platform-mechanics
Convert verified algorithmic research into structured, machine-readable frameworks describing how social media platforms rank, reward, and penalize content. Provides factual, updatable platform rules for strategy agents (social-media, content, brand) to reference when developing or evaluating str...
Full skill instructions
Transform algorithmic research into actionable, version-controlled platform mechanics frameworks. This skill extracts verified data from /research/ and converts it into structured references (MECHANICS.md, SCHEMA.json, CHANGELOG.md) that enable strategy agents to make evidence-based decisions aligned with current platform realities.
Primary outputs saved to /skills/platform-mechanics/{platform}/:
Trigger this skill when:
Do not use for:
research skill instead)brand-strategy skill instead)The PMF follows a five-phase extraction and normalization process:
Pull verified data from completed research execution folders:
Input sources:
/research/{platform}-algorithm-updates/{YYYY-MM-DD}/RESEARCH.md/research/{platform}-algorithm-updates/{YYYY-MM-DD}/artifacts/citations.mdExtract these data types:
Convert findings into consistent schema format:
{
"signal_name": {
"type": "engagement|content|account|temporal",
"impact": "positive|negative|neutral",
"weight": <numerical_value>,
"confidence": <0.0-1.0>,
"evidence": ["citation_reference_1", "citation_reference_2"],
"last_verified": "YYYY-MM-DD",
"notes": "Additional context"
}
}
Confidence scoring:
Organize normalized data into strategic categories:
1. Content Type Performance
2. Engagement Signal Hierarchy
3. Penalty Triggers
4. Boost Factors
5. Temporal Dynamics
Generate human-readable MECHANICS.md with this structure:
# {Platform} Platform Mechanics
**Version:** {version_number}
**Last Verified:** {YYYY-MM-DD}
**Source Research:** /research/{platform}-algorithm-updates/{YYYY-MM-DD}/
## Quick Reference
[1-2 paragraph executive summary of current mechanics state]
## Content Type Rankings
### 1. Video
- Priority: [High/Medium/Low]
- Key threshold: [e.g., 10+ second watch time]
- Weight: [numerical if available]
- Best practices: [bullet points]
[Continue for each content type...]
## Engagement Signal Hierarchy
| Signal | Weight | Impact | Confidence | Notes |
|--------|--------|--------|------------|-------|
| [signal] | [value] | [+/-] | [0-1.0] | [context] |
## Algorithmic Penalties
[Structured list with severity levels]
## Boost Factors
[Prioritized list with activation conditions]
## Posting Strategy Implications
[Tactical recommendations derived from mechanics]
## Recent Changes
[Highlight what changed since last version]
## Evidence Sources
[Link to research citations]
Save outputs with proper version control:
Directory structure:
/skills/platform-mechanics/
├── {platform}/
│ ├── MECHANICS.md # Current version (human-readable)
│ ├── SCHEMA.json # Current version (machine-readable)
│ ├── CHANGELOG.md # Historical record
│ └── archive/
│ ├── v1-YYYY-MM-DD/
│ │ ├── MECHANICS.md
│ │ └── SCHEMA.json
│ └── v2-YYYY-MM-DD/
│ ├── MECHANICS.md
│ └── SCHEMA.json
Versioning rules:
Is there new algorithm research available?
├─ YES → Has research been verified and completed?
│ ├─ YES → Extract data using Phase 1
│ │ └─ Normalize data using Phase 2
│ │ └─ Categorize using Phase 3
│ │ └─ Generate MECHANICS.md using Phase 4
│ │ └─ Version and save using Phase 5
│ └─ NO → Wait for research completion
│
└─ NO → Use existing platform-mechanics/{platform}/ files
└─ Reference MECHANICS.md for strategy decisions
Input: /research/x-algorithm-updates/{YYYY-MM-DD}/
Output: /skills/platform-mechanics/twitter/
Key mechanics to extract:
Schema extensions for Twitter:
{
"feed_types": {
"for_you": {...},
"following": {...},
"explore": {...}
},
"grok_features": {
"conversational_customization": {...},
"ai_evaluation": {...}
}
}
To create mechanics for a new platform:
research skill/skills/platform-mechanics/{platform-name}/ directoryUser: "We just completed X algorithm research for October 2025. Update the platform-mechanics skill."
Process:
1. Read /research/x-algorithm-updates/2025-10-25/RESEARCH.md
2. Extract engagement weights, penalties, boosts, content types
3. Normalize into schema format with confidence scores
4. Categorize by PMF categories
5. Generate updated MECHANICS.md
6. Archive previous version
7. Save new version with date 2025-10-25
8. Update CHANGELOG.md with key changes
User: "Check if our Twitter content plan aligns with current algorithm priorities."
