Skip to content
Back to search

theamazingwolf

MarketplaceWorks with Claude CodeGitHub

Public agent skills and Claude Code plugins by Tim Wolf.

Safety scan

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

Badge for your README
findsafeskills safety rating

Markdown

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

HTML

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

Install

Install instructions from the README

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

Any agent via `npx skills`

npx skills add theamazingwolf/skills

List the skills without installing:

npx skills add theamazingwolf/skills --list

Install one skill only:

npx skills add theamazingwolf/skills --skill wlf-jev

Claude Code

/plugin marketplace add theamazingwolf/skills
/plugin install wlf-skills@theamazingwolf

From your shell: `claude plugin marketplace add theamazingwolf/skills`, then `claude plugin install wlf-skills@theamazingwolf`.

Codex

codex plugin marketplace add theamazingwolf/skills
codex plugin add wlf-skills@theamazingwolf

GitHub Copilot CLI

copilot plugin marketplace add theamazingwolf/skills
copilot plugin install wlf-skills@theamazingwolf

Pick one route per agent. Installing the same skill through both `npx skills` and the plugin loads it twice.

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 · 32 lines
  1. {
  2. "name": "theamazingwolf",
  3. "description": "Public agent skills and Claude Code plugins by Tim Wolf.",
  4. "owner": {
  5. "name": "Tim Wolf",
  6. "url": "https://timwolf.com"
  7. },
  8. "metadata": {
  9. "description": "Public agent skills and Claude Code plugins by Tim Wolf.",
  10. "version": "1.0.0"
  11. },
  12. "plugins": [
  13. {
  14. "name": "wlf-skills",
  15. "source": "./plugins/wlf-skills",
  16. "description": "Tim Wolf's public agent skills. Includes wlf-jev: design, code, calibrate and run TypeSafe Jev typed-judgment questions in your codebase, with runner and calibration scripts, TypeScript starters and a visual explainer.",
  17. "version": "1.0.0",
  18. "author": {
  19. "name": "Tim Wolf"
  20. },
  21. "license": "MIT",
  22. "homepage": "https://github.com/theamazingwolf/skills",
  23. "category": "development",
  24. "keywords": [
  25. "agent-skills",
  26. "typesafe",
  27. "jev",
  28. "calibration"
  29. ]
  30. }
  31. ]
  32. }
README.md · README · 122 lines
  1. # Skills
  2. Agent skills by Tim Wolf · [timwolf.com](https://timwolf.com) · GitHub [@theamazingwolf](https://github.com/theamazingwolf) · X/IG @realtimwolf
  3. Each skill is a self-contained folder under `plugins/wlf-skills/skills/` (`SKILL.md` plus its
  4. references, scripts and assets) that works in any agent that reads skills.
  5. The whole pack also installs as one plugin, `wlf-skills`, which adds slash
  6. commands as entry points. Install the pack once; each skill below lists its
  7. own requirements.
  8. ## Install
  9. ### Any agent via `npx skills`
  10. ```bash
  11. npx skills add theamazingwolf/skills
  12. ```
  13. List the skills without installing:
  14. ```bash
  15. npx skills add theamazingwolf/skills --list
  16. ```
  17. Install one skill only:
  18. ```bash
  19. npx skills add theamazingwolf/skills --skill wlf-jev
  20. ```
  21. ### Claude Code
  22. ```
  23. /plugin marketplace add theamazingwolf/skills
  24. /plugin install wlf-skills@theamazingwolf
  25. ```
  26. From your shell: `claude plugin marketplace add theamazingwolf/skills`,
  27. then `claude plugin install wlf-skills@theamazingwolf`.
  28. ### Codex
  29. ```bash
  30. codex plugin marketplace add theamazingwolf/skills
  31. codex plugin add wlf-skills@theamazingwolf
  32. ```
  33. ### GitHub Copilot CLI
  34. ```bash
  35. copilot plugin marketplace add theamazingwolf/skills
  36. copilot plugin install wlf-skills@theamazingwolf
  37. ```
  38. Pick one route per agent. Installing the same skill through both
  39. `npx skills` and the plugin loads it twice.
  40. ## Skills
  41. | Skill | What it does |
  42. |---|---|
  43. | [wlf-jev](plugins/wlf-skills/skills/wlf-jev/) | Design, code, calibrate and run TypeSafe Jev typed-judgment questions in your codebase |
  44. ### wlf-jev
  45. #### What it does
  46. Turns "classify / check / score / route X" into TypeSafe Jev questions,
  47. working TypeScript in your repo, and a calibration report that says how far
  48. to trust them. It picks the primitive (noul, choice, score, box), writes the
  49. wording and state, measures agreement against a small set of human labels,
  50. and wires the result in as an agent tool, in-app classifier, agent guard
  51. check or batch run. Ships a calibration script, a question runner with an
  52. offline mock mode, TypeScript starters and a visual explainer.
  53. The rule it follows: Jev makes judgments and code makes decisions, and no
  54. threshold ships without agreement measured against human labels.
  55. #### What you need
  56. - Node 22 or newer.
  57. - A [TypeSafe](https://typesafe.ai) account and an API key in
  58. `TYPESAFE_API_KEY` (environment or a git-ignored `.env`). Without a key,
  59. the question runner's `--mock` mode still supports offline design and
  60. pipeline tests.
  61. - **Data notice:** whatever goes into a Jev question's `state` (and its
  62. `instructions` or `criteria`) is sent to TypeSafe, a third-party service.
  63. Keep secrets out, and check that the data's owner is fine with that.
  64. #### Commands
  65. Plugin commands (Claude Code):
  66. | Command | Skill mode |
  67. |---|---|
  68. | `/wlf-skills:jev-setup [client-project-path]` | Check Node, SDK and key; make a smoke call |
  69. | `/wlf-skills:jev-explain [question]` | Open the visual explainer |
  70. | `/wlf-skills:jev-design <what-to-judge>` | Pick primitives, write questions, state and a confidence plan |
  71. | `/wlf-skills:jev-calibrate [spec] [labelled-items]` | Measure agreement against human labels, pick thresholds |
  72. | `/wlf-skills:jev-integrate [shape] [spec]` | Wire in as agent tool, classifier, guard check or batch run |
  73. | `/wlf-skills:jev-run <spec> <data>` | Estimate cost, then run at scale |
  74. Or just ask ("add a Jev check for...") and the skill triggers on its own.
  75. _Not affiliated with or endorsed by TypeSafe. TypeSafe and Jev are trademarks of their respective owners._
  76. ## Layout
  77. ```
  78. .claude-plugin/marketplace.json marketplace "theamazingwolf"
  79. plugins/wlf-skills/
  80. .claude-plugin/plugin.json plugin "wlf-skills" (bundles every skill)
  81. commands/ slash commands (plugin installs only)
  82. skills/<skill>/ each skill: SKILL.md, references, scripts, assets
  83. ```
  84. `npx skills` finds every skill under `plugins/wlf-skills/skills/` through
  85. the marketplace file, so each one is installable on its own.
  86. ## License
  87. [MIT](LICENSE) © 2026 Tim Wolf

Ratings and comments

Sign in to rate this skill.

Sign in

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