sickn33/agentic-awesome-skills v19.11.0

on GitHub

[19.11.0] - 2026-10-19 - "Three Reviewed Additions And A Continuity Checker"

Installable skill library update for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and related AI coding assistants. Adds 3 catalog skills and ships 2,715 skills.

Start here

• Install: npx agentic-awesome-skills@19.11.0
• Choose your tool
• Best skills by tool
• Bundles
• Workflows

Added

• ppl-personal-crm - use the ppl personal CRM over MCP to prepare for conversations, recall facts about people, log interactions and manage follow-ups. Resolves the exact person first, reads only what the task needs, writes only on explicit request, and never describes a draft as sent. risk: critical because it can write to personal records.
• story-bible-continuity - deterministically check a long manuscript against a story bible for name drift, age arithmetic, era anachronisms, unpaid foreshadowing and POV leaks, with file:line evidence and a manuscript-bug / stale-bible / retcon verdict per hit. Ships its stdlib-only Python checker as reviewable source in references/sbc-checker.md; no model, no network.
• keenable-search-mcp - search the public web with enforced site and published_after/published_before parameters, and read pages with an extraction prompt, through Keenable's keyless MCP server. States that queries, URLs and prompts go to Keenable, warns that extraction output is model-written rather than a quote, and never switches provider silently.

Merge batch

• Six open PRs were triaged, all of them touching catalog skills. Three merged: ppl-personal-crm, story-bible-continuity and keenable-search-mcp, each refreshed onto current main with its complete skill tree byte-identical to the reviewed head.
• Where the automated review did not produce a passing result, approval used the exact-head maintainer attestation path, bound to the full 40-character head SHA. manual-review-required is recorded as such and is not a Tessl pass.
• Three PRs remain open with one exact blocker each, and none of them was merged or bypassed: goal-instruction-writer carries skills/<id>/agents/openai.yaml and walkthrough.md, which the fork intake classifies as unapproved paths; taasky is an official skill whose source is published only as a docs-site well-known file, so the changed-skill evaluator rejects it for a missing source_repo; krexa 1.3.3 bumps the pinned source: field, which the provenance-identity gate blocks because the trusted ledger records source_repo renames only.

Review scope

Every new skill was reviewed in full at its exact submitted bytes, including bundled references and the embedded checker source in story-bible-continuity. The embedded checker was extracted, compiled and run against a two-chapter fixture to confirm it reports the intended findings and exits non-zero. ppl-personal-crm and keenable-search-mcp were reviewed statically; neither was exercised against its live hosted service during review. The broader catalog audit remains unfinished.

Thanks

Thanks to @dbhurley for ppl-personal-crm, @jiawood2006 for story-bible-continuity, and @keenableai for keenable-search-mcp, and to the upstream authors whose licensed material is included.