Skip to content
Back to search

nurijanian-skills

SkillWorks with Claude CodeGitHub

Claude Code and Cursor skills for product managers — PM coaching, verbalized sampling, tech sensemaking, and more.

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/gnurio--nurijanian-skills/badge.svg)](/listings/gnurio--nurijanian-skills)

HTML

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

One-liner (recommended)

npx nurijanian-skills

Installs all skills into Claude Code, Cursor, and Codex. Pass flags to pick targets:

npx nurijanian-skills --claude   # Claude Code only → ~/.claude/skills/<skill>/
npx nurijanian-skills --cursor   # Cursor only      → ~/.cursor/skills/<skill>/
npx nurijanian-skills --codex    # Codex only       → ~/.codex/skills/<skill>/

Combine flags to target multiple tools (`--claude --cursor`).

From source (for development)

git clone https://github.com/gnurio/nurijanian-skills.git
cd nurijanian-skills
node bin/install.js               # copy mode
node bin/install.js --link        # symlink mode (live-edit source → changes hit Claude Code instantly)

`--link` applies to Claude Code, Cursor, and Codex directory-form skills.

Where things land

| Tool | Location | Invocation | |-------------|------------------------------------------|-----------------------------------| | Claude Code | `~/.claude/skills/<skill>/SKILL.md` | `/skill-name` | | Cursor | `~/.cursor/skills/<skill>/SKILL.md` | `/skill-name` | | Codex | `~/.codex/skills/<skill>/SKILL.md` | `/skill-name` |

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.

