Skip to content

epistex-dev/poteto-kit / templates/skills/team-mode

team-mode

Unverified

Router for {{OWNER}}'s way of working. Use for "{{OWNER}} mode", "/team-mode", or when asked to work to this team's standard of rigor (concise detailed answers, deliberate subagents, plain prose, simple code, verified work). Routes each situation to the leaf skill or playbook that owns it.

principles/script-the-deterministic-parts.md

View on GitHub
# script-the-deterministic-parts

**Rule:** When a step has one right answer every time, put it in code (a script, a CLI, a codemod) and leave only the judgment to the agent.

**Why:** Without a script, every agent writes its own throwaway version of the same step, and the next one discards it (the story is in `docs/02-verification.md`). A mechanical migration done by agent rewrites is slow and inconsistent where a transform would be exact.

**In practice:**
- When a skill tells the agent to run the same sequence of commands again, ask whether the sequence is deterministic. If it is, write the script once, give it tests, and have the skill call it (the `verify-app` CLI is the example).
- For a migration or bulk change that is mechanical, write a codemod or a syntax-tree transform instead of asking agents to rewrite files by hand. Review the transform and its output, not every file.
- Keep in the skill text only what needs judgment: what to check, how to read the result, when to stop.

**Tells you are violating it:** several near-identical one-off scripts in agent transcripts; a skill that lists exact commands for the agent to retype; the same mechanical edit made by hand across many agent PRs.

**Enforced by:** soft: this file. The hard form is the script itself, with its own tests.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 470kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall