Execute an implementation plan by working through each task file in order. Use when an implementation plan folder exists at docs/<feature>/implementation_plan/.
Cut a new "production" release of the minds app. Pushes a release branch in the mngr clone at ~/project/minds_prod, syncs vendor/mngr in ~/project/forever-claude-template to…
Enable the code review stop hook in .reviewer/settings.local.json. Optionally takes a shell expression for when to enforce (defaults to always).
Resolve an agent name or description to an exact mngr agent name. Used by other skills that target agents.
Create a new PRIVATE GitHub repo that is a full-history copy of imbue-ai/forever-claude-template's current main branch, clone it to <parent-dir>/<repo-name> (default…
Review the conversation transcript for behavioral issues (misleading behavior, disobeyed instructions, instructions worth saving).
Wait for another agent to enter WAITING state, then execute follow-up instructions
Fix a random FIXME in the codebase (in the given scope, use "." for the whole codebase)
Send a message to another mngr agent. Use when you need to communicate with a peer agent.
Identify outdated docstrings in the $1 library
Telegram-specific implementation for reading recent conversation history. Only use when the deployment is known to use telegram (e.g.
Assess whether the approach taken on a branch is the right way to solve the problem.
Write an implementation plan from architecture documents
Run local vs Offload benchmarks for mng and sculptor, then update the Benchmarks section of the Offload README.
Audit recent CI runs for anomalies (warnings, uncached docker builds, flaky/slow tests, regressions).
Restore the stop hook to blocking mode (default: block up to 3 times before letting through)
Create a verifying agent to check whether a working agent's task was completed successfully. Use after a working agent finishes (transitions to "done", "stopped", "waiting", or…
Convert triaged autoclaude GitHub issues into FIXMEs in the codebase. Use when you want to process issues that have been triaged by authorized users.
Onboard a repository to use Offload for parallel test execution on Modal. Detects test setup, creates config, Dockerfile, CI job, and optimizes performance.
Push local improvements to shared infrastructure (skills, scripts, CLAUDE.md scaffolding, Dockerfile, services.toml) back to the parent template repo so other agents derived from…
Search through past events in the event log files. Use when you need to look up something that happened previously but didn't store in memory.
Write ratchet tests to prevent accumulation of code anti-patterns. Use when asked to create a "ratchet test" for tracking and preventing specific code patterns (e.g., TODO…
Create a ticket to track work that needs to be done. Use when you need to record some work or action that needs to be done later (e.g., when at capacity), track a multi-step…
Check for pending tickets that are ready to be worked on. Use when capacity opens up (e.g., after an agent finishes) to find the next highest-priority work to delegate.
Convert a file containing identified issues into GitHub issues. Use after running identify-* commands to create corresponding GitHub issues.
Add, modify, or remove background services managed by the bootstrap service manager. Use this when you want to run a long-lived process alongside your main agent.
List all event sources and types you may receive, with descriptions of their fields and meaning. Note that event types are dynamic and new sources may appear.
Use immediately when the user asks you to do something net-new -- a task you haven't done before, no existing skill applies, and getting it right will require nontrivial research,…
Create HTML mocks for a new feature idea
Copy the default issue categories to .reviewer/ for customization. Use when you want to edit the code review or conversation review categories for your project.
Forward new information to a running agent, or adjust a task based on changed requirements. Use when the user provides additional context, clarifications, or changed requirements…
Create FIXME's in the codebase for each of the issues in the given input file.
Extract requirements document from HTML mock iteration
Match tutorial script blocks to e2e pytest functions and add missing tests
Convert a file containing identified issues into a tracked file in current_tasks/. Use after running identify-* commands to create a local record of current issues.
Clean up old agents, their output directories, and other historical data. Use during nightly cleanup or when the system has accumulated stale data.
Pull in updates from the parent branch to improve this Mind's skills, prompts, and configuration. Use only when prompted by the user.
Send a message to the user through whatever channel the deployment has configured. Use whenever another skill tells you to "ask the user" or "tell the user" something.
Identify inconsistencies in the $1 library
Handle unexpected situations where things are not working as expected. Use when you encounter errors, confusing state, or behavior that contradicts your docs and prompts.
Write high quality specifications or design docs for a program. Use any time you are asked to write, improve, or update specs / design docs (e.g., files in a `specs/` folder).
End the Q&A phase and generate the plan. Use after the blueprint skill has gathered enough context.
List all active conversations for this mind. Use when you need to see what conversations exist, check their models, or find a conversation ID.
Create a sub-agent to perform a task. Use when you need to delegate work to another agent, for example, a working agent (for actually accomplishing some task) or a verifying agent…
Create 1-3 short asciinema demo recordings (5-20 seconds each) that demonstrate completed work. Use only when explicitly instructed to create demos.
End-to-end dev workflow for the minds app stack -- first-time bring-up, every-startup vendor/mngr sync, and the iteration loop against a running Docker agent.
Create a prompt from a short task description in a JSON file
Use whenever you want to use latchkey commands or interact with third-party or self-hosted services (Slack, Google Workspace, Dropbox, GitHub, Linear, Coolify...) using their HTTP…
Interactively triage the user's local engineering backlog file into GitHub issues. Use when the user wants to process their raw thought notes / ticket backlog into proper GitHub…
Create a new skill to handle a previously-unknown type of event (eg, from an unknown source). Use in order to generate the appropriate skill for the user, and ensure that such…
Set the maximum number of times the stop hook will block before letting the agent through
Come up with good ideas about what to fix. Use when you have to fix something, but you're not sure what.
Turn a process from the turn that just finished into a reusable skill. A skill captures a stable process -- SKILL.md prose describing the recipe, with scripts for deterministic…
Write an architecture document from goals and requirements
Pull updates from the upstream template repo. Use when upstream has new skills, script fixes, or config improvements you want to incorporate.
Identify divergences from the style guide in the $1 library
Create a sub-agent to perform a larger task. Use when work is large enough to warrant a separate context, involves multi-file changes, or benefits from isolation.
Use when you want to create a new web view for the user. Covers scaffolding a new FastAPI service (canonical path) and the escape hatch for wrapping a pre-existing third-party…
Identify places in the $1 library where the docs and code disagree
Handle the one-time first-run event to set up onboarding tickets and introduce yourself to the user. You **MUST** use this skill (and *carefully follow the process in this doc*)…