dotfiles

Report on currently-running SASE agents. Use when the user asks "what's running?", "agent status", "status report", or any question about live/background agents.

Reference for sase bead commands (create, update, list, search, ready, show, dep). Use when working with beads.

Inspect prior sase agent chat transcripts. Use when the user asks about previous chats, chat transcripts, prior agent conversations, "what did agent X say?", "summarize the previous agent", or any question about an earlier sase agent's prompt or response.

Create an implementation plan. Use instead of plan mode (which is disabled).

Create an implementation plan. Use instead of plan mode (which is disabled).

Create an implementation plan. Use instead of plan mode (which is disabled).

Create an implementation plan. Use instead of plan mode (which is disabled).

Create an implementation plan. Use instead of plan mode (which is disabled).

Request a SASE agent launch through LaunchApproval instead of spawning directly.

Attach named output variables to the current SASE agent run.

Create beautiful, robust, and powerful custom notification gates on the fly. Use this as the easy way to propose commands for user confirmation, especially dangerous commands or commands the user asked to confirm before use.

Inspect SASE notifications and notification inbox entries. Use when the user asks about SASE notifications, the notification inbox, axe notifications/errors, plan or question notifications, or "the notification I just got".

Create explicit SASE artifact files produced during an agent run.

Ask the user questions. Use instead of AskUserQuestion (which is disabled).

Ask the user questions. Use instead of ask_user (which is disabled).

Ask the user questions. Use instead of ask_user (which is disabled).

Ask the user questions. Use instead of ask_user (which is disabled).

Ask the user questions. Use instead of ask_user (which is disabled).

Work with repos through `sase repo` (list, open, log). MUST be used to open any repo other than your own workspace checkout before reading or modifying its files: linked repos, sidecars, other SASE projects, or any GitHub repo not linked to the current project (opened on demand as an external repo). Also required instead of web-fetching a repo's files or history (github.com / raw.githubusercontent.com / GitHub API).

Inspect and manage SASE projects with `sase project` (list, show, enable, disable, alias). Use when you need the set of enabled projects, one project's lifecycle record, or machine-readable project data — e.g. to fan out one agent per enabled project.

Run read-only Obsidian Dataview queries against Bryan's Bob vault via `bob query`.

Commit changes using sase commit for git-based VCS (bare git and GitHub). This is the ONLY way you should EVER commit to git repos. NEVER invoke this skill unless the user explicitly asks you to commit or a post-completion finalizer triggers it.

Commit changes using sase commit for git-based VCS (bare git and GitHub). This is the ONLY way you should EVER commit to git repos. NEVER invoke this skill unless the user explicitly asks you to commit or a post-completion finalizer triggers it.

Commit changes using sase commit for git-based VCS (bare git and GitHub). This is the ONLY way you should EVER commit to git repos. NEVER invoke this skill unless the user explicitly asks you to commit or a post-completion finalizer triggers it.

Commit changes using sase commit for git-based VCS (bare git and GitHub). This is the ONLY way you should EVER commit to git repos. NEVER invoke this skill unless the user explicitly asks you to commit or a post-completion finalizer triggers it.

Commit changes using sase commit for git-based VCS (bare git and GitHub). This is the ONLY way you should EVER commit to git repos. NEVER invoke this skill unless the user explicitly asks you to commit or a post-completion finalizer triggers it.

Analyze and work with SASE ChangeSpecs. Use when inspecting PR status, dependencies, commits, hooks, comments, mentors, or `.sase` project files.

Create an implementation plan. Use instead of plan mode (which is disabled).

Reference for sase bead commands (create, update, list, search, ready, show, dep). Use when working with beads.

Guide audited SASE long-term memory reads through `sase memory read`. Use when instructions require reading long-term memory context or mention the long-memory read procedure.

Report on currently-running SASE agents. Use when the user asks "what's running?", "agent status", "status report", or any question about live/background agents.

Inspect prior sase agent chat transcripts. Use when the user asks about previous chats, chat transcripts, prior agent conversations, "what did agent X say?", "summarize the previous agent", or any question about an earlier sase agent's prompt or response.

Read-only personal Gmail access through gog.

Analyze and work with SASE ChangeSpecs. Use when inspecting CL/PR status, dependencies, commits, hooks, comments, mentors, or `.sase` project files.

Commit changes using sase commit for git-based VCS (bare git and GitHub). This is the ONLY way you should EVER commit to git repos. NEVER invoke this skill unless the user explicitly asks you to commit or a post-completion finalizer triggers it.

Commit changes using sase commit for Google's fig VCS. This skill is the ONLY way that you should EVER commit to fig repos. NEVER invoke this skill unless the user explicitly asks you to commit or a post-completion finalizer triggers it.

Inspect SASE notifications and notification inbox entries. Use when the user asks about SASE notifications, the notification inbox, axe notifications/errors, plan or question notifications, or "the notification I just got".

Ask the user questions. Use instead of ask_user (which is disabled).

Attach named output variables to the current SASE agent run.