sancovp/dark-factory-live/0-2-5-understand-colbert-maxsim-operator
Claude Code and agent skill by sancovp/dark-factory-live
- community
Checking that the SKILL.md file is still in the repository.
[0.2.5] Maximum similarity operator that for each query token finds the highest-scoring document token via cosine simi
Install
npx vskill@latest install sancovp/dark-factory-live/0-2-5-understand-colbert-maxsim-operatorSKILL.md
The same SKILL.md was published earlier as sancovp/dark-factory-live/0-2-5-understand-colbert-maxsim-operator.
understand-colbert_maxsim_operator
CALL NUMBER: deep_dense_retrieval.colbert_maxsim_operator DEFINITION: Maximum similarity operator that for each query token finds the highest-scoring document token via cosine similarity, then aggregates across query tokens to produce document relevance score.
Invoke this skill to understand colbert_maxsim_operator down to its primitives. The RELATIVE ROOT below is the least-fixed-point closure of everything it bundles from — the full import cone, grouped by the lib each prim comes from. Projected from a prover-typed KB (MAP/SWI-Prolog consistency gate): every reference below resolves.
THE RELATIVE ROOT (the import cone, by lib)
from deep_dense_retrieval
- colbert_token_embedding (d1): Dense contextualized vector representation produced per token by an encoder model, preserving token identity and positional context for late interaction scoring.
- colbert_document_encoder (d2): Encoder producing per-token document embeddings from document passages, typically run offline and indexed for fast retrieval against query embeddings.
- colbert_query_encoder (d2): Encoder producing per-token query embeddings from input query tokens, enabling efficient single-pass encoding with late interaction against document tokens.
- colbert_representation_rank (d3): Rank dimension of per-token embeddings determining expressiveness of token-level similarity computation in late interaction framework.
CONSUMERS (what needs this)
colbert_late_interaction, colbert_token_aggregation
Projected from the `retrieval augmented generation architecture patterns` KB (207 concepts / 225 relations) — consistency-typed by MAP; the facet list after the colon IS the cross-lib dependency web.
_(leaf — this is an actual skill.)_
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingkbworld/state/modules/retrieval_augmented_generation_architect/skills/0-2-5-understand-colbert-maxsim-operator/SKILL.md
Popularity
- Repository stars
- 1
- 7-day trend score
- 8
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/sancovp/dark-factory-live/0-2-5-understand-colbert-maxsim-operator)