agentleFS
Sign inStart free
loganware05loganware05/captains-compass-cursor/.cursor/skills/embedding-providers/SKILL.md

embedding-providers

Skill2 starsChanged 32 days agoMITView on GitHub

Rebuilds and queries fixture or OpenAI-compatible dense embedding indexes with TF-IDF always as fallback

  • Reads credentials

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Default path stays TF-IDF (COMPASS_EMBEDDING_PROVIDER unset or tfidf):

    line 24
  2. Distinctive:

    Never enable live embedding HTTP in CI.

    line 53

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Embedding Providers

Use this Skill when

The Captain wants opt-in dense embedding search for Knowledge Steward while keeping TF-IDF as the always-on fallback.

Inputs

  • Knowledge items under .agent/knowledge/items/
  • Env COMPASS_EMBEDDING_PROVIDER (tfidf default | fixture | openai-compatible)
  • For live HTTP: COMPASS_EMBEDDING_API_KEY (required), optional COMPASS_EMBEDDING_BASE_URL, COMPASS_EMBEDDING_MODEL, COMPASS_EMBEDDING_DIMENSIONS
  • Explicit rebuild CLI

Procedure

  1. Default path stays TF-IDF (COMPASS_EMBEDDING_PROVIDER unset or tfidf):

    ./scripts/rebuild-knowledge-vector-index.sh
./scripts/query-knowledge.sh --query "matcher tuning" --mode hybrid

  2. Opt into fixture dense embeddings (offline; no network):

    COMPASS_EMBEDDING_PROVIDER=fixture \
  ./scripts/rebuild-knowledge-embedding-index.sh
COMPASS_EMBEDDING_PROVIDER=fixture \
  ./scripts/query-knowledge.sh --query "matcher tuning" --mode vector

  3. Opt into OpenAI-compatible embeddings (Captain local only; never CI):

    export COMPASS_EMBEDDING_PROVIDER=openai-compatible
export COMPASS_EMBEDDING_API_KEY=...   # never commit
# optional:
# export COMPASS_EMBEDDING_BASE_URL=https://api.openai.com/v1
# export COMPASS_EMBEDDING_MODEL=text-embedding-3-small
./scripts/rebuild-knowledge-embedding-index.sh
./scripts/query-knowledge.sh --query "matcher tuning" --mode vector
  4. Missing dense index or live HTTP failure → automatic TF-IDF fallback.
  5. Never enable live embedding HTTP in CI.

Output

  • .agent/knowledge/embedding-index.json (dense; optional)
  • Existing .agent/knowledge/vector-index.json (TF-IDF; always rebuildable)
  • Optional hosted pgvector rows when Skill hosted-vector-db is active

Prohibited actions

  • Network embedding API calls in CI or default path
  • Committing API keys or logging Authorization headers
  • Removing or skipping TF-IDF fallback
  • Mutating matcher weights from embedding scores
  • Auto-rebuild on workstream close

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free