Neura Market Logo

query-intel

Query rewriting + retrieval gating + outline-first synthesis. Use when a question needs decomposition (Step-Back/Least-to-Most), retrieve-or-skip decisions (CRAG/Self-RAG gates), o…

Gautham-AI-dev

@gautham-ai-dev

Install

$ openclaw skills install @gautham-ai-dev/query-intel

Query Intel

Question → better questions → gated retrieval → outline → cited report.

Commands (intel.py, stdlib)

python intel.py stepback "<question>"     # principle + sub-questions
python intel.py decompose "<question>"    # least-to-most ordered steps
python intel.py gate "<query>" --conf X   # retrieve|skip + reason
python intel.py outline "<topic>" --slots # outline w/ breakthrough slots

Rules

  • Rewriters are retriever-specific: lexical expansion → BM25, hypothetical-doc → dense. One universal rewriter fails (RL-QR).
  • Skip retrieval when confident AND answer is stable knowledge (Self-RAG/FLARE gate) — cuts poisoned/noisy exposure.
  • Outline-first always for reports: contradiction / vacancy / method-transfer / hostile-evidence slots before any prose.

Top skills in this category

self-improving agent

@pskoett

Captures and maintains learnings, errors, and corrections. Use when a command fails, the user corrects an assumption, a capability is missing, knowledge is outdated, or a better approach is found. Review relevant saved guidance before major tasks, reuse, and promotion; revalidate it according to wha

4.0k485k

Self-Improving + Proactive Agent

@ivangdavila

Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...

1.3k211k

ontology

@oswalpalash

Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...

659200k

Humanizer

@biostartechnology

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

714132k

Obsidian

@steipete

Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.

460111k