Skip to content
Back to search

skills

SkillGitHubIncomplete

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/humanlayer--skills/badge.svg)](/listings/humanlayer--skills)

HTML

<a href="/listings/humanlayer--skills"><img src="/api/listings/humanlayer--skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

npx skills add humanlayer/skills --skill SKILLNAME

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 98 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  3. "name": "skills",
  4. "owner": {
  5. "name": "humanlayer",
  6. "email": "support@humanlayer.dev"
  7. },
  8. "metadata": {
  9. "description": "Claude Code skills from HumanLayer",
  10. "version": "1.0.0"
  11. },
  12. "plugins": [
  13. {
  14. "name": "rpi",
  15. "description": "Research a change, work through its design, and implement it with reviewable local documents",
  16. "version": "1.1.0",
  17. "author": {
  18. "name": "humanlayer",
  19. "email": "support@humanlayer.dev"
  20. },
  21. "source": "./plugins/rpi",
  22. "category": "productivity",
  23. "keywords": ["research", "design", "implementation", "skills"]
  24. },
  25. {
  26. "name": "improve-claude-md",
  27. "description": "Rewrite a CLAUDE.md file using <important if> blocks to improve instruction adherence",
  28. "version": "1.0.0",
  29. "author": {
  30. "name": "humanlayer",
  31. "email": "support@humanlayer.dev"
  32. },
  33. "source": "./plugins/improve-claude-md",
  34. "category": "productivity",
  35. "keywords": ["claude-md", "instructions", "important-if", "claude-code"]
  36. },
  37. {
  38. "name": "narrow-react-prop-types",
  39. "description": "Narrow React component prop types to match live code paths",
  40. "version": "1.0.0",
  41. "author": {
  42. "name": "humanlayer",
  43. "email": "support@humanlayer.dev"
  44. },
  45. "source": "./plugins/narrow-react-prop-types",
  46. "category": "productivity",
  47. "keywords": ["react", "typescript", "props", "components", "claude-code"]
  48. },
  49. {
  50. "name": "build-iterated-agentic-loop",
  51. "description": "Build a repo-local skill plus an iterated coding-agent workflow, prompt, and memory file",
  52. "version": "1.0.0",
  53. "author": {
  54. "name": "humanlayer",
  55. "email": "support@humanlayer.dev"
  56. },
  57. "source": "./plugins/build-iterated-agentic-loop",
  58. "category": "productivity",
  59. "keywords": ["iterated-agentic-loop", "coding-agents", "github-actions", "skills", "claude-code"]
  60. },
  61. {
  62. "name": "design-control-loop",
  63. "description": "Interview the user to design an agentic control loop (sensor, controller, actuator under disturbances), then build it as locally-runnable components plus a scheduled coding-agent workflow",
  64. "version": "1.0.0",
  65. "author": {
  66. "name": "humanlayer",
  67. "email": "support@humanlayer.dev"
  68. },
  69. "source": "./plugins/design-control-loop",
  70. "category": "productivity",
  71. "keywords": ["control-loop", "control-theory", "sensor-controller-actuator", "iterated-agentic-loop", "coding-agents", "github-actions", "skills", "claude-code"]
  72. },
  73. {
  74. "name": "show-me",
  75. "description": "Explain the current topic with concise diagrams, code-shape sketches, and focused HTML artifacts",
  76. "version": "1.0.1",
  77. "author": {
  78. "name": "humanlayer",
  79. "email": "support@humanlayer.dev"
  80. },
  81. "source": "./plugins/show-me",
  82. "category": "productivity",
  83. "keywords": ["visualization", "diagrams", "mermaid", "code", "html"]
  84. },
  85. {
  86. "name": "visual-pr",
  87. "description": "Create or update a pull request with a concise visual outline for reviewers",
  88. "version": "1.0.0",
  89. "author": {
  90. "name": "humanlayer",
  91. "email": "support@humanlayer.dev"
  92. },
  93. "source": "./plugins/visual-pr",
  94. "category": "productivity",
  95. "keywords": ["pull-request", "code-review", "visualization", "github", "claude-code"]
  96. }
  97. ]
  98. }
README.md · README · 114 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # skills
  2. Claude Code skills from [HumanLayer](https://humanlayer.dev).
  3. ## Installation
  4. ```bash
  5. npx skills add humanlayer/skills --skill SKILLNAME
  6. ```
  7. ## Available Skills
  8. ### rpi
  9. Researches a change, works through design choices with you, and implements it from local documents. Choose design discussion, PRD followed by TDD, technical design, or research followed by implementation. Each phase works in a fresh session by default.
  10. ```bash
  11. npx skills add humanlayer/skills --skill rpi
  12. ```
  13. Then invoke `/rpi` with your task, or request a step directly:
  14. ```text
  15. /rpi research how the collections connect to the database
  16. /rpi make a PRD
  17. /rpi what's next .agents/artifacts/my-change
  18. /rpi implement .agents/artifacts/my-change
  19. ```
  20. In Codex, use `$rpi` instead of `/rpi`, for example `$rpi research how the collections connect to the database`. Its default sandbox can make `.agents` read-only; grant the session write access to `.agents/artifacts`, or pass a writable task directory such as `artifacts/my-change`. RPI asks before changing a blocked destination.
  21. ### show-me
  22. Explains the current topic with concise diagrams, code-shape sketches, and focused HTML artifacts.
  23. ```bash
  24. npx skills add humanlayer/skills --skill show-me
  25. ```
  26. Then invoke:
  27. ```
  28. /show-me
  29. ```
  30. ### visual-pr
  31. Creates or updates a pull request with a concise visual outline that helps reviewers understand the change.
  32. ```bash
  33. npx skills add humanlayer/skills --skill visual-pr
  34. ```
  35. Then invoke:
  36. ```
  37. /visual-pr
  38. ```
  39. ### improve-claude-md
  40. Rewrites your CLAUDE.md using `<important if>` blocks to improve instruction adherence.
  41. ```bash
  42. npx skills add humanlayer/skills --skill improve-claude-md
  43. ```
  44. Then in your project:
  45. ```
  46. /improve-claude-md
  47. ```
  48. ### narrow-react-prop-types
  49. Narrows React component prop types to match live code paths instead of Storybook, test, or mock-only states.
  50. ```bash
  51. npx skills add humanlayer/skills --skill narrow-react-prop-types
  52. ```
  53. Then in your project:
  54. ```
  55. /narrow-react-prop-types
  56. ```
  57. ### build-iterated-agentic-loop
  58. Builds a repo-local skill plus an iterated coding-agent GitHub Actions workflow, prompt, memory file, and reference templates.
  59. ```bash
  60. npx skills add humanlayer/skills --skill build-iterated-agentic-loop
  61. ```
  62. Then in your project:
  63. ```
  64. /build-iterated-agentic-loop
  65. ```
  66. ### design-control-loop
  67. Interviews you to design an agentic control loop — sensor, controller, actuator, and disturbances — tailored to your codebase, then builds it as locally-runnable components plus a scheduled coding-agent workflow.
  68. ```bash
  69. npx skills add humanlayer/skills --skill design-control-loop
  70. ```
  71. Then in your project:
  72. ```
  73. /design-control-loop
  74. ```

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.