ajobi-uhc-seer

Repository of reusable agents, skills, and utilities designed for Claude integration and multi-agent orchestration.

200 skills · 85 agents · hooks

Enterprise multi-agent swarm platform enabling distributed autonomous workflows with RAG integration and Claude Code support.

200 skills · 3 MCP servers

Claude skill for coordinating multiple agents in collaborative novel writing. Manages character consistency, plot coherence, and multi-perspective narrative generation.

200 skills

Development framework featuring cognitive automation and collaborative agent systems. Redefines development through AI-powered agent coordination.

196 skills

Ready-to-use agent skills for research, science, engineering, analysis, finance, and technical writing across domains.

181 skills

AI-native development platform converting chat-based coding into structured workflows with code intelligence, spec-driven planning, and agent orchestration.

150 skills

Configure, run, and interpret HawkScan DAST results inside Claude Code. Generates stackhawk.yml configs, runs scans via CLI or Docker, and transforms security findings into prioritized fix tasks for your coding agent.

Configure, run, and interpret HawkScan DAST results. Generates stackhawk.yml configs, runs scans via CLI or Docker, and transforms security findings into prioritized fix tasks for your coding agent.

1 skill · hooks

Neural network interpretability tools including TransformerLens, SAELens, NNSight, and pyvene. Use when analyzing model internals, finding circuits, or understanding how models compute.

98 skills

Draws the 12 Houses of the Zodiac Tarot spread using cryptographic randomness to add 100+ bits of entropy to vague or underspecified planning. Interprets the spread to guide next steps. Use when feeling lucky, invoking heart-of-the-cards energy, or when prompts are ambiguous.

1 skill · 1 agent

Authoring and verification for LNPL, the language of the linkly LLM-native platform (declare entities, services and workflows; the compiler lowers them to a semantic IR that runs on an interpreter or compiles through MLIR to a native binary). LNPL's verb vocabulary is closed and absent from model training data, so a plausible word compiles into a step that silently does nothing. The plugin routes Claude to the lexicon generated from the compiler's own tables, surfaces lnpl compile diagnostics on every save, offers an independent reviewer subagent, derives spec cases, and gates completion on evidence.

5 skills · 1 agent · hooks

Analyze query performance with EXPLAIN plan interpretation, bottleneck identification, and optimization recommendations

1 skill · 1 agent