Skill

rlm-distill-ollama

Distill repository files into the RLM Summary Ledger using agentic intelligence (fast) or Ollama (offline batch)

Install

Run in your terminal

npx claudepluginhub richfrem/agent-plugins-skills --plugin rlm-factory

Tool Access

This skill is limited to using the following tools:

BashReadWrite

Supporting Assets

View in Repository

assets/diagrams/rlm_late_binding_flow.mmd

assets/diagrams/rlm_tool_enrichment_flow.mmd

evals/evals.json

evals/results.tsv

references/BLUEPRINT.md

references/RLM_ARCHITECTURE.md

references/diagrams/distillation_process.mmd

references/diagrams/logic.mmd

references/diagrams/rlm-factory-architecture.mmd

references/diagrams/rlm-factory-architecture.png

references/diagrams/rlm-factory-dual-path.mmd

references/diagrams/rlm-factory-dual-path.png

references/diagrams/rlm-factory-workflow.mmd

references/diagrams/rlm_late_binding_flow.mmd

references/diagrams/rlm_mechanism_workflow.mmd

references/diagrams/rlm_mechanism_workflow.png

references/diagrams/rlm_tool_enrichment_flow.mmd

references/diagrams/search_process.mmd

references/diagrams/unpacking.mmd

references/diagrams/workflow.mmd

Skill Content

Similar Skills

cache-components

Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.

cache-components

138.7k

claude-opus-4-5-migration

2 files

Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.

claude-opus-4-5-migration

83.2k

hybrid-cloud-networking

1 file

Configures VPN and dedicated connections like Direct Connect, ExpressRoute, Interconnect for secure on-premises to AWS, Azure, GCP, OCI hybrid networking.

cloud-infrastructure

33.0k

Stats

Parent Repo Stars1

Parent Repo Forks1

Last CommitApr 4, 2026

Actions

View Source View Plugin View on GitHub View README

Path 1 -- Agent Distillation (default, fast, no Ollama)

The agent reads each file and writes a high-quality summary via inject_summary.py. Use for 1-50 files. The agent is faster and produces better summaries than local Ollama.

python3 ./scripts/inject_summary.py \ --profile project \ --file path/to/file.md \ --summary "Your agent-generated summary here."

Path 2 -- Ollama Batch (offline, bulk, 50+ files)

Requires Ollama running locally (ollama serve, model: granite3.2:8b).

# All files in profile scope python3 ./scripts/distiller.py --profile project # Single file python3 ./scripts/distiller.py --profile project --file path/to/file.md # Changed in last 2 hours python3 ./scripts/distiller.py --profile project --since 2

Profile

Flag

Cache file

Docs / protocols

--profile project

rlm_summary_cache.json

Plugins / scripts

--profile tools

rlm_tool_cache.json

Dependencies

This skill requires Python 3.8+ and standard library only. No external packages needed.

To install this skill's dependencies:

pip-compile ./requirements.in
pip install -r ./requirements.txt

See ./requirements.txt for the dependency lockfile (currently empty — standard library only).

/rlm-factory:distill

Summarize files into the RLM Summary Ledger. Two paths depending on context:

For detailed execution protocol, see agent: rlm-distill-agent

Path 1 -- Agent Distillation (default, fast, no Ollama)

The agent reads each file and writes a high-quality summary via inject_summary.py. Use for 1-50 files. The agent is faster and produces better summaries than local Ollama.

python3 ./scripts/inject_summary.py \
  --profile project \
  --file path/to/file.md \
  --summary "Your agent-generated summary here."

Path 2 -- Ollama Batch (offline, bulk, 50+ files)

Requires Ollama running locally (ollama serve, model: granite3.2:8b).

# All files in profile scope
python3 ./scripts/distiller.py --profile project

# Single file
python3 ./scripts/distiller.py --profile project --file path/to/file.md

# Changed in last 2 hours
python3 ./scripts/distiller.py --profile project --since 2

Profile	Flag	Cache file
Docs / protocols	`--profile project`	`rlm_summary_cache.json`
Plugins / scripts	`--profile tools`	`rlm_tool_cache.json`