chore(data): index release 2026-06-22 — 42,068 skills (+ backlog tidy) - #65
Merged
Conversation
…w-up Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Rebuilt the FAISS index from the refreshed raw crawl data (March baseline + the partial June incremental crawl, which added skillsmp/skillhub records). 42,068 skills (up from 37,962 in the 2026-03-17 release). Sources: marketplace 28,253, topic 15,397, skillhub 12,448, clawhub 4,614, skillsmp 435. Embedded locally via Ollama qwen3-embedding:0.6b (SQ8-quantized IVF index, 43 MB). README/SKILL.md stat sentinels refreshed via pipeline/update_docs.py. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Fresh data/index release + backlog tidy.
qwen3-embedding:0.6binto an SQ8-quantized IVF index (43 MB). Sources: marketplace 28,253 · topic 15,397 · skillhub 12,448 · clawhub 4,614 · skillsmp 435.Changed (committed artifacts)
data/index.faiss,data/metadata.jsonl,data/version.txt— the new index (committed per repo convention).README.md,SKILL.md— stat sentinels refreshed viapipeline/update_docs.py.BACKLOG.md— pruned.Verification
scripts/search.py "deploy kubernetes" --no-json).version.txt: date 2026-06-22, skill_count 42068, index/metadata sha256 recorded.Notes
Built locally per the hybrid release model (CI is incremental-only and no-ops on the IVF index — PRD-005 amendment). Data is March baseline + the partial June crawl; a fuller refresh awaits wiring the new caches into the remaining crawlers so a full re-crawl is cheap (backlog). After merge: publish the
index-20260622GitHub Release artifact and bump the npm package.Risk & rollback
Low — data + docs only, no code change. Rollback = revert (restores the prior committed index).
🤖 Generated with Claude Code