Skip to content
Back to search

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

HTML

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

Add this marketplace to your Claude Code:

/plugin marketplace add obie/skills

Then install individual skills:

/plugin install better-stimulus@obie-skills

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 · 183 lines

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

  1. {
  2. "name": "obie-skills",
  3. "owner": {
  4. "name": "Obie Fernandez",
  5. "email": "obiefernandez@gmail.com"
  6. },
  7. "metadata": {
  8. "description": "Curated collection of production-ready Claude Code skills",
  9. "version": "1.0.0"
  10. },
  11. "plugins": [
  12. {
  13. "name": "better-stimulus",
  14. "source": "./skills/better-stimulus",
  15. "description": "Apply Better Stimulus best practices for writing maintainable, reusable StimulusJS controllers following SOLID principles",
  16. "version": "1.0.0",
  17. "author": {
  18. "name": "Obie Fernandez"
  19. },
  20. "keywords": [
  21. "stimulus",
  22. "hotwire",
  23. "rails",
  24. "javascript",
  25. "best-practices",
  26. "solid"
  27. ],
  28. "category": "development",
  29. "homepage": "https://github.com/obie/skills",
  30. "license": "MIT"
  31. },
  32. {
  33. "name": "rails-activity-timeline",
  34. "source": "./skills/rails-activity-timeline",
  35. "description": "Add polymorphic activity timelines with live Turbo Stream updates to any Rails model",
  36. "version": "1.0.0",
  37. "author": {
  38. "name": "Obie Fernandez"
  39. },
  40. "keywords": [
  41. "rails",
  42. "hotwire",
  43. "turbo-streams",
  44. "activity-log",
  45. "audit-trail",
  46. "timeline",
  47. "action-cable"
  48. ],
  49. "category": "development",
  50. "homepage": "https://github.com/obie/skills",
  51. "license": "MIT"
  52. },
  53. {
  54. "name": "rails-tiptap-autosave",
  55. "source": "./skills/rails-tiptap-autosave",
  56. "description": "Add Tiptap rich text editing with debounced autosave to Rails models using Stimulus",
  57. "version": "1.0.0",
  58. "author": {
  59. "name": "Obie Fernandez"
  60. },
  61. "keywords": [
  62. "rails",
  63. "tiptap",
  64. "stimulus",
  65. "rich-text",
  66. "autosave",
  67. "markdown",
  68. "hotwire"
  69. ],
  70. "category": "development",
  71. "homepage": "https://github.com/obie/skills",
  72. "license": "MIT"
  73. },
  74. {
  75. "name": "deletion-test",
  76. "source": "./skills/deletion-test",
  77. "description": "Run the regenerative-software deletion test on a component: extract intent and decision records, write a durable contract spec, mutation-test both oracles, regenerate the implementation in isolated arms, score by behavioral diff, and report evaluation gaps",
  78. "version": "0.1.0",
  79. "author": {
  80. "name": "Obie Fernandez"
  81. },
  82. "keywords": [
  83. "regenerative-software",
  84. "deletion-test",
  85. "mutation-testing",
  86. "mutant",
  87. "provenance",
  88. "decision-records",
  89. "evaluations",
  90. "ruby",
  91. "rails",
  92. "feelings"
  93. ],
  94. "category": "development",
  95. "homepage": "https://github.com/obie/skills",
  96. "license": "MIT"
  97. },
  98. {
  99. "name": "graphs-and-shit",
  100. "source": "./skills/graphs-and-shit",
  101. "description": "Pull the latest data from a survey, sheet, API, database or file and turn it into a shareable, editable Claude Doc with hand-drawn charts, each one screenshot-checked; refreshes the doc when the data changes",
  102. "version": "0.1.0",
  103. "author": {
  104. "name": "Obie Fernandez"
  105. },
  106. "keywords": [
  107. "charts",
  108. "data-visualization",
  109. "reports",
  110. "claude-docs",
  111. "artifacts",
  112. "surveys",
  113. "google-forms"
  114. ],
  115. "category": "productivity",
  116. "homepage": "https://github.com/obie/skills",
  117. "license": "MIT"
  118. },
  119. {
  120. "name": "beat-the-benchmark-website",
  121. "source": "./skills/beat-the-benchmark-website",
  122. "description": "Build a website that measurably beats a named benchmark site: audit the benchmark, owner voting galleries, a parallel agent build with one integrator, QC and Codex review of an immutable preview, then a scope freeze and byte-parity production ship",
  123. "category": "development",
  124. "keywords": [
  125. "website",
  126. "qc",
  127. "playwright",
  128. "cloudflare-pages",
  129. "agent-teams",
  130. "review",
  131. "astro"
  132. ],
  133. "version": "1.0.0",
  134. "author": {
  135. "name": "Obie Fernandez"
  136. },
  137. "homepage": "https://github.com/obie/skills",
  138. "license": "MIT"
  139. },
  140. {
  141. "name": "ai-character-imaging",
  142. "source": "./skills/ai-character-imaging",
  143. "description": "Keep one AI character or persona consistent across stills and motion loops: canon identity pack, prompt slots, owner review rounds, filter workarounds, waxy-free upscaling, feathered patch merges and seamless Kling loops",
  144. "category": "creative",
  145. "keywords": [
  146. "ai-images",
  147. "character-consistency",
  148. "gpt-image",
  149. "kling",
  150. "fal",
  151. "persona",
  152. "video-loops"
  153. ],
  154. "version": "1.0.0",
  155. "author": {
  156. "name": "Obie Fernandez"
  157. },
  158. "homepage": "https://github.com/obie/skills",
  159. "license": "MIT"
  160. },
  161. {
  162. "name": "decision-docket",
  163. "source": "./skills/decision-docket",
  164. "description": "Keep one standing page of every decision you need from the user, each answerable cold with its context, options, costs and gains, your recommendation and what happens if they do nothing; they record answers on the page, you act on them, log the ruling and remove the card",
  165. "category": "productivity",
  166. "keywords": [
  167. "decisions",
  168. "questions",
  169. "artifacts",
  170. "async",
  171. "autonomous-agents",
  172. "human-in-the-loop",
  173. "docket"
  174. ],
  175. "version": "1.0.0",
  176. "author": {
  177. "name": "Obie Fernandez"
  178. },
  179. "homepage": "https://github.com/obie/skills",
  180. "license": "MIT"
  181. }
  182. ]
  183. }
README.md · README · 169 lines