Process:
1. Read current /skills/platform-mechanics/twitter/MECHANICS.md
2. Review content plan against:
- Content type rankings (video > images > text)
- Engagement optimization (reply generation priority)
- Penalty avoidance (link handling, all-caps)
- Posting time recommendations
3. Flag misalignments
4. Suggest adjustments based on current mechanics
User: "Create a Twitter posting playbook using platform-mechanics."
Process:
1. Read /skills/platform-mechanics/twitter/MECHANICS.md
2. Read /skills/platform-mechanics/twitter/SCHEMA.json
3. Generate playbook sections:
- Optimal content types (prioritized list)
- Posting frequency/timing (from temporal factors)
- Engagement tactics (from signal hierarchy)
- Penalty avoidance checklist
- Account optimization (from credibility signals)
4. Include confidence levels and evidence sources
5. Add "last updated" date for shelf-life awareness
Before finalizing platform mechanics:
✅ Evidence verification
✅ Schema completeness
✅ Usability
✅ Version control
With research skill:
/research/{platform}-algorithm-updates/{date}/RESEARCH.mdWith brand-strategy skill:
With social-media workflow:
When to update platform mechanics:
Shelf-life awareness:
schema-template.json - Base template for platform mechanic schemas with all standard fields and confidence scoring structure.
extract-mechanics.md - Detailed step-by-step workflow for executing the Platform Mechanics Framework on new research.
Platform-specific mechanics implementation for Twitter/X, including current MECHANICS.md, SCHEMA.json, and version history.
Next steps after creating mechanics:
Comprehensive Spring Framework and Spring Boot best practices including dependency injection patterns, bean lifecycle and scopes, REST API development, Spring Data JPA, service layer design, Spring Security, testing strategies, caching, AOP, async processing, error handling, and common anti-patte...
Dispatch to the right problem-solving technique based on how you're stuck
TypeScript厳格モードによる型安全性設計を専門とするスキル。 📖 参照書籍: - 『Effective TypeScript』（Dan Vanderkam）: 型設計 📚 リソース参照: - `resources/Level1_basics.md`: レベル1の基礎ガイド - `resources/Level2_intermediate.md`: レベル2の実務ガイド - `resources/Level3_advanced.md`: レベル3の応用ガイド - `resources/Level4_expert.md`: レベル4の専門ガイド - `resources/di...
Deploys applications to cloud Kubernetes (AKS/GKE/DOKS) with CI/CD pipelines. Use when deploying to production, setting up GitHub Actions, troubleshooting deployments. Covers build-time vs runtime vars, architecture matching, and battle-tested debugging.
19-agent team structure, decision trees for agent selection, Haiku vs Sonnet model selection, and agent collaboration principles. Use when deciding which sub-agent to invoke, understanding team responsibilities, or learning multi-agent orchestration.
Converts architecture descriptions, module specs, or workflow docs into Mermaid diagrams. Use when visualizing brick module relationships, workflows (DDD, investigation), or system architecture. Supports: flowcharts, sequence diagrams, class diagrams, state machines, entity relationship diagrams,...
INVOKE FIRST before any code work. Validates git workflow (branch, issue, worklog) and checks approach. Use at START of every task and END before completing. Prevents skipped steps.
This skill should be used when working with browser-rendered artifacts (i.e. Bun, React/React Native) to proactively validate that development work on localhost is being built appropriately and to support debugging browser-rendered content. Use this skill after making frontend changes to verify t...
Lead Développeur - Coordination technique opérationnelle, code review, mentoring et livraison. Pair de web-dev-process au niveau OPÉRATIONS.
Monitor Docker workers, RQ queue health, and auto-scale workers (max 4). Use when: checking job progress, monitoring queue depth, scaling workers up/down, diagnosing slow processing, or waiting for jobs to complete. Referenced by data-quality skill during reprocessing.
Proactive quality guidance system that monitors artifact creation and provides real-time feedback on documentation quality
This skill should be used when the user wants to bump the version number in the workspace. It updates versions across all pyproject.toml files (root, tde, and tda packages) and the CHANGELOG.md to keep them synchronized.
Generate, edit, and beat-sync AI video with leading models in one workspace.
The world's fastest calendar for remote work
Transform Your Design with AI Designer by ImgCreator.ai
Revolutionizing Video Production with AI-Powered Creativity
Extend an image past the frame and let AI fill the new aspect ratio.
Discover your celebrity doppelgänger with StarByFace!
ChainClarity explains 700+ crypto whitepapers in plain English, with layered summaries, comparisons, research tools, alerts, and a $4.99 Pro plan.
Opus.ai: Revolutionize Your Web Experience