deduplication skills

30 tagged deduplication, measured the same way as everything else here.

Browse within: idempotency 15model-checking 15open-source 15Data Curation 5Data Processing 5GPU Acceleration 5LLM Training Data 5Multimodal 5NVIDIA 5NeMo Curator 5PII Redaction 5Quality Filtering 5RAPIDS 5

bash

01

ZenSystemAI/Zengram

Skill Claude CodeCodex

Command-line interface for the Zengram system. Use this to store, search, and retrieve shared memories from any terminal-based agent or script.

60 9d ago A 0 tokens original MIT

sessionend

02

ZenSystemAI/Zengram

Skill Claude CodeCodex

End-of-session ritual that turns sessions into institutional memory via Zengram. Detects repeatable workflows worth capturing as skills AND mistakes/corrections worth capturing as CLAUDE.md rules. Reflects honestly, stores to Zengram, updates local memory, spots workflow patterns, and proposes rule updates. Use when…

60 9d ago A 147 tokens original MIT

skill-compact

03

JuanJoseGonGi/skill-compact

Skill Claude CodeCodex

Analyze, deduplicate, and restructure agent skills to follow agentskills.io best practices. Merges duplicate skills, extracts shared content into references, reduces SKILL.md sizes, and tracks original sources for update-then-recompact workflows. Use when the user mentions "compact skills", "deduplicate skills"…

3 6mo ago A 103 tokens original MIT

skill-alpha

04

JuanJoseGonGi/skill-compact

Skill Claude CodeCodex

A sample skill for testing. Use when the user mentions alpha testing, widget creation, or component design patterns.

3 6mo ago A 25 tokens original MIT

skill-beta

05

JuanJoseGonGi/skill-compact

Skill Claude CodeCodex

Another sample skill for testing. Use when the user wants to create widgets with advanced features or mentions beta testing.

3 6mo ago A 25 tokens original MIT

flowguard

08

liuyingxuvka/FlowGuard

Skill Claude CodeCodex

Unified FlowGuard entry for behavior/state models, unclear routes, cross-route work, and kernel gates; use a clear public satellite directly.

2 5d ago A 30 tokens original MIT