max-sixty

Tend-specific guidance for tend CI workflows. Adds non-standard workflow inclusion for usage analysis and repo conventions on top of the generic tend-* skills.

Outcome-based analysis of tend's CI behavior — checks whether tend's outputs were accepted or rejected, escalating to session logs only when outcomes look wrong.

Reviews a pull request for code quality and correctness. Use when asked to review a PR or when running as an automated PR reviewer.

Generic CI environment rules for GitHub Actions workflows. Use when operating in CI — covers security, CI monitoring, comment formatting, and investigating session logs from other runs.

Investigates a specific tend GitHub Actions run by downloading its session-log artifacts and parsing the JSONL traces. Surfaces which skill tend loaded, what tools it called with what inputs, files it read or wrote, and where decisions went wrong. Use when…

Sets up tend — an autonomous junior maintainer for a GitHub repo, powered by Claude or OpenAI Codex — that reviews PRs, triages issues, and fixes CI. Creates config, generates workflows, configures secrets and branch protection via API, creates the bot…

Debug unsuccessful CI on the default branch. Use when CI fails or is cancelled on main.

Nightly code quality sweep — resolves bot PR conflicts, reviews recent commits, surveys existing code, checks resolved issues, and updates tend workflows.

Guidance for Worktrunk (the `wt` CLI) — git worktree management, hooks, and config. Load when working out which worktree a `wt` command will act on, or reaching for the global `-C <path>` to target one; editing .config/wt.toml or…

Guidance for Worktrunk (the `wt` CLI) — git worktree management, hooks, and config. Load when working out which worktree a `wt` command will act on, or reaching for the global `-C <path>` to target one; editing .config/wt.toml or…

CLI output formatting standards for worktrunk. Load before editing any code that calls warning_message, hint_message, error_message, info_message, eprintln, or println, or that produces strings the user will see (CLI help, progress UI, snapshot text).…

Worktrunk release workflow. Use when user asks to "do a release", "release a new version", "cut a release", or wants to publish a new version to crates.io and GitHub.

Worktrunk-specific guidance for tend CI workflows. Adds codecov polling, Rust test commands, labels, and review criteria on top of the generic tend-* skills. Use when operating in CI.

Create a new worktrunk worktree (optionally in another repo) and switch this session's working directory into it. Use when launching a session that should work in its own worktree.

Presents designs, decisions, findings, or live work as an HTML page the user can comment on and manipulate. Use for “explain this in HTML,” “write up the findings,” “show me the options,” or work whose progress or review belongs in a shared page.

Use the shipped examples like a user in a real browser and fix the interaction defects the sweeps can't see — placement, tracking, legibility, crowding. Run after runtime or theme changes, or as a standing dispatch.

Project-specific guidance loaded by tend workflows alongside CLAUDE.md.

Develops Leaf from the current checkout by previewing examples, comparing runtimes, refreshing catalog stills, and testing page changes in the browser.

This skill should be used when the user asks to search/send/draft email, check calendar, create events, schedule meetings, find/upload/share Drive files, read/edit Google Docs, read spreadsheet data, send texts/iMessages, send WhatsApp messages, send Signal…

Check the whole inbox and present it as a fresh grouped list, surfacing mail that has gone stale as its own group. Use when the user says /check-emails or asks to check their email starting from a clean list.

Use the shipped examples like a user in a real browser and fix the interaction defects the sweeps can't see — placement, tracking, legibility, crowding. Run after runtime or theme changes, or as a standing dispatch.

Presents a concept, design, decisions, findings, or a run of work in progress as an HTML page the user comments on in the browser — the agent watches for comments, replies in-thread, and ships revised versions as the work moves. Use instead of a wall-of-text…

Project-specific guidance loaded by tend workflows alongside CLAUDE.md.