cc-market

Academic research toolchain -- systematic literature review, manuscript peer review, and IEEE reviewer discovery, backed by a single deterministic Python library and an accumulating local scholarly database.

4 skills · 1 command · 9 agents · 1 MCP server · hooks

Multi-provider agent fabric — any agent (claude / codex / …) invoking, orchestrating, and handing off to models of any provider. One `call` primitive (task/review/agent/image modes), parallel fan_out, and a minimal observe proxy that dissolves the Foundry-vs-tap conflict.

2 skills · 3 commands · 1 agent · 1 MCP server

REM sleep for Claude sessions — consolidate learnings into memory that converges without deletion: read-only recall, a derived index, crystallized rules. Includes memos: fact caching keyed on git blob hashes, listed on SessionStart/PostCompact.

4 skills · 1 command · hooks

Unattended server & long-running task supervision — the Claude front end over lab_commons.supervise. Health checks, anomaly detection, auto-repair and multi-channel alerting. One TOML config per project; the machinery is in the shared library.

1 skill · 3 commands

LaTeX writing assistant — compile workflow, academic writing style, and word counting (texcount) for LaTeX documents. Per-section word counts with references excluded, targets and JSON output.

2 skills · 1 agent

Post-feature sharp review — 3 parallel reviewers with schema enforcement, merge findings, sync structured task list with memory cross-references.

1 skill · 1 agent · hooks

Iterative TDD review→fix loop — each round critiques the codebase, fans out fix agents over disjoint files, verifies, gates hard calls to the human, keeps tests green, and commits. Severity-based convergence with safety caps.

1 skill