SkillsAdd

posthog/ai-plugin · Official

context-layer-consolidation

Keep the context wiki coherent using the deterministic lint report queue

Installation

$ npx skills add https://github.com/posthog/ai-plugin
View on skills.sh ↗ GitHub repository ↗
Feature your product here Skill page unit · reach builders installing agent skills View pricing →

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

ad-campaign-consolidation Similar name
mbfinotti/advertising-skills

Evaluate a fragmented paid-ads account and recommend which campaigns and ad sets to merge, whic…

816 installs
knowledge-consolidation Similar name
huytieu/cog-second-brain

Build frameworks from scattered insights across all braindumps and notes

131 installs
doc-consolidation Similar name
athola/claude-night-market

Merges ephemeral report and analysis artifacts into permanent documentation. Use when LLM-gener…

106 installs

Also in this package

Other skills from posthog/ai-plugin · top by installs.

npx skills add https://github.com/posthog/ai-plugin
instrument-product-analytics 2 instrument-feature-flags 2 cleaning-up-stale-feature-flags 2 auditing-experiments-flags 2 creating-experiments 2 configuring-experiment-analytics 2 configuring-experiment-rollout 2 diagnosing-sdk-health 2 querying-posthog-data 2 copying-flags-across-projects 2

Browse all from posthog/ai-plugin

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 80
License MIT
Default branch main
Open issues 10
Status Active

History

  1. First recorded snapshot · 9 installs

SKILL.md

Context layer consolidation

Start with scripts/lint --report. Work the queue on the current dream branch.

Only edit sourced Markdown content under org/, areas/, decisions/, and existing Space pages. Never edit repository instructions, generated indexes, or scripts/; report structural failures in the run summary for the server to repair.

  • Remove unsupported synthesis.
  • Remove expired priorities unless historically significant; mark those status: historical.
  • Mark replaced decisions superseded and link their replacement.
  • Merge near-duplicates and leave a wikilink from the old subject.
  • Resolve disagreements only with evidence; leave the rest explicit.
  • Repair or intentionally retain ghost links, add sources, and split oversized pages.
  • Name every deletion in the commit message.

Keep this bounded and evidence-led. Run scripts/lint after editing.