Results for “refiner”

54 skills

refiner-automation

Automate Refiner operations through Composio's Refiner toolkit via Rube MCP, with dynamic tool discovery and connection management.

Process the Refinery merge queue - collect agent work, detect and resolve conflicts, merge in dependency order, and verify integration.

>- Skill Refiner, the eval-guided improvement loop for SKILL.md files. Runs the bootstrap, score, propose, apply, and status cycle as a thin wrapper over the published @intentsolutions/refiner CLI, proposing safe, minimal, bounded SKILL.md edits and accepting an edit only when a held-out eval score strictly improves with no regression on any other case. Ships a 3-layer cost-tiered hook architecture (sinker, line, hook) that gates skill quality at edit time, end of turn, and commit time. Use when improving an existing skill, refining a SKILL.md against measured behavior, bootstrapping an eval set for a skill, or gating skill edits before they ship. Trigger with "/j-rig", "refine this skill", "bootstrap an eval set", "propose a skill edit", "promote the candidate", or "skill refiner status".

More results

Use when an existing Antigravity skill has weak triggers, vague instructions, missing constraints, or poor structure and needs to be improved. Trigger on requests to rewrite, tighten, split, or review a skill for better routing and reuse.

matteobortolazzo

Refine a ticket interactively until it is ready for planning.

通用多轮迭代改进：对任意研究制品反复调用 /review → 解析反馈 → 修复 → 更新 wiki，直到达标

brycewang-stanford

VS-Enhanced Research Question Refiner - Prevents Mode Collapse and derives differentiated research questions Enhanced VS 3-Phase process: Modal question avoidance, alternatives presentation, differentiated RQ recommendation Use when: refining research ideas, formulating research questions, clarifying scope Triggers: research question, 연구 질문, PICO, SPIDER, research idea

Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking, producing a concrete one-pager.

42.4k · bundle

projectious-work

rag-engineering

Retrieval-Augmented Generation pipelines — ingestion, chunking, embedding, vector stores, retrieval, evaluation. Use when building a RAG pipeline, choosing chunking strategies or embedding models, debugging retrieval quality or hallucinations, evaluating an existing RAG system, or scaling/migrating vector stores.

code-simplifier

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality.

Train, evaluate, export, distill, quantize, or run inference for a TAO DINO 2D object detector using transformer-based detection with denoising training and multi-scale features.

deepstream-import-vision-model

Import object detection models from HuggingFace or NVIDIA NGC into a DeepStream pipeline with automated ONNX download, TensorRT engine build, custom parser, multi-stream benchmark, and PDF report generation.

prompt-optimizer

Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templates with evals.

deepstream-generate-pipeline

Builds and validates DeepStream GStreamer pipelines through an interactive questionnaire and a BM25 retrieval engine over 270+ verified pipelines.

finalize-agent-prompt

Refines and polishes prompt files by applying proven best practices for structure, wording, and clarity while preserving original intent and formatting.

thanakijwanavit

code-simplifier

Use this skill after completing code changes to review for reuse, quality, and efficiency. Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality.

Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or "stress-test my plan".

orch-refine-code

Restructure code while preserving behavior: confirm tests are green, refactor in small steps, keep tests green, review, and commit with a gated workflow.

lucassantana-dev

Build and debug Retrieval-Augmented Generation pipelines — chunking, embedding, retrieval, reranking

Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on \"ideate\", \"refine this idea\", or \"stress-test my plan\".

Runs three parallel reviewers to find code reuse, quality, and efficiency issues in a diff, then applies safe fixes and reports risky ones.

Design, tune, and evaluate production RAG pipelines with deterministic tools for chunking, pipeline design, and retrieval evaluation.

20.4k · bundle

Transforms vague ideas into structured, actionable concepts through guided divergent and convergent thinking, producing a markdown one-pager.

69.5k · bundle

Silently restructures natural-language prompts into the format best suited for the model currently executing the skill, then answers the rewritten version.

Extracts specifications from existing codebases by analyzing structure, data flows, and observable behaviors to document requirements in EARS format.

10.4k · bundle

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval.

brycewang-stanford

Systematic audit and review by Referee 2. Two modes — "deck" reviews slide presentations for rhetoric, visual quality, and compile cleanliness; "code" performs cross-language replication and econometric audit of empirical pipelines. Use when reviewing slides, auditing code, or verifying replication.

Use for thorough code review before merging changes.

Refines ideas iteratively. Refine ideas through structured divergent and convergent thinking. Use "idea-refine" or "ideate" to trigger.

Medicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, for compound prioritization and library filtering.

Apply medicinal chemistry filters for compound triage: drug-likeness rules (Lipinski, Veber, CNS), structural alert catalogs (PAINS, NIBR, ChEMBL), complexity metrics, and a custom query language for library filtering.

30.2k · bundle

Filters and prioritizes compound libraries in drug discovery using drug-likeness rules, structural alerts, complexity metrics, and a query language.

iterative-retrieval

Progressively refines context retrieval in multi-agent workflows to solve the subagent context problem.

theheavenlyd3mon

High-fidelity ASCII/Braille rendering via the Risomorphism-1911 pipeline — edge-aware downsampling, presets, quality gates, and eikon mirror workflows

Generates specific, implementable fixes for each vulnerability finding, producing code patches, configuration changes, dependency updates, and IaC fixes with before/after code and verification steps.

Manages vector embeddings with Pinecone for semantic search, recommendation, and RAG pipelines.