Skip to content

papperrollinggery/Paperrolling-DIRcreative-SKILL / skills/dircreative/learn

dircreative-learn

Verified

Record reusable project learnings, prompt fixes, channel rules, and model behavior.

FileKindSize
SKILL.mdskill md1.5 KB
---
name: dircreative-learn
description: Record reusable project learnings, prompt fixes, channel rules, and model behavior.
---

# Learn

## Required Knowledge

Read only the reference needed for the active task, not this entire list.
The root v2 route owns scope and authorization; legacy records do not add gates.

- `docs/film-preproduction/prompt-pattern-registry.json`
- `.dircreative/learnings.jsonl`
- `.dircreative/timeline.jsonl`

## Inputs

- QA report
- retry plan
- user feedback
- observed output behavior
- evidence-bound reference analysis and effect-comparison review

## Outputs

- learning entry
- registry update request
- deprecation request when a pattern fails repeatedly

## Rules

- Write append-only JSONL.
- Mark source as `user-stated`, `observed`, `inferred`, `official`, or `internal_eval`.
- Do not promote a pattern without fixture QA improvement.
- Reference mechanisms remain candidates until an original transfer test shows
  the intended audience effect without copying distinctive expression. Use
  `skills/dircreative/references/video-distillation.md` for scoped research, before/after evidence,
  review, and source-maintenance boundaries; no autonomous global installation.

## skill_run_receipt

Persist the following only for a requested formal handoff, pause/resume or actual
execution record. Ordinary work returns its result without a separate receipt.
The next skill is advisory; the controller continues only the requested scope.

Record new learning keys, confidence, source, and `next_recommended_skill: checkpoint`.
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: 472kUpdated 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