The library

agentic-ops-core · Shared loop discipline for all live-surface operations: read state, smallest reversible action, prove it, report exact status.

swarmwage-hire · Hiring specialized agents (image generation, transcription, charting) when they beat your native capability.

agentic-ops-orchestrator · Single entry point for operating any live surface: inbox, repo, tracker, billing, docs, alerts.

understand-chat · Answering codebase questions using a pre-built knowledge graph instead of reading source directly.

swarmwage-publish · Publishing agent capabilities to the Swarmwage registry so other agents discover and pay you in USDC.

agentic-os · Building persistent multi-agent operating systems that survive session restarts on Claude Code.

understand-dashboard · Visualizing knowledge graph structure as interactive architecture instead of raw JSON.

agents-sdk · Building agents using standardized SDK patterns and tool composition.

understand-diff · Analyzing code diffs to understand what changed and its graph-based impact zone.

ai-agents-architect · Designing agentic system architecture when multiple specialized agents are needed.

understand-domain · Extracting domain models from source when you need semantic structure, not syntax.

ai-agents-meta-core · Shared reference used by ALL agents in a cluster to enforce consistent discipline.

understand-explain · Explaining code concepts to humans using graph-derived semantic connections.

comfy-nodes · Managing ComfyUI workflow nodes when you need programmatic graph composition.

ai-agents-meta-orchestrator · Routing agentic tasks to specialized experts within a meta-orchestration layer.

understand-knowledge · Mapping large codebases when architecture documentation is stale or nonexistent.

ai-automation-workflows · Distributed multi-stage tasks where visibility and approval gates prevent unauthorized changes.

understand · Mapping large codebases when architecture documentation is stale or nonexistent.

ai-native-cli · Command-line tools that AI agents will invoke without human-in-the-loop monitoring.

ai-product · Production LLM features where validation and caching prevent probabilistic failures from reaching users.

ai-regression-testing · AI-assisted development where automated regression tests catch blind spots the same model would miss.

submission-qa · Teams automating repetitive tasks while maintaining control over execution and output quality.

airflow-dag-patterns · Teams automating repetitive tasks while maintaining control over execution and output quality.

td-feature-build · Teams automating repetitive tasks while maintaining control over execution and output quality.

algolia-search · Teams automating repetitive tasks while maintaining control over execution and output quality.

td-feature-design · Teams automating repetitive tasks while maintaining control over execution and output quality.

td-feature-integrate · Use for td feature integrate tasks. See artifact body for specific use cases.

android-clean-architecture · ## When to Activate

td-feature-qa · ## Live TD validation — when the bridge is up

angular-developer · ## When to Activate

add-imessage · Use for add imessage tasks. See artifact body for specific use cases.

animejs · **When to use this skill:**

add-karpathy-llm-wiki · Use for add karpathy llm wiki tasks. See artifact body for specific use cases.

td-feature-survey · Use for td feature survey tasks. See artifact body for specific use cases.

add-linear · - `LINEAR_BOT_USERNAME`: display name for the bot (used for self-message detection when using a Personal API Key)

td-feature-synthesize · | Profile | Leads with | When the user wants… |

add-macos-statusbar · Use for add macos statusbar tasks. See artifact body for specific use cases.

tdmcp-backlog-campaign · > **When NOT to use this:** one feature, or one small ad-hoc batch → `tdmcp-pipeline`.

api-connector-builder · Use this when the job is to add a repo-native integration surface, not just a generic HTTP client.

add-matrix · Use for add matrix tasks. See artifact body for specific use cases.

tdmcp-bridge-endpoint · A bridge feature is correct only when **four layers agree on one shape**: the

api-design · ## When to Activate

add-mnemon · Use for add mnemon tasks. See artifact body for specific use cases.

add-ollama-provider · When you want to run agent inference locally to cut API costs or experiment with open models.

tdmcp-coverage-writer · When you need to raise test coverage without weakening behavior under focused branch requirements.

add-ollama-tool · When you want the agent to offload work to local LLMs (inference, summaries) and optionally manage the model library.

add-opencode · When you want to run agents on cheaper models (DeepSeek, Qwen) or multi-provider failover without rewriting orchestration.

tdmcp-feature-discovery · When you want a prioritized feature backlog that reconciles roadmap, competitive gaps, and user ask without committing to build.

add-resend · When you want your agent to receive and respond to email asynchronously as a conversation channel.

tdmcp-interactive-projection-mapping · When you have an approved physical-interaction feature (camera/projector) and need specialized team orchestration beyond generic pipeline.