README.md · README · 196 lines

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

  1. # nurijanian-skills
  2. A growing collection of Claude Code, Cursor, and Codex skills for product managers.
  3. These skills are part of [PM OS](https://www.prodmgmt.world/products/pm-os) — an AI workspace for product managers built inside Cursor and Claude Code, with 190+ skills, 168 frameworks, and 7 guided workflows. If you want the full system, start there. If you want just these skills, install them below.
  4. ## Install
  5. ### One-liner (recommended)
  6. ```bash
  7. npx nurijanian-skills
  8. ```
  9. Installs all skills into Claude Code, Cursor, and Codex. Pass flags to pick targets:
  10. ```bash
  11. npx nurijanian-skills --claude # Claude Code only → ~/.claude/skills/<skill>/
  12. npx nurijanian-skills --cursor # Cursor only → ~/.cursor/skills/<skill>/
  13. npx nurijanian-skills --codex # Codex only → ~/.codex/skills/<skill>/
  14. ```
  15. Combine flags to target multiple tools (`--claude --cursor`).
  16. ### From source (for development)
  17. ```bash
  18. git clone https://github.com/gnurio/nurijanian-skills.git
  19. cd nurijanian-skills
  20. node bin/install.js # copy mode
  21. node bin/install.js --link # symlink mode (live-edit source → changes hit Claude Code instantly)
  22. ```
  23. `--link` applies to Claude Code, Cursor, and Codex directory-form skills.
  24. ### Where things land
  25. | Tool | Location | Invocation |
  26. |-------------|------------------------------------------|-----------------------------------|
  27. | Claude Code | `~/.claude/skills/<skill>/SKILL.md` | `/skill-name` |
  28. | Cursor | `~/.cursor/skills/<skill>/SKILL.md` | `/skill-name` |
  29. | Codex | `~/.codex/skills/<skill>/SKILL.md` | `/skill-name` |
  30. ## Uninstall
  31. ```bash
  32. npx nurijanian-skills --uninstall
  33. ```
  34. Or target a single tool: `--uninstall --claude`.
  35. To wipe and reinstall fresh: `npx nurijanian-skills --clean`.
  36. ---
  37. ## Skills
  38. ### PM Alignment
  39. PM coaching grounded in what designers and engineers actually say about their best product managers. A survey of the people closest to PMs surfaces 7 behavioral clusters that separate great from average.
  40. | Skill | What it does |
  41. |-------|-------------|
  42. | `orchestrate-pm-alignment` | Entry point — detects what you need and routes you to the right mode |
  43. | `situation-retrospective` | Debrief a real situation against the 7 PM excellence clusters |
  44. | `team-perspective-reveal` | Simulate what your team would say about you in a peer survey |
  45. | `adversarial-roleplay` | Practice live with a frustrated designer or engineer, then debrief |
  46. | `decision-audit` | Audit whether a past decision was high quality — not just whether it worked out |
  47. | `blind-spot-scan` | Full interview to surface the behavioral patterns you can't see yourself |
  48. Start here:
  49. ```
  50. /orchestrate-pm-alignment
  51. ```
  52. ---
  53. ### Verbalized Sampling
  54. Implements Verbalized Sampling (Zhang et al. 2025) — a training-free technique that counteracts LLM mode collapse caused by typicality bias. Instead of asking for a single response, it prompts for a probability distribution over outputs to generate genuine diversity.
  55. Use when the task needs real variety: creative writing, brainstorming, synthetic data generation, persona simulation, adversarial examples, or any situation where "generate 5 ideas" keeps returning the same cluster.
  56. ```
  57. /verbalized-sampling
  58. ```
  59. ---
  60. ### Tech Sensemaking
  61. Analyzes technology announcements to surface non-obvious strategic implications using Verbalized Sampling. Works against any context — a business, product, codebase, feature branch, personal project, career, or exploratory domain. Goes beyond obvious hot takes to find new outcomes, affordances, and competitive levers a technology change creates.
  62. Trigger on: "analyze this announcement", "what does this mean for us", "what can we do with this", "strategic implications of X".
  63. ```
  64. /tech-sensemaking
  65. ```
  66. ---
  67. ### Focal Point Finder
  68. Find, evaluate, or create focal points in coordination and negotiation problems. Based on Thomas Schelling's *The Strategy of Conflict* — the foundational game theory text on how people converge on outcomes without explicit agreement.
  69. Use when multiple parties need to align on a single choice (a standard, a deadline, a boundary, a price, a process) and no one has the authority to dictate the answer. The skill walks through scanning for existing focal points, diagnosing why convergence is failing, and creating or proposing a focal point using 7 Schelling-grounded techniques.
  70. Trigger on: "where should we align?", "how do we get everyone on the same page?", "find a focal point", "Schelling point", "coordination problem", "propose a standard", "set a default".
  71. ```
  72. /focal-point-finder
  73. ```
  74. ---
  75. ### Rulebook for Arguments
  76. Construct, critique, and audit arguments using the complete methodology from Weston's *A Rulebook for Arguments*. Four modes: **BUILD** a logically sound argument from scratch, **AUDIT** an existing argument for validity and fallacies, **ESSAY** to draft or improve argumentative writing using the full extended-argument rules, or **DEBATE** to steelman both sides and identify the stronger position.
  77. Covers all 45 rules, 19 common fallacies, 3 definition rules, deductive forms (modus ponens, modus tollens, disjunctive syllogism, reductio ad absurdum), causal reasoning, analogy evaluation, and source quality assessment.
  78. ```
  79. /rulebook-for-arguments
  80. ```
  81. ---
  82. ### Make Requirements Great
  83. Review existing requirements or turn raw context into strong requirements using an 18-characteristic quality framework: unambiguous, clear, cohesive, consistent, conformant, current, modifiable, traceable, relevant, unique, categorised, complete, correct, concise, testable, implementation-independent, owned, and feasible.
  84. Use for PRDs, specs, user stories, acceptance criteria, BRDs, FRDs, requirements catalogues, requirements traceability, requirements audits, or feature notes that need to become formal requirements.
  85. ```
  86. /make-requirements-great
  87. ```
  88. ---
  89. ### Vibe Code Leaf Finder
  90. Audit a codebase and classify every file as **LEAF** (safe to vibe code freely), **BRANCH** (AI can draft, human reviews structural decisions), or **TRUNK** (human writes every line). Produces a `LEAF_REPORT.md` with a classification table, suggested stress tests per leaf file, and a plain-English summary for non-engineers.
  91. Grounded in Erik Schluntz's (Anthropic) leaf-vs-trunk framework from the *Vibe coding in prod* talk (Code w/ Claude, 2025): tech debt is acceptable in leaf nodes because nothing depends on them, but trunks and branches must stay protected, deeply understood, and extensible.
  92. Use when:
  93. - You want to know where it's safe to let Claude rewrite code without engineer review of every line.
  94. - You're a PM or founder who wants to ship features without breaking core architecture.
  95. - You're setting up a vibe-coding session and need to scope which files are in bounds.
  96. Trigger on: "vibe-code audit", "leaf finder", "where can I let Claude loose", "which files are safe to rewrite", "can a PM edit this".
  97. ```
  98. /vibe-code-leaf-finder
  99. ```
  100. ---
  101. ### Workflow Trellis
  102. Turn messy workflow evidence into a visible model of the work: durable obligations, entities, states, fragmented sources of truth, AI insertion points, and exception queues. Useful for analyzing interviews, customer research, operational workflows, vertical SaaS opportunities, PM workflows, and AI feature ideas.
  103. The core move is to represent the work before proposing automation, so product strategy is grounded in obligations, fragments, confidence signals, and human accountability.
  104. ```
  105. /workflow-trellis
  106. ```
  107. ---
  108. ### Reasons People Buy
  109. Ground persuasive writing in a real reason people buy before reaching for features or mechanisms. The skill uses 15 buying reasons, 8 deeper human drives, and buyer-journey checks to make copy outcome-led instead of feature-led.
  110. Use for landing pages, ads, offers, positioning, subscription copy, or audits where the question is "why would anyone buy this?"
  111. ```
  112. /reasons-people-buy
  113. ```
  114. ---
  115. ## Contributing
  116. To add a new skill:
  117. 1. Create `skills/<skill-name>/SKILL.md` with YAML frontmatter (`name`, `description`).
  118. 2. Put any reference files or templates in `skills/<skill-name>/references/` or `skills/<skill-name>/assets/`. Every skill must be self-contained — no shared top-level references.
  119. 3. Register it in `skills.json` (`name`, `dir`, `description`).
  120. 4. Add a section to this README.
  121. 5. Test locally with `node bin/install.js --link` so edits flow to Claude Code instantly.
  122. ## License
  123. MIT © George (gnurio)

Ratings and comments

Sign in to rate this skill.

Sign in

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