s2, p1, e1-e7, li) from MOSP_database. Do NOT reuse MSR's input.json. See kmc-simulator.
  • Parameter modification: If user changes temperature, parameter-builder MUST recalculate gas entropy per §7.5.
  • Missing parameters: If key parameters (E_ads, w, gamma) are missing, parameter-builder calls literature-search to fill the gap (open-access journals prioritized). See literature-search.
  • Visualization: After MSR completes, msr-generator runs utils/paint.py to produce PNG + GIF. See msr-generator.
  • Wine environment: KMC tasks are checked and managed by kmc-simulator. See kmc-simulator.

4.3 Error handling

SituationAction
Missing parametersPrompt user, suggest reasonable defaults
Task ambiguityOffer 2–3 candidate scenarios
EKMC/slab/Stepwise/server requestedExplain that this main test release does not support that feature
Skill failureSuggest retry or degradation
Low confidenceActively clarify intent
Directory existsAsk before overwriting

5. Interaction

5.1 Task confirmation

After task recognition, MUST confirm with user. Display templates are defined in parameter-builder's "MSR / KMC parameter display format" section.

5.2 Clarification triggers

  • Vague temperature: "high temperature" → ask for specific value
  • Unknown gas ratio: CO oxidation needs CO+O₂ → ask for partial pressures
  • Unclear unit: "pressure" → ask Pa / kPa / atm
  • Unspecified metal/gas: list available options for the current task

6. Dependencies

  • chatmosp-parameter-builder — parameter completion + gas entropy calculation
  • chatmosp-file-organizer — directory structure creation
  • chatmosp-msr-generator — MSR calculation
  • chatmosp-kmc-simulator — KMC simulation
  • chatmosp-literature-search — literature search (when parameters missing)

7. File structure

chatmosp-input-coordinator/
├── SKILL.md       # Chinese reference
└── SKILL_cn.md    # This file (English)

ChatMOSP Companion Skills

This skill is part of the ChatMOSP skill set. For complete functionality, install the companion ChatMOSP skills from ClawHub when they are missing:

  • chatmosp-input-coordinator
  • chatmosp-parameter-builder
  • chatmosp-msr-generator
  • chatmosp-kmc-simulator
  • chatmosp-literature-search
  • chatmosp-file-organizer

If a required companion skill is unavailable, ask the user to install the missing ChatMOSP skill from ClawHub before continuing. Use the GitHub repository only as a fallback.

相关技能

Parameter building and management center of the chatMOSP system. Handles MSR / KMC parameter queries, intelligent completion, gas entropy calculation, MSR↔KMC interaction parameter conversion, and missing-parameter handling. Triggers: after input-coordinator identifies a task but before the calculat

1 次安装

KMC (Kinetic Monte Carlo) simulation engine of the chatMOSP system. Invokes kmc_standalone.py via Wine to run the Windows main.exe engine, executes catalyst surface reaction kinetic simulations, and produces TOF / coverage results.

1 次安装

File system manager of the chatMOSP system. Handles MSR / KMC task directory creation, intelligent naming (in `metal_gas-pp_T_K_P_Pa_R_size` format), and secure file operations (path-traversal protection, whitelist restriction). Triggers: after parameter-builder confirms parameters and before calcul

2 次安装

MSR (Multiscale Structure Reconstruction) calculation engine of the chatMOSP system. Invokes mosp-for-chatMOSP/utils/msr.py to generate metal cluster structures (Wulff construction), producing ini.xyz and {task_name}_cluster.xyz, then automatically generates PNG structure images and GIF rotation ani

2 次安装

Academic literature searcher of the chatMOSP system. When MOSP_database lacks matching parameters, searches open-access journals (Nature Communications, Science Advances, PNAS, etc.) and other academic resources to extract MSR/KMC parameters.

Catalysis literature search skill. Given a user-provided catalyst topic, reaction type, or material system, retrieve and organize relevant catalysis research papers from the open web (ScienceDirect, arXiv, OpenAlex, Google Scholar, etc.) and output structured literature-review information (literatur

1 星标