Menu

#840 by GitHub stars

Jingyi-Wu-Richael/rachel-digital-human-production

Public-safe MiniMax overseas voice clone and HeyGen API workflow for creating digital-human talking-head videos. Use when Codex is asked to make, automate, QA, or batch-produce authorized 数字人/口播 videos from a script, portrait, voice sample, MiniMax voice cloning, HeyGen Image-to-Video, HeyGen Photo

Engineering

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

SKILL.md

Week of Oct 26, 2026 · +0 / −0 lines

Before Local scripts → After Local scripts

a20258b8eb38 → a20258b8eb38

Compare on GitHub

View on GitHubAdd to my skills

Verified commit a20258b8eb38eb370cf3402fb4414754b4c44c2a

1.1kGitHub stars
6stars in 7 days
1skill in this repository
0commits in 30 days

Heat

3.0
  • Star growth, last 7 daysAhead of 72% of tracked repositories
  • Star growth, last 24 hoursAhead of 2% of tracked repositories
  • Rank movement, last 7 daysAhead of 16% of tracked repositories
  • Commits, last 30 daysAhead of 0% of tracked repositories
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Aug 2, 2026Nov 6, 20261,083

Individual skills in this repository

How it works

rachel-digital-human-production

When your agent uses it

Public-safe MiniMax overseas voice clone and HeyGen API workflow for creating digital-human talking-head videos. Use when Codex is asked to make, automate, QA, or batch-produce authorized 数字人/口播 videos from a script, portrait, voice sample, MiniMax voice cloning, HeyGen Image-to-Video, HeyGen Photo Avatar, a 15-second preview, full-video generation, or job-state tracking.

What it loads into context

Frontmatter

97 tokens

Always available to the agent

SKILL.md

1,624 tokens

When the skill is activated

Reference documents

2,371 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Core Rule
  2. Operating Boundaries
  3. Required Workflow
  4. Batch Mode
  5. Failure Policy
  6. Public Distribution Policy
  7. References

Scripts executed separately

  • scripts/init_job_state.py
  • scripts/preflight_assets.py

Files

  • .gitignoreasset122 bytes
  • LICENSEasset1,066 bytes
  • README.mddoc2,386 bytes
  • SKILL.mdcore7,336 bytes
  • SKILL.mdcore7,336 bytes
  • SKILL.mdcore7,336 bytes
  • SKILL.mdcore7,336 bytes
  • SKILL.mdcore7,336 bytes
  • SKILL.mdcore7,336 bytes
  • SKILL.mdcore7,336 bytes
  • agents/openai.yamlasset341 bytes
  • references/api-facts.mddoc2,863 bytes
  • references/checklists.mddoc3,019 bytes
  • references/public-safety.mddoc2,065 bytes
  • scripts/init_job_state.pyruns1,787 bytes
  • scripts/preflight_assets.pyruns2,903 bytes
Read SKILL.md

# Rachel Digital Human Production

## Core Rule

Use MiniMax for cloned narration and HeyGen for image-driven video. If a MiniMax audio file is available, drive HeyGen with the uploaded audio asset. Do not switch to HeyGen `script + voice_id` unless the user explicitly asks to use HeyGen's own voice.

Always preserve the production gate:

```text
asset check -> MiniMax narration -> 15-second HeyGen preview -> user approval -> full HeyGen video -> download QA -> archive state
```

This skill is a workflow guide. It does not grant HeyGen, MiniMax, OpenAI, network, billing, or workspace permissions.
View the complete source on GitHub

Skills included

  • rachel-digital-human-production

Repository facts

License
MIT
Created
Jul 16, 2026
Last pushed
Jul 16, 2026
Forks
160
Open issues
0
Project activity
Slowing