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

  1. # Claude Code Skills by Obie
  2. Production-ready skills for enhanced Claude Code development workflows.
  3. ## Installation
  4. Add this marketplace to your Claude Code:
  5. ```shell
  6. /plugin marketplace add obie/skills
  7. ```
  8. Then install individual skills:
  9. ```shell
  10. /plugin install better-stimulus@obie-skills
  11. ```
  12. ## Available Skills
  13. ### Better Stimulus
  14. Apply opinionated best practices from [betterstimulus.com](https://betterstimulus.com/) when writing or refactoring Stimulus controllers.
  15. **When to use:**
  16. - Writing new Stimulus controllers
  17. - Refactoring existing Stimulus code
  18. - Reviewing Stimulus controller architecture
  19. - Debugging inter-controller communication
  20. **Key patterns:**
  21. - Values API for reactive state management
  22. - Static classes for configurable CSS
  23. - Single Responsibility Principle
  24. - Minimal connect() usage
  25. - Declarative event registration
  26. **Invoke with:** `/better-stimulus` or Claude invokes automatically when working with Stimulus code
  27. ### MCP OAuth Setup
  28. Implement zero-configuration OAuth for MCP (Model Context Protocol) server connections using Dynamic Client Registration (RFC 7591) and Authorization Server Metadata Discovery (RFC 8414). Battle-tested with Linear, Sentry, and Granola.
  29. **When to use:**
  30. - Building admin UIs for managing MCP server connections with OAuth
  31. - Integrating with third-party MCP providers
  32. - Implementing MCP Streamable HTTP transport with authenticated tool sync
  33. - Adding OAuth to an existing MCP connector management system
  34. **What it covers:**
  35. - RFC 8414 metadata discovery + RFC 7591 dynamic client registration
  36. - PKCE (S256) authorization flow with signed state
  37. - Token exchange, storage, and refresh (shared + per-agent modes)
  38. - MCP Streamable HTTP tool sync (session handshake, SSE parsing)
  39. - UI patterns (Stimulus forms, Connect vs Sync logic)
  40. - Common failure modes and fixes (Turbo Drive, route helpers, SSE)
  41. **Invoke with:** `/mcp-oauth-setup` or Claude invokes automatically when implementing MCP OAuth
  42. ### Deletion Test
  43. Run the deletion test from Chad Fowler's *Regenerative Software* on one component: could we delete this and rebuild it from what the system holds outside the code? Extracts intent and decision records from code, history, and tickets; writes a durable contract spec that asserts promises rather than pinned numbers; mutation-tests both oracles; deletes the implementation and regenerates it in isolated arms from the intent alone; scores every candidate by behavioral diff; reports what the code knew that nothing else did.
  44. **When to use:**
  45. - Making a component safely replaceable, or finding out whether it already is
  46. - Extracting the reasons buried in a legacy module's comments, commits, and tickets
  47. - Checking whether a test suite is an oracle or a museum of the current implementation
  48. - Establishing a baseline before adopting regeneration tooling
  49. **What it covers:**
  50. - Intent document and decision-record formats, with the sparse variant for a decisions-withheld arm
  51. - Durable contract specs: properties over grids, the language-change membership test, degenerate inputs
  52. - mutant two-pass scoring with a survivor classification table
  53. - Isolated regeneration arms in git worktrees with a regenerator brief
  54. - Behavioral-diff scoring scripts and a findings template
  55. - Optional survivor triage with a calibrated decision model (feelings / Jev)
  56. **Invoke with:** `/deletion-test` or Claude invokes automatically when asked to regenerate a module from spec or make a component replaceable
  57. ### Graphs and Shit
  58. Pull the latest data from wherever it lives and turn it into a shareable, editable Claude Doc with hand-drawn charts. The lead states the answer with its numbers. Each section gets one chart for one finding, and every chart is checked in a screenshot before the doc is called done. Run it again later and it refreshes the same doc with new numbers.
  59. **When to use:**
  60. - Survey results that need to go in front of a team
  61. - A spreadsheet or query result that people will discuss and comment on
  62. - Numbers that keep changing, such as responses trickling in, where the doc should be refreshed rather than rebuilt
  63. **What it covers:**
  64. - Pulling fresh data (Google Forms, Sheets, CSV, a database, an API) and tallying it with a script
