Skip to content
Back to search

skills

AI agent skills created by me: Dan McAteer

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/dannymac180--skills/badge.svg)](/listings/dannymac180--skills)

HTML

<a href="/listings/dannymac180--skills"><img src="/api/listings/dannymac180--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.

**Claude Code plugin marketplace (ModSmith).** Run `/plugin marketplace add DannyMac180/skills`, then `/plugin install modsmith-all@modsmith` for the skill plus all six ready-made mods, or `/plugin install modsmith@modsmith` for the skill alone and `/plugin install quiz-after@modsmith` (or any other ModSmith mod) one by one.

**Any agent.** If your AI agent supports skills, you can point it at the GitHub URL for a skill and ask it to install that skill:

Install the AI agent skill at https://github.com/DannyMac180/skills/tree/main/codex-dynamic-workflows

You can also clone this repo and copy a skill folder into your agent's skills directory. Adjust the destination path for your agent; this example uses Codex's user-scope skills folder (`~/.agents/skills`):

git clone https://github.com/DannyMac180/skills.git
cd skills
mkdir -p "$HOME/.agents/skills"
cp -R codex-dynamic-workflows "$HOME/.agents/skills/"

Then start a new agent session and invoke it with:

Use $codex-dynamic-workflows to plan and run a supervised multi-agent workflow for this task: ...

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 · 92 lines

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

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. {
  2. "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  3. "name": "modsmith",
  4. "owner": {
  5. "name": "Dan McAteer",
  6. "url": "https://github.com/DannyMac180"
  7. },
  8. "metadata": {
  9. "description": "ModSmith: a Claude Code skill for building, pricing and vetting mods, plus ready-made mods you can install one by one."
  10. },
  11. "plugins": [
  12. {
  13. "name": "modsmith",
  14. "source": "./modsmith",
  15. "strict": false,
  16. "skills": [
  17. "./"
  18. ],
  19. "description": "The ModSmith skill: ready-made mod patterns, per-turn token and prompt-cache review, vetting someone else's mod before installing, and rules for mods that work together.",
  20. "version": "0.2.0",
  21. "author": {
  22. "name": "Dan McAteer"
  23. },
  24. "license": "MIT",
  25. "homepage": "https://github.com/DannyMac180/skills/tree/main/modsmith",
  26. "keywords": [
  27. "mods",
  28. "function-hooks",
  29. "prompt-cache",
  30. "skills"
  31. ],
  32. "category": "development"
  33. },
  34. {
  35. "name": "modsmith-all",
  36. "source": "./modsmith/bundle",
  37. "strict": false,
  38. "description": "Installs the ModSmith skill and all six ModSmith mods in one go: quiz-after, next-steps-supervisor, assumption-ledger, mode-registry, effort-modes and artifact-dashboard. Remove any one later from /plugin.",
  39. "version": "0.2.0",
  40. "author": {
  41. "name": "Dan McAteer"
  42. },
  43. "license": "MIT",
  44. "dependencies": [
  45. "modsmith",
  46. "quiz-after",
  47. "next-steps-supervisor",
  48. "assumption-ledger",
  49. "mode-registry",
  50. "effort-modes",
  51. "artifact-dashboard"
  52. ],
  53. "category": "development"
  54. },
  55. {
  56. "name": "quiz-after",
  57. "source": "./modsmith/templates/quiz-after",
  58. "description": "After Claude finishes a task that changed something, shows 2-3 questions about what was built above the prompt. One cached fork on those turns only; /quiz turns it off.",
  59. "category": "learning"
  60. },
  61. {
  62. "name": "next-steps-supervisor",
  63. "source": "./modsmith/templates/next-steps-supervisor",
  64. "description": "After a turn that did real work, a cached side check asks whether the goal was met, where corners were cut and what needs your approval, with next steps as buttons. /supervisor turns it off.",
  65. "category": "productivity"
  66. },
  67. {
  68. "name": "assumption-ledger",
  69. "source": "./modsmith/templates/assumption-ledger",
  70. "description": "Gives Claude a register_assumption tool and shows the turn's assumptions, decisions and considered-but-not-done items above the prompt. No model calls of its own.",
  71. "category": "productivity"
  72. },
  73. {
  74. "name": "mode-registry",
  75. "source": "./modsmith/templates/mode-registry",
  76. "description": "One /mode switch any mod can add a mode to; the active mode shows in the prompt footer. No model calls.",
  77. "category": "productivity"
  78. },
  79. {
  80. "name": "effort-modes",
  81. "source": "./modsmith/templates/effort-modes",
  82. "description": "Three modes on the /mode switch: ui (low effort), api (medium), review (max). Needs mode-registry. Each switch rebuilds the prompt cache once.",
  83. "category": "productivity"
  84. },
  85. {
  86. "name": "artifact-dashboard",
  87. "source": "./modsmith/templates/artifact-dashboard",
  88. "description": "A one-line summary of a shared Kanban artifact above the prompt, so several Claude sessions work from the same board. No model tokens.",
  89. "category": "productivity"
  90. }
  91. ]
  92. }
README.md · README · 45 lines

