AI Agent Workflow Collection

Post-change checklist to run after any set of code edits. Runs three steps in sequence: (1) code review via /simplify, (2) README consistency check and update, (3) git commit. Trigger on phrases like "review and commit", "after-changes", "wrap up changes", "commit my changes", or when the user says to remember to do this after every change.

Lorekeeper backlog management — ticket lifecycle, numbering, scripts, and conventions. Load this when filing tickets, moving ticket states, checking what's ready to work on, or onboarding to the project workflow.

Git commit convention for Lorekeeper — enforced by commit-msg hook. Covers author identity, ticket tags, and message format for both PM (Akane) and Dev roles.

GitHub App bot authentication — setup, token rotation, and cron refresh for…

Lorekeeper-specific BLOCKER patterns, severity tiers, and review checklist — used when reviewing any PR touching…

Engineering practices for developing the Lorekeeper codebase. Load this skill when working on Lorekeeper source code, fixing bugs, adding features, writing tests, or reviewing PRs. Covers architecture conventions, SQLite/LanceDB/Chroma quirks, testing patterns, and the verification standard for shipped changes. For backlog/ticket workflow, see backlog-management skill.

Discover and create typed relationships between memories using lorerecommendlinks. Use after inserting new memories, after a session reflection, or during periodic maintenance to connect orphaned memories. Surfaces high-confidence link candidates scored by cosine similarity, BM25 keyword overlap, entity overlap, and temporal proximity. The agent decides which candidates to confirm — lorerecommendlinks never writes.

Marketing workflow for Lorekeeper — README copy, manifesto, positioning, and multi-agent A/B testing of copy variations. Load this when working on any user-facing content: README, docs/manifesto.md, positioning, comparison tables, or launch copy.

Memorize important facts, user instructions, unique discoveries, and interesting knowledge into the Lorekeeper knowledge base. Use proactively whenever the agent encounters noteworthy information — domain knowledge, user preferences, architectural decisions, debugging insights, workflow instructions, or any fact worth recalling in future sessions. Always searches for related memories and creates links between them.

PM workflow for Lorekeeper. Load this when managing the backlog, filing tickets, reviewing dev work, or planning features. For ticket lifecycle, numbering, and script details, see the backlog-management skill.

Full session protocol for using Lorekeeper MCP tools correctly. Load at the start of any session that uses Lorekeeper. Covers when and how to call loresearch, loreinsert, loreupdate, lorereflect, and loreprocessedsessions across all three phases — session start, mid-session topic shift, and session end.

Reconcile and fact-check Lorekeeper memories against source materials, existing documentation, and internal consistency. Use when (1) the user provides reference materials to verify against, (2) the user requests a general knowledge audit, or (3) the user wants to verify specific topics. Updates memory scores and soft-deletes incorrect facts.

Search the Lorekeeper knowledge base and provide relevance feedback with confidence ratings. Use when the agent needs to recall domain knowledge, look up facts, or query the memory store. Ensures every search ends with a loreupdate feedback call (including confidence) to improve knowledge quality over time.

File a new Lorekeeper proposal ticket — create markdown, create GitHub issue, commit, push. Use when requesting a new feature, filing a bug, or submitting a product idea.

Bulk-rewrite commit titles on a PR branch to match [LKPR-N] format using filter-branch — avoids per-commit hook re-runs.