epistex-dev/poteto-kit / templates/skills/team-mode
team-mode
UnverifiedRouter 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.2 KB |
| principles/_principle.template.md | markdown | 1.4 KB |
| principles/boundary-discipline.md | markdown | 946 B |
| principles/encode-lessons-in-skills.md | markdown | 957 B |
| principles/fix-root-causes.md | markdown | 892 B |
| principles/script-the-deterministic-parts.md | markdown | 1.3 KB |
principles/encode-lessons-in-skills.md
View on GitHub# encode-lessons-in-skills
**Rule:** When you learn something that a future agent would otherwise have to rediscover, write it down where agents will read it, in the smallest durable form.
**Why:** Lessons that stay in a conversation vanish; the same failure then recurs, and each recurrence costs a human a review comment.
**In practice:**
- After a recurring failure caused by missing knowledge, add a rule, a gotcha line in a feature file, or a skill, following the failure loop in the `team-mode` skill.
- Prefer the hardest form that works: type or lint rule first, then CI check, then a skill (see `guardrails/review-comment-to-rule.md`).
- Put the lesson in the same PR as the fix, with the evidence that reproduced the failure.
**Tells you are violating it:** the same mistake twice, "I'll remember for next time", a fix PR with no change to docs, rules or skills.
**Enforced by:** soft: this file; review asks "where is this lesson encoded?".
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 471k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |