Skip to content

JasonColapietro/suede-creator-skills / skills/suede-clip-to-guide

suede-clip-to-guide

Verified

Suede Clip to Guide Skills. Use when creating short-to-long content and asked to "turn this clip into a guide funnel": select a rights-supported moment, score fit, draft the bridge, approval bundle and measurement plan. NOT FOR: rendering (suede-video), social calendars (suede-social), full guide writing (suede-copy), paid ads (suede-ad-creative), or publication without exact-content and identity approval.

FileKindSize
CARD.mdmarkdown4.5 KB
SKILL.mdskill md18.2 KB
agents/openai.yamlconfig417 B
evals/evals.jsonconfig8.7 KB
references/example-package.mdmarkdown4.3 KB
references/package-template.mdmarkdown3.0 KB
references/third-party-video-rights.mdmarkdown3.0 KB
references/worked-contract.mdmarkdown2.0 KB
scripts/validate_package.pyexecutablescript8.3 KB

references/package-template.md

View on GitHub
# Clip-to-Guide Package Template

Use this structure for every durable package. Keep URLs and timestamps exact.
Use `not available` instead of inventing a value.
Max Effort and Worker Fleet packages need two distinct evidence records and a
final `PROVED` verdict before approval or publication.

```markdown
---
campaign: "<short campaign name>"
platform: "<platform>"
identity: "<visible account identity>"
rights_status: "<original|licensed|permission-recorded|native-repost-only|fair-use-review|blocked>"
guide_status: "<existing|drafted|needs-long-form|blocked>"
publication_status: "<draft|approved|published|blocked>"
execution_mode: "<standard|max-effort|worker-fleet>"
certainty_status: "<not-required|pending|proved|unproved|blocked>"
---

# Clip-to-Guide Package

## Decision Snapshot

- Goal:
- Audience:
- Platform:
- Visible identity:
- Sequence: <anchor-first|clip-first|native-repost>
- Blueprint fit: <use|revise|do-not-use>
- Fit evidence:
- Next action:

## Source and Rights

- Video source:
- Video owner:
- Rights evidence:
- Allowed use:
- Jurisdiction:
- Transcript source:
- Selected excerpt:
- Claim qualifications:

### Fair-use review

- Purpose and character:
- Nature of the source work:
- Amount and substantiality:
- Effect on the potential market:
- Why this exact excerpt is necessary:
- Accountable decision owner:
- Decision or legal-review state:

## Guide Anchor

- Guide title:
- Guide URL:
- Publication state:
- Promise:
- Question the clip creates:
- Answer the guide delivers:

## Clip Brief

- In timestamp:
- Out timestamp:
- Target duration:
- Moment score:
- Exact opening:
- Subtitle text:
- On-screen source credit:
- Ending bridge:
- Export owner:
- Media file:

## Funnel Post

### Exact post text

<exact copy>

### Copy checks

- Hook matches the clip:
- Claim language matches the source:
- Guide bridge is explicit:
- One CTA only:
- Platform composer verified:

## Publish Sequence

1. <first action>
2. <second action>
3. <readback action>

## Measurement

- Baseline:
- Observation window:
- Clip metric:
- Guide metric:
- Campaign action:
- Decision rule:

## Certainty Gate

- Required: <yes|no>
- Checked artifact version/hash:
- Check 1 owner/process:
- Check 1 evidence:
- Check 1 verdict: <PROVED|UNPROVED|BLOCKED|NOT-REQUIRED>
- Check 2 owner/process:
- Check 2 evidence:
- Check 2 verdict: <PROVED|UNPROVED|BLOCKED|NOT-REQUIRED>
- Contradictions resolved:
- Final certainty verdict: <PROVED|UNPROVED|BLOCKED|NOT-REQUIRED>

## Approval Gate

- Exact media approved:
- Exact post text approved:
- Exact guide and URL approved:
- Exact identity approved:
- Exact sequence approved:
- Approved by:
- Approval timestamp:

## Verification

- Package validation:
- Live permalink:
- Visible identity:
- Rendered media or source reference:
- Guide readback:
- Publication timestamp:
- Caveats:
```

For chat-only delivery, mirror these headings and state that no saved package
was validated. For a saved package, validate with:

```bash
python3 scripts/validate_package.py path/to/package.md
```
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: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated 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: 323kUpdated Claude CodeCodexVerifiedInstall