Build, manage, and improve the context that makes Hex's AI agents (Threads, Notebook Agent, Modeling Agent) accurate — endorsements, warehouse descriptions, workspace context, guides, and semantic models — then measure it with a dedicated eval engine that authors and runs eval suites, sources cases from real usage, and gates changes in a hex context preview. Publish via GitHub sync or the Hex CLI. Routes to the specific workflow instead of running full setup each time.
Plugin context-consultant from marketplace hex-skills in hex-inc/hex-skills. Commands read from the repo's manifest — yesterday.
context-consultantUse to build, manage, and improve the context that makes Hex's AI agents (Threads, the Notebook Agent, the Modeling Agent) accurate — endorsements & exclusions, warehouse descriptions, workspace context & guides, and semantic models. Covers standing context up from scratch, measuring it with a dedic
context-architectAdvise on and DRAFT Hex context assets. Use to decide what to build first, to write workspace context and guides, warehouse descriptions, endorsement plans, and semantic models, and to diagnose why an agent gave a wrong answer and prescribe the fix. Invoke on "write me a workspace guide", "my descri
eval-engineerAuthor, run, and maintain Hex eval suites — the measurement half of context work. Use to write eval cases and rubrics, run a suite and read the results honestly, source cases from real usage, convert an existing eval suite into Hex format, or gate a context change in a preview before it ships. Invok
Migrate Looker dashboards/Looks into Hex: translate LookML + Looker's generated SQL, let Hex's notebook agent build a generative app on gated SQL cells, and verify with a SQL-fidelity gate (numeric parity vs Looker) + a visual-QA loop.
1 skill
Migrate Tableau dashboards/workbooks into Hex: parse the .twb into a migration brief, let Hex's notebook agent build a generative app on gated SQL cells, and verify with a SQL-fidelity gate + a visual-QA loop.
1 skill
Long-term semantic memory for Claude Code, powered by OpenViking
5 skills · 1 command · 1 MCP server · hooks
Engineer an agent's forgetting, not just its remembering. Four deterministic stdlib scripts implement the four lenses of agent memory: a cost profiler that splits construction from query spend and reports cost per correct answer (construction energy exceeds total query energy across 300 queries in the Stanford characterization); an architecture picker that scores the four paradigm families — long-context, flat RAG, structure-augmented RAG, agentic — disqualifies on hard constraints, names the cost the winning choice makes you pay, and refuses to pick when the top two tie; a density auditor that classifies every record in a memory directory or JSONL export as FACT / SKILL / LOG / PROSE, finds near-duplicates, and flags stale wording; and a forgetting-policy linter that fails any design with no forgetting rule. Ships cs-memory-engineer agent, /cs-memory-engineering and /cs-forgetting-audit commands, 4 references, and a seven-question forcing worksheet.
1 skill · 2 commands · 1 agent
Persistent project planning files with lifecycle hooks that inject selected plan context. Automatic recovery uses project files only. Explicit catchup modes may read same-project local session records to emit aggregate counts or bounded nonce-framed excerpts. Optional gated mode can request continuation on capable hosts and never runs commands declared in Markdown. No network upload path. Installs across 60+ agents.
6 skills · 13 commands · hooks
GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.
72 skills · 72 commands · 64 agents · hooks
Diagnose context stuffing vs. context engineering in AI workflows.
1 skill
Agents for data engineering, machine learning, and AI development
12 agents
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.