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

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # Skills
  2. Public AI agent skills by [DannyMac180](https://github.com/DannyMac180).
  3. ## Go deeper
  4. I write [**Attention Heads**](https://attentionheads.substack.com/?utm_source=github&utm_medium=readme&utm_campaign=skills) — deep, evidence-backed writing on AI, cognition, and agentic engineering. The **Agentic Engineering Field Notes** series is where I publish practical advice on the craft of using AI. [Subscribe](https://attentionheads.substack.com/subscribe?utm_source=github&utm_medium=readme&utm_campaign=skills) to get new posts to your inbox.
  5. ## Available Skills
  6. - [`modsmith`](./modsmith/) - ModSmith: ready-made Claude Mods (quiz after the turn, assumption ledger, next-steps supervisor, mode registry, effort modes, shared Kanban dashboard) plus the judgment Claude Code's built-in mod authoring leaves out: per-turn token and prompt-cache review, vetting someone else's mod before installing, and rules for mods that compose.
  7. - [`codex-dynamic-workflows`](./codex-dynamic-workflows/) - Plan and run supervised AI-agent dynamic workflows with goal mode, subagents or simulated work packets, approval gates, integration, verification, and reusable workflow artifacts.
  8. - [`codex-relay`](./codex-relay/) - Relay: open one new native Codex task from your current task with a compact handoff, end your turn, and receive a single completion or blocker message back. Honors your chosen model and effort, or your default.
  9. - [`be-ambitious`](./be-ambitious/) - Ask for a deeper version of a task, not a bigger one: what a top professional would add, the rawest source material, the specific methods and tools, and an external check that the result is right. Then it rewrites your prompt to ask for exactly that.
  10. - [`fable-5-2-prompt-audit`](./fable-5-2-prompt-audit/) - Audit a project's prompts and instructions for lines written for earlier Claude models that Anthropic says to reconsider on Claude Fable 5.2. Reports each finding with file and line, the guidance behind it, and a proposed change; edits nothing without approval.
  11. - [`explain-this`](./explain-this/) - Explain any digital artifact (papers, articles, code) shaped by a persistent learner profile, with comprehension quizzes and spaced-repetition review. On first use it interviews you (~10 min) and creates `~/.explain-this/`.
  12. ## Install
  13. **Claude Code plugin marketplace (ModSmith).** Run `/plugin marketplace add DannyMac180/skills`, then `/plugin install modsmith-all@modsmith` for the skill plus all six ready-made mods, or `/plugin install modsmith@modsmith` for the skill alone and `/plugin install quiz-after@modsmith` (or any other ModSmith mod) one by one.
  14. **Any agent.** If your AI agent supports skills, you can point it at the GitHub URL for a skill and ask it to install that skill:
  15. ```text
  16. Install the AI agent skill at https://github.com/DannyMac180/skills/tree/main/codex-dynamic-workflows
  17. ```
  18. You can also clone this repo and copy a skill folder into your agent's skills directory. Adjust the destination path for your agent; this example uses Codex's user-scope skills folder (`~/.agents/skills`):
  19. ```bash
  20. git clone https://github.com/DannyMac180/skills.git
  21. cd skills
  22. mkdir -p "$HOME/.agents/skills"
  23. cp -R codex-dynamic-workflows "$HOME/.agents/skills/"
  24. ```
  25. Then start a new agent session and invoke it with:
  26. ```text
  27. Use $codex-dynamic-workflows to plan and run a supervised multi-agent workflow for this task: ...
  28. ```
  29. ## License
  30. MIT

Ratings and comments

Sign in to rate this skill.

Sign in

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