Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub Β· AI
input classification
Deterministic rule-based system for classifying clarified input into a single primary task category and assigning execution complexity. Use when the Main Age...
skill openclawclawhub Free
Deterministic rule-based system for classifying clarified input into a single primary task category and assigning execution complexity. Use when the Main Age...
β¬ 0 downloads β
0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- SKILL.md, references/classification-models.md, references/system-integration.md
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 1.0.0
Provenance
- Publisher
- omprasad122007-rgb
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
1. Skill Name
Input Classification System Identifier: input-classification-system
2. Version
1.0 This is the initial release of the Input Classification System skill.
3. Skill Purpose
Provide a deterministic, rule-based classification system that enables the Main Agent to categorize clarified user input into exactly one primary task category, assign execution complexity, assess risk level, and determine confidence score before any task decomposition or execution planning occurs. Measurable Objectives: Achieve 100% single-category classification (no ambiguous multi-category outputs) Provide deterministic tie-breaking for all edge cases Assign complexity levels using measurable thresholds Calculate confidence scores with explicit formulas Route ambiguous inputs to clarification with specific triggers
4. What This Skill Does
Classifies clarified input into exactly one primary category from a fixed list Assigns complexity level based on measurable operation counts and time estimates Calculates risk level based on impact scope and reversibility criteria Computes confidence score using explicit scoring factors Determines if input requires additional clarification Sets the appropriate state transition after classification Applies deterministic tie-breaking logic when multiple categories match Validates that input has been clarified before classification Logs all classification decisions with full context Provides secondary tags for additional context (maximum 3) Enforces boundary definitions between categories Triggers escalation for high-risk or low-confidence classifications Prevents misclassification through explicit rules Outputs structured ClassificationResult for downstream systems Maintains audit trail for all classification decisions
5. What This Skill Must Not Do
Must not perform task decomposition or breakdown Must not solve or execute any tasks Must not create execution plans or strategies Must not apply emotional reasoning or sentiment analysis Must not assign multiple primary categories to a single input Must not overlap with Clarification System responsibilities Must not modify the original input content Must not make assumptions about user intent without explicit indicators Must not skip complexity assessment for any classification Must not bypass risk assessment for any classification Must not assign confidence scores below threshold without escalation Must not classify inputs that have not been clarified first Must not use probabilistic or non-deterministic classification methods Must not ignore tie-breaking rules when categories conflict Must not proceed to execution without setting state transition
6. Activation Conditions
This skill activates when ALL of the following conditions are met: Clarification Complete: Input has been processed by the Clarification System and marked as clarified No Pending Questions: No outstanding clarification questions remain Classification Not Yet Performed: Input has not been previously classified Valid Input Structure: Input contains recognizable task indicators Pre-Activation Checklist: Input marked as "clarified" by Clarification System No clarification questions pending Input contains actionable request Input is not empty or malformed Do NOT activate if: Input is still being clarified Input is a clarification question itself Input is a response to a clarification question Input has already been classified
7. Classification Categories
The following 15 categories form the fixed classification list: CategoryCodeDescriptionCODE_GENERATIONCGWriting, modifying, or generating source codeCODE_REVIEWCRReviewing, analyzing, or auditing existing codeDEBUGGINGDBIdentifying and fixing bugs, errors, or issuesDATA_ANALYSISDAAnalyzing, processing, or visualizing dataFILE_OPERATIONSFOReading, writing, moving, or managing filesDOCUMENTATIONDCCreating or updating documentationREFACTORINGRFRestructuring code without changing behaviorTESTINGTSWriting, running, or managing testsDEPLOYMENTDPDeploying applications or infrastructureRESEARCHRSInvestigating, searching, or gathering informationCONFIGURATIONCFSetting up or modifying configurationsCOMMUNICATIONCMDrafting messages, emails, or communicationsCONVERSIONCVTransforming data or files between formatsANALYSISANGeneral analysis not covered by other categoriesPLANNINGPLCreating plans, strategies, or roadmaps Category Priority Order (for tie-breaking): DEBUGGING (highest - immediate attention needed) DEPLOYMENT CODE_GENERATION REFACTORING TESTING CODE_REVIEW DATA_ANALYSIS CONFIGURATION FILE_OPERATIONS CONVERSION DOCUMENTATION RESEARCH ANALYSIS COMMUNICATION PLANNING (lowest)
