Skip to content
Back to skills

Done

ASecurity

> **Status:** done — 2026-06-18 > **Filed:** 2026-06-18 > **Folder:** issues > **Severity:** medium > **Category:** skill / workflow

  • 136 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 5, 2026
ai-agentsgo

Security analysis

A100/100

Pro scans all 21 files and shows the line behind each finding

Scanned September 5, 2026

npx -y skills add alecs5am/ralphy --skill done --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Done?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Done
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/alecs5am-done-b4ba1050/badge)](https://www.skillsdirectory.com/skills/alecs5am-done-b4ba1050)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# `/<universe>-studio` orchestrator skill (idea → tag → 4 staged gates)

> **Status:** done — 2026-06-18
> **Filed:** 2026-06-18
> **Folder:** issues
> **Severity:** medium
> **Category:** skill / workflow

## Context

The user's ideal UX: come with an idea, tag a workspace, and make four approval decisions while everything else auto-assembles + auto-repairs against the universe evals. This needs an orchestrator skill that sequences the staged production with the eval gates and user checkpoints.

## What

A generic orchestrator skill that, given an idea + a tagged workspace, runs the four stages (location/cast → scenario → anchors → final montage), each through the per-stage auto-repair loop (#473) gated by the workspace criteria (#472), pausing for user approval at each stage.

## Why it matters

It ties the framework into the one-tag, four-approvals workflow the user described — the product-level payoff of the whole effort.

## Scope / acceptance

- Skill `.agents/skills/universe-studio/SKILL.md` (namespace `user`). Reads the workspace rubric (#468), drives the contract stages (#472), runs the per-stage loop (#473), checkpoints with the user at each stage.
- Generic — works for any workspace that has an evaluator config; Silent Hill is the first to exercise it end-to-end.
- Frontmatter passes `lint:skills` (kebab name, ≤1536-char description, namespace).
- Does NOT replace the per-role playbooks (scenarist / art-director / editor) — it sequences them under the eval gates.

## Dependencies and linked work

- Stage-gate map #472, per-stage loop #473.
- Sits above the production contract #406 and the per-role playbooks.

## Notes

- Naming: a generic slug (e.g. `universe-studio`) parameterized by the active workspace, not a Silent-Hill-specific skill.

Files in this skill

  • 001-cli-pretty-mode-untested.md7.3 KB
  • 002-bun-bytecode-crash.md5.6 KB
  • 004-auto-version-on-generate-overwrite.md3.9 KB
  • 005-provider-transient-errors-no-retry.md2.7 KB
  • 006-elevenlabs-music-tos-no-auto-resubmit.md2 KB
  • 007-provider-concurrency-not-self-throttled.md2.4 KB
  • 008-kling-multiframe-base64-broken.md2 KB
  • 009-ralphy-render-no-hyperframes-route.md3.4 KB
  • 010-generate-captions-clobbers-and-throws.md2 KB
  • 011-audio-sidechain-filter-label-bug.md1.4 KB
  • 012-no-frame-extract-or-i2v-extend-verbs.md2 KB
  • 013-no-compose-timeline-verb.md1.9 KB
  • 014-no-site-grounding-pull-site-verb.md2.4 KB
  • 015-invariants-not-tested-in-ci.md2.8 KB
  • 016-art-director-soft-self-review.md1.9 KB
  • 017-art-director-register-and-character-fit-gaps.md2.6 KB
  • 018-location-master-plate-rule-missing.md1.7 KB
  • 019-scribe-first-and-captions-first-discipline.md2.2 KB
  • 020-static-root-and-composition-props-undocumented.md2 KB
  • 021-auto-strip-c2pa-and-resize-png-anchors.md1.7 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.