Clippings skill harvester

Obsidian + Hermes agent intelligence economy kit: clippings harvest, skill optimization, token efficiency, verification, loop scoring.

Install

npx -y skills add w3rdist-creator/agent-intelligence-economy --skill clippings-skill-harvester

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

Copied from the file, not written here

Turn Obsidian clippings into routed synthesis, skill/runbook candidates, and killed/deferred items without rereading unchanged files.

1.0 KB, 181 tokens by cl100k_base, as published. Nobody here has run it

Use when processing a folder of saved clippings, source notes, exported articles, or raw notes.

Workflow:

Build/update a hash log so unchanged files are skipped.
For each new/changed clipping, capture title/path/hash/source metadata.
Classify claims, evidence quality, and reusable procedures.
Assign a disposition: use-now, route-project, skill-runbook, experiment, source-to-read, research-lead, defer, kill/archive, already-absorbed.
Draft skill/runbook patch candidates only for reusable procedures.
Record rejected/deferred ideas so they do not recur.
Write one dated synthesis report, not one note per clipping unless a source deserves it.
Verify paths, hashes, links, and absence of secrets.

Do not create a new skill for every interesting clipping.

Read from the repository

Just SKILL.md. No reference files, no scripts.