interserve

mistakeknotmistakeknot

Dispatch tasks to Codex CLI agents — single megaprompt for one task, parallel delegation for many. Includes structured debate triggers and Oracle escalation.

194 days ago

refactor-safely

mistakeknotmistakeknot

Use when performing significant refactoring — guides a disciplined process that leverages duplication detection, characterization tests, staged execution, and continuous simplicity review

194 days ago

engineering-docs

mistakeknotmistakeknot

Use when capturing a solved problem as categorized documentation with YAML frontmatter for fast lookup

194 days ago

landing-a-change

mistakeknotmistakeknot

Use when implementation is complete and all tests pass — guides the disciplined process of verifying, documenting, and landing a change on trunk

194 days ago

using-clavain

mistakeknotmistakeknot

Use when starting any conversation - establishes how to find and use skills, agents, and commands, requiring Skill tool invocation before ANY response including clarifying questions

194 days ago

executing-plans

mistakeknotmistakeknot

Use when you have a written implementation plan to execute in a separate session with review checkpoints

194 days ago

lane

mistakeknotmistakeknot

Manage thematic work lanes — discover, create, tag beads, show velocity and starvation scores

194 days ago

brainstorming

mistakeknotmistakeknot

Freeform brainstorming mode — loads collaborative dialogue style (one question at a time, multiple choice, incremental design). Use for open-ended exploration without structured phases. For a guided workflow with repo research, use /brainstorm instead.

194 days ago

upstream-sync

mistakeknotmistakeknot

Use when checking for updates from upstream tool repos (beads, oracle, superpowers, compound-engineering) or when the /clavain:upstream-sync command is invoked

194 days ago

galiana

mistakeknotmistakeknot

Show discipline analytics — defect escape rate, override rate, cost metrics, and agent scorecard

194 days ago

writing-plans

mistakeknotmistakeknot

Use when you have a spec or requirements for a multi-step task, before touching code

194 days ago

subagent-driven-development

mistakeknotmistakeknot

Use when executing implementation plans with independent tasks in the current session

194 days ago

dispatching-parallel-agents

mistakeknotmistakeknot

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

194 days ago

code-review-discipline

mistakeknotmistakeknot

Use when requesting or receiving code review — covers dispatching reviewer subagents, handling feedback with technical rigor, and avoiding performative agreement

194 days ago

using-tmux-for-interactive-commands

mistakeknotmistakeknot

Use when you need to run interactive CLI tools (vim, git rebase -i, Python REPL, etc.) that require real-time input/output - provides tmux-based approach for controlling interactive sessions through detached sessions and send-keys

194 days ago

file-todos

mistakeknotmistakeknot

This skill should be used when managing the file-based todo tracking system in the todos/ directory. It provides workflows for creating todos, managing status and dependencies, conducting triage, and integrating with slash commands and code review processes.

194 days ago