Rank over the last 12 weeks

Now #840 · best #567 · down 116 in 30 days

  1. #823 on Nov 1
  2. #827 on Nov 2
  3. #832 from Nov 3 to Nov 4
  4. #833 on Nov 5
  5. #834 on Nov 6
  6. #840 since Nov 7
63 earlier periods
  1. #646 on Aug 2
  2. #587 on Aug 8
  3. #575 on Aug 9
  4. #602 on Aug 10
  5. #601 on Aug 11
  6. #590 on Aug 12
  7. #585 on Aug 13
  8. #584 on Aug 14
  9. #565 on Aug 15
  10. #580 on Aug 16
  11. #585 on Aug 17
  12. #599 on Aug 18
  13. #587 on Aug 19
  14. #585 on Aug 20
  15. #590 on Aug 21
  16. #567 on Aug 22
  17. #596 on Aug 23
  18. #598 on Aug 24
  19. #611 on Aug 25
  20. #596 on Aug 26
  21. #604 on Aug 27
  22. #619 on Aug 28
  23. #578 on Aug 29
  24. #576 on Aug 30
  25. #601 on Aug 31
  26. #609 on Sep 2
  27. #612 on Sep 3
  28. #592 on Sep 4
  29. #590 on Sep 5
  30. #608 on Sep 7
  31. #628 on Sep 8
  32. #614 on Sep 9
  33. #620 on Sep 10
  34. #607 on Sep 11
  35. #639 on Sep 14
  36. #622 on Sep 19
  37. #634 on Sep 20
  38. #648 on Sep 21
  39. #659 on Sep 23
  40. #651 on Sep 27
  41. #655 on Sep 28
  42. #694 on Sep 29
  43. #674 on Sep 30
  44. #634 on Oct 3
  45. #724 on Oct 8
  46. #694 on Oct 9
  47. #677 on Oct 11
  48. #696 on Oct 12
  49. #699 on Oct 13
  50. #712 on Oct 14
  51. #705 on Oct 15
  52. #712 on Oct 16
  53. #691 on Oct 17
  54. #685 on Oct 18
  55. #723 on Oct 19
  56. #737 on Oct 21
  57. #711 on Oct 22
  58. #718 on Oct 23
  59. #802 on Oct 25
  60. #811 on Oct 28
  61. #815 on Oct 29
  62. #819 on Oct 30
  63. #822 on Oct 31

Before you install

Local scripts

Automated signals, not a guarantee

Checked Nov 3, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 6 notes
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 14 signals by file

.gitignore

  • Access to secretsline 1
    [Credential-related source omitted]

README.md

  • Access to secretsline 51
    [Credential-related source omitted]
  • Access to secretsline 52
    [Credential-related source omitted]

SKILL.md

  • Access to secretsline 22
    [Credential-related source omitted]

references/api-facts.md

  • Network accessline 11
    - https://platform.minimax.io/docs/guides/speech-voice-clone
  • Network accessline 12
    - https://platform.minimax.io/docs/api-reference/voice-cloning-clone
  • Network accessline 13
    - https://platform.minimax.io/docs/api-reference/speech-t2a-http
  • Network accessline 37
    - https://developers.heygen.com/image-to-video
  • Network accessline 38
    - https://developers.heygen.com/assets
  • Network accessline 39
    - https://developers.heygen.com/docs/pricing

references/checklists.md

  • Access to secretsline 73
    [Credential-related source omitted]
  • Access to secretsline 74
    [Credential-related source omitted]

scripts/init_job_state.py

  • Executable scriptline 1
    #!/usr/bin/env python3

scripts/preflight_assets.py

  • Executable scriptline 1
    #!/usr/bin/env python3

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 2 facts
  • Access to secrets in code of documentationREADME.md:51Low confidence
  • Access to secrets in code of documentationREADME.md:52Low confidence

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

mattpocock/skills

Skills for Real Engineers. Straight from my .agents directory.

317.5kGitHub stars

obra/superpowers

An agentic skills framework & software development methodology that works.

314kGitHub stars

NousResearch/hermes-agent

The agent that grows with you

261.5kGitHub stars

multica-ai/andrej-karpathy-skills

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions,…

230.6kGitHub stars

anthropics/skills

Public repository for Agent Skills

188.6kGitHub stars

DietrichGebert/ponytail

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

186.3kGitHub stars

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

Jingyi-Wu-Richael/rachel-digital-human-production: #840 on hotskills, 1.1k stars

[![Jingyi-Wu-Richael/rachel-digital-human-production on hotskills](https://hotskills.dev/badge/jingyi-wu-richael-rachel-digital-human-production.svg)](https://hotskills.dev/skill/jingyi-wu-richael-rachel-digital-human-production/)