CODE_GENERATION vs CODE_REVIEW
CODE_GENERATION: Input requests creating new code or modifying existing code CODE_REVIEW: Input requests analysis of existing code without modifications Boundary: If modification is implied, classify as CODE_GENERATION
CODE_GENERATION vs REFACTORING
CODE_GENERATION: Creating new functionality or features REFACTORING: Restructuring existing code without new functionality Boundary: "Improve performance" without feature change = REFACTORING
DEBUGGING vs CODE_GENERATION
DEBUGGING: Input explicitly mentions errors, bugs, or failures CODE_GENERATION: Input requests new features without error context Boundary: "Fix this bug" = DEBUGGING; "Add error handling" = CODE_GENERATION
DATA_ANALYSIS vs ANALYSIS
DATA_ANALYSIS: Input involves data processing, statistics, or visualization ANALYSIS: Input involves general analysis of concepts, requirements, or situations Boundary: If data files/sets are mentioned = DATA_ANALYSIS
FILE_OPERATIONS vs CONVERSION
FILE_OPERATIONS: Input requests file management (read, write, move, delete) CONVERSION: Input requests format transformation between file types Boundary: "Convert X to Y format" = CONVERSION; "Read file X" = FILE_OPERATIONS
RESEARCH vs ANALYSIS
RESEARCH: Input requests information gathering or investigation ANALYSIS: Input requests evaluation or assessment of known information Boundary: "Find information about X" = RESEARCH; "Evaluate X" = ANALYSIS
TESTING vs CODE_GENERATION
TESTING: Input specifically requests test creation or test execution CODE_GENERATION: Input requests production code Boundary: "Write tests for X" = TESTING; "Write X with tests" = CODE_GENERATION (primary)
CONFIGURATION vs DEPLOYMENT
CONFIGURATION: Input requests setup of settings or configurations DEPLOYMENT: Input requests deployment to environments or infrastructure Boundary: Local setup = CONFIGURATION; Remote/environment setup = DEPLOYMENT
9. Single-Primary-Category Rule
Rule: Every classified input MUST have exactly one primary category.
Enforcement Rules
No Multi-Category Output: Never output multiple primary categories Tie-Breaking Required: When multiple categories match, apply tie-breaking logic Category Exclusivity: Primary category is mutually exclusive with other primary categories
Tie-Breaking Logic
When input matches multiple categories, apply in order: Step 1: Keyword Dominance Count explicit keyword matches for each candidate category Category with highest keyword count wins If tied, proceed to Step 2 Step 2: Action Verb Analysis Identify primary action verb in input Map action verb to category using verb-to-category mapping If still tied, proceed to Step 3 Step 3: Priority Order Apply category priority order (see Section 7) Higher priority category wins Step 4: Default Fallback If all steps fail, default to ANALYSIS category
Tie-Breaking Example
Input: "Debug and fix the error in the authentication code, then add logging" Keywords: DEBUGGING (debug, fix, error), CODE_GENERATION (add, logging) Action Verb: "Debug" (primary action) β DEBUGGING Result: DEBUGGING (primary), secondary_tags: [CODE_GENERATION]
10. Secondary Tag Rules
Secondary tags provide additional context without affecting primary routing.
Rules
Maximum 3 Tags: No more than 3 secondary tags per classification No Primary Duplicate: Secondary tags cannot duplicate primary category Related Categories Only: Secondary tags must be from the fixed category list Relevance Threshold: Only add tags with >50% keyword match confidence
Secondary Tag Selection Process
Identify all categories with keyword matches (excluding primary) Calculate relevance score for each (0.0-1.0) Sort by relevance score (descending) Select top 3 with score > 0.5 Add to ClassificationResult
When to Apply Secondary Tags
Input contains multiple distinct sub-tasks Input references multiple technology domains Input implies follow-up work in other categories Input has context from previous interactions in different categories
When NOT to Apply Secondary Tags
Input is single-focused with no additional context Relevance scores are below threshold (0.5) Would duplicate primary category Would exceed 3-tag limit
Secondary Tag Examples
InputPrimarySecondary Tags"Debug the API and update the docs"DEBUGGING[DOCUMENTATION]"Refactor the auth module and add tests"REFACTORING[TESTING]"Analyze sales data and create a report"DATA_ANALYSIS[DOCUMENTATION, COMMUNICATION]"Fix this bug"DEBUGGING[]
Classification Models Reference
For detailed complexity, risk, confidence, and state transition models, see classification-models.md. For system integration, failure conditions, logging, and examples, see system-integration.md.
Category context
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
3 Docs
- SKILL.md
- references/classification-models.md
- references/system-integration.md