akunzai/agent-skills
8 skills128 installsGitHub
Install
npx skills add https://github.com/akunzai/agent-skillsSkills in this repo
1Mem Syncmem-sync synchronizes a project's .memories/ daily logs across machines over Git using a dedicated per-user branch and a background worktree, so the active development branch is never disturbed. It pulls other devices' logs at session start and pushes local logs at session end. A developer uses it to keep agent memory consistent across devices. The sync branch is derived from git user.email so developers on the same repo never collide.25installs2Mem AutoThis skill runs an automatic memory lifecycle for coding agents. It resumes open handoff entries, captures verified durable insights as dated Candidate notes, and delegates detailed work to mem-recall, mem-promote, mem-clean and mem-sync. It keeps short-term daily logs and per-task handoff files separate from long-term AGENTS.md/CLAUDE.md rules, applying a capture gate so only genuinely reusable knowledge is written.20installs3Mem Recallmem-recall searches an agent's short-term memory on demand, scanning project .memories/ and ~/.agents/memories/ for recent daily logs, candidate notes, and open handoffs. It uses grep to pull only matching lines so whole logs are not loaded into context. A developer uses it when resuming a task and needing prior state that AGENTS.md or CLAUDE.md did not auto-load.18installs4Mem CleanThis skill interactively cleans short-term agent memory. It deletes expired daily logs computed from the YYYY-MM-DD filename under a confirmed retention window and resolves cloud-drive conflict copies. It is destructive, so it always produces a dry-run plan and requires explicit confirmation, and it blocks cleanup of logs that still hold unresolved Candidate entries.16installs5Agents MdThis skill audits, creates and maintains AGENTS.md files that give AI assistants persistent project context. It scans for existing AGENTS.md and CLAUDE.md, evaluates quality against a rubric, and generates or improves the file with build/test/run commands, code style and workflows. It can optionally symlink CLAUDE.md to AGENTS.md for Claude Code compatibility and writes back durable learnings only with user approval.15installs6Mem Promotemem-promote reviews verified [Candidate] notes from daily logs and promotes the durable ones into long-term memory files like ~/.agents/AGENTS.md or a project AGENTS.md/CLAUDE.md. It also prunes those durable files for duplicates, obsoletes, and contradictions. A developer uses it when consolidating agent conventions so long-term memory stays lean and current. It only promotes facts that are verified, reusable, and stable, and it asks for confirmation before editing.14installs7Tidy Commitstidy-commits cleans up a local git branch's commit history before review or merge, turning WIP, fixup, and poorly ordered commits into a clear commit story while preserving the intended final tree. It classifies each commit as keep, squash, fixup, reword, reorder, split, or drop, then rebases non-interactively after showing the plan. A developer uses it before opening or merging a PR. It creates a backup ref and requires force-with-lease for any push.12installs8Mem Setupmem-setup wires each installed coding agent's native global memory file to a single canonical ~/.agents/AGENTS.md so Claude Code, Codex, OpenCode, Antigravity/Gemini, and pi all read the same durable cross-agent memory. It uses @import, symlink, or config instructions depending on each agent. A developer runs it to set up or refresh shared global memory across agents. The bundled script supports a dry-run plan before apply and backs up real files first.8installs