refactor

Intelligent codebase exploration powered by codebase-memory-mcp. Natural language queries, change impact analysis, symbol graph traversal, and automatic brainstorming/planning integration.

7 skills · hooks

Quick, low-friction capture of notes, tasks, ideas, session summaries, and tech radar blips with Obsidian-style auto-linking

4 skills · 2 agents

Adaptive study coach with multi-gear learning sessions (Socratic, Explain, Guide, Check, Help) and spaced recall tracking via Feynman loops. Saves coaching notes with gap tracking and a recall log that shows improvement over time.

3 skills · 3 agents

Generate beautiful PDF/HTML shareable notes using Typst with 7 professional templates, infographics, and modern typography

4 skills · 2 agents

End-to-end commit hygiene: write atomic commits with style enforcement, review and consolidate them before push, validate the final history

4 skills · hooks

Spec-driven development workshop with beads wisps and thin stories: park, debug, shape, and build

3 skills · 1 agent · hooks

Build high-quality datasets and computer vision models. Visualize datasets, analyze models, find duplicates, run inference, evaluate predictions, and develop custom plugins.

18 skills · 2 commands · 1 MCP server

Test-driven development methodology with red-green-refactor cycles and code review

4 commands · 2 agents

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

Agent coordination and meta-programming - multi-agent orchestration, workflow automation, and safe refactor governance. Works best with other voltagent plugins installed.

Installs the general Sepia router plus five separate entries: sepia-write, sepia-review, sepia-refactor, sepia-recreate, and sepia-hemingway.

6 skills

13 MIT-licensed SKILL.md skills for everyday developer work: review-my-diff, repro-first-debugging, pr-description, safe-refactor, dependency-upgrade (shows the target version and files and waits for a yes before changing anything), explain-codebase, security-quick-review, prove-it-ran (make the agent show real test output before saying done), session-handoff, brag-doc-from-git, write-agents-md, agents-md-audit (with a small read-only Python audit script) and write-subagent. Skills only: no hooks, no MCP servers, no settings, no network calls.

13 skills