Pull and normalize GitHub PRs, issues, and commits into markdown files.
npx skills add https://github.com/mycelium-hq/ai-brain-starter --skill ingest-github
Please help me install this Agent Skill. Skill: ingest-github Source: https://github.com/mycelium-hq/ai-brain-starter/tree/main/skills/ingest-github Command: npx skills add https://github.com/mycelium-hq/ai-brain-starter --skill ingest-github
Ingests recent GitHub repository activity into the vault as markdown the graphify pipeline can read and the rest of the AI Brain Starter substrate (decision log, session-close cascade, hooks) can act on.
Invoke /ingest-github <owner/repo> [--days N] to ingest recent PRs, issues, and commits into the vault and store them at External Inputs/GitHub/<owner-repo>/<YYYY-MM-DD>.md.
High-intent search queries and answers about installing and using this skill.
To ingest GitHub activity into a markdown vault, you can pull and normalize recent pull requests, issues, and commits from a repository into a structured markdown file with generated frontmatter. The output is written to External Inputs/GitHub/<owner-repo>/<YYYY-MM-DD>.md.
To synchronize GitHub repository activity for a specific date range, invoke the ingestion command with the optional days parameter to fetch merged PRs, issues, and commits within that window. The process generates frontmatter including repo, date_range, item_count, ingested_at, and entity_ids.
Yes, you can re-run GitHub activity ingestion without creating duplicate vault files because the process supports idempotent re-runs. It writes one deterministic markdown file per repository per day, ensuring repeated synchronization operations overwrite rather than duplicate the output.
Yes, this GitHub ingestion method requires the GitHub MCP to fetch merged pull requests, issues, and commits. It relies on this protocol layer to pull the raw repository activity data before normalizing it into vault-friendly markdown.
The best way to store GitHub commits as structured markdown for querying is to ingest them into your vault with standardized frontmatter. This approach writes normalized activity data to dated files that the graphify pipeline and other substrate components can read and act on.
You should not use automated GitHub activity ingestion when you need real-time event streaming rather than daily batch synchronization, as the process writes one file per repository per day. It is designed for on-demand or scheduled knowledge ingestion, not continuous polling.
robertbr123Configure GitHub authentication via HTTPS tokens, SSH keys, or gh CLI.
NinatuziRoute and parse content inputs into a structured knowledge graph.
tiancaiamaoMaintain and query a personal wiki from structured Markdown sources.
georgernstgrafGrade student project repositories from Git commits, issues, and PR activity.
