From pkos
Internal skill — collects behavioral signals from Notion pipeline and Obsidian graph. Triggered by Adam cron (daily 10pm).
npx claudepluginhub n0rvyn/indie-toolkit --plugin pkosThis skill uses the workspace's default tool permissions.
Collect behavioral signals from the PKOS ecosystem for feedback loop analysis. Aggregates data from Notion pipeline flow, Obsidian graph density, and search behavior.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Uses ctx7 CLI to fetch current library docs, manage AI coding skills (install/search/generate), and configure Context7 MCP for AI editors.
Collect behavioral signals from the PKOS ecosystem for feedback loop analysis. Aggregates data from Notion pipeline flow, Obsidian graph density, and search behavior.
--days N: Signal collection window in days (default: 1)--verbose: Show detailed signal breakdown per sourceQuery Notion Pipeline DB for items in the collection window:
NO_PROXY="*" python3 ~/.claude/skills/notion-with-api/scripts/notion_api.py query-db \
32a1bde4-ddac-81ff-8f82-f2d8d7a361d7 \
--filter '{"and": [{"property": "Created", "date": {"on_or_after": "{start_date}"}}]}'
From the results, calculate:
Scan vault frontmatter for notes created in the window:
grep -rl "created: {date_pattern}" ~/Obsidian/PKOS/10-Knowledge/ ~/Obsidian/PKOS/20-Ideas/ ~/Obsidian/PKOS/50-References/ 2>/dev/null
For each note found:
tags from frontmatter → topic hotness distribution[[wikilinks]] in body → new links addedUse Grep to find backlinks:
Grep(pattern="\\[\\[{note-name}\\]\\]", path="~/Obsidian/PKOS", output_mode="count")
Combine all metrics and write to signal file:
mkdir -p ~/Obsidian/PKOS/.signals
Write ~/Obsidian/PKOS/.signals/{today}-feedback.yaml:
date: {today}
window_days: {N}
pipeline:
total_items: {count}
by_status:
inbox: {N}
processed: {N}
actionable: {N}
archived: {N}
archive_rate_by_source:
voice: {pct}
reminder: {pct}
domain-intel: {pct}
action_rate_by_source:
voice: {pct}
reminder: {pct}
graph:
new_notes: {N}
topic_hotness:
topic1: {count}
topic2: {count}
new_links: {N}
orphan_count: {N}
Present summary:
📊 PKOS Signal Report ({date}, {N}-day window)
Pipeline:
Total items: {N}
Action rate: {pct}% | Archive rate: {pct}%
Noisiest source: {source} ({archive_rate}% archived)
Knowledge Graph:
New notes: {N} | New links: {N} | Orphans: {N}
Hottest tags: {tag1} ({N}), {tag2} ({N})
Signal written to .signals/{date}-feedback.yaml
pkos:signal-aggregator agent for cross-source pattern analysis (optional, for weekly deep analysis)