  65. - A short brief per chart: the reader, the finding, the form a pro would draw
  66. - Creating the doc from the Docs Artifact type and landing an outline the reader can watch fill
  67. - Hand-rolled `claude.Visualize` charts: grey first, one accent, values on the marks, everything computed from rows
  68. - Screenshot review and redraws
  69. - Keeping anonymous data anonymous
  70. - Refreshing chart rows and prose numbers without clobbering people's edits
  71. Requires the Artifact tool and the Claude Docs connector. Without the connector it falls back to a single HTML Artifact.
  72. **Invoke with:** `/graphs-and-shit <data source>` or Claude invokes automatically when asked to chart results into something shareable
  73. ### beat-the-benchmark-website
  74. Build a site that beats a named benchmark site on every dimension the owner cares about, and prove it.
  75. **When to use:** a new or rebuilt website with a reference site to beat, and an owner who wants evidence, not opinions.
  76. **Key patterns:**
  77. - Audit the benchmark into a scored QC matrix before building
  78. - One generated source of truth; owner voting galleries for every visual choice
  79. - Parallel builders, one integrator; QC and Codex review an immutable preview
  80. - Scope freeze, then byte-parity check of production against the verified build
  81. - Playwright scripts: screenshot matrix, decoded image ratio, tap targets, forbidden-token sweep, JSON-LD
  82. **Invoke with:** `/beat-the-benchmark-website <site> vs <benchmark>`
  83. ### ai-character-imaging
  84. Keep one synthetic character recognisably the same across many images and short video loops.
  85. **When to use:** a virtual artist, mascot or brand persona that needs a consistent face across plates and motion.
  86. **Key patterns:**
  87. - Canon identity pack of the newest approved face, plus an identity paragraph
  88. - Slot prompts; refs carry identity only; GPT Image edit with refs
  89. - Owner review rounds; promote approved picks to ref #1
  90. - Upscale with face enhancement off; patch defects with a feathered merge
  91. - Kling image-to-video loops with the seam scored by frame difference
  92. **Invoke with:** `/ai-character-imaging` or Claude invokes automatically for consistent-character generation
  93. ### Decision Docket
  94. Keep one standing page of every decision Claude needs from you, instead of questions buried in chat replies. Each card can be answered cold: what happened, why it's your call, the options with their cost and gain, Claude's recommendation, and what happens if you do nothing. You pick an option and record it on the page; on its next check-in Claude reads the answer, acts on it, logs the ruling and removes the card, so the page only ever shows what is still waiting on you.
  95. **When to use:**
  96. - Long-running or autonomous work where Claude keeps going while you're elsewhere
  97. - You move between many threads and lose questions asked inline
  98. - Sorting a list of items (keep, hide, cut) or auditing calls Claude made without you
  99. **What it covers:**
  100. - A ready-made docket page (an Artifact with a small database): a sticky index, one card per decision, light and dark themes, a phone layout, drafts kept while you type
  101. - The question format and how to write a card someone can decide from with no other context
  102. - The check-in loop: read answers, act, log the ruling, delete the card pinned to its version
  103. - FYI "calls" cards, item lists with their own choices, owner-only or team write access
  104. **Invoke with:** `/decision-docket` or Claude invokes automatically when it has a decision to put to you during long-running work
  105. ## How It Works
  106. Skills are stored in `skills/<skill-name>/SKILL.md` format. Each skill:
  107. - Contains YAML frontmatter describing when to use it
  108. - Includes comprehensive instructions for Claude
  109. - May reference supporting documentation files
  110. - Can be invoked manually with `/skill-name` or automatically by Claude
  111. ## Contributing
  112. Want to add your own skills to this marketplace?
  113. 1. Fork this repository
  114. 2. Create a new skill directory under `skills/`
  115. 3. Write your `SKILL.md` following the [Agent Skills standard](https://agentskills.io)
  116. 4. Add an entry to `.claude-plugin/marketplace.json`
  117. 5. Submit a pull request
  118. ## License
  119. MIT - See LICENSE file for details

Ratings and comments

Sign in to rate this skill.

Sign in

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