pm-claude-skills 22.0.0 → 22.2.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +9 -5
  2. package/package.json +2 -1
package/README.md CHANGED
@@ -12,7 +12,7 @@
12
12
  [![Platforms](https://img.shields.io/badge/works%20with-Claude%20%7C%20ChatGPT%20%7C%20Gemini%20%7C%20Cursor%20%7C%20Codex%20%7C%20Hermes-8A2BE2)](#-works-with--cross-tool-compatibility)
13
13
  [![SkillCheck](https://img.shields.io/github/actions/workflow/status/mohitagw15856/pm-claude-skills/skillcheck.yml?branch=main&label=SkillCheck)](.github/workflows/skillcheck.yml)
14
14
  [![Security Audit](https://img.shields.io/github/actions/workflow/status/mohitagw15856/pm-claude-skills/skill-audit.yml?branch=main&label=security%20audit)](.github/workflows/skill-audit.yml)
15
- [![Version](https://img.shields.io/badge/version-22.0.0-brightgreen)](https://github.com/mohitagw15856/pm-claude-skills/releases)
15
+ [![Version](https://img.shields.io/badge/version-22.2.0-brightgreen)](https://github.com/mohitagw15856/pm-claude-skills/releases)
16
16
  [![Install](https://img.shields.io/badge/Install%20in%20Claude%20Code-2%20minutes-orange)](https://github.com/mohitagw15856/pm-claude-skills#-quick-install-2-minutes)
17
17
  [![License](https://img.shields.io/badge/license-MIT-lightgrey)](LICENSE)
18
18
  [![Sponsor](https://img.shields.io/badge/sponsor-❤️-ff69b4)](https://github.com/sponsors/mohitagw15856)
@@ -24,7 +24,7 @@
24
24
 
25
25
  A community-built library of professional skills for every field — product management, engineering, customer success, marketing, social media, writers, design, legal, finance, HR, sales, operations, research, and more. Each skill is a structured `SKILL.md` file that teaches an AI assistant how to produce professional-grade outputs for your workflows. Skills run natively in **Claude Code** and **Hermes Agent** (same open `SKILL.md` standard), and ship as ready-to-paste exports for **ChatGPT** and **Gemini** — see [Works With](#-works-with--cross-tool-compatibility).
26
26
 
27
- **🆕 Latest release (v22.0.0 — Closing the Loop):** skills now [**improve themselves**](#-eval-verified-quality--not-just-quantity) via the eval harness, you can [**grade your own drafts**](#-eval-verified-quality--not-just-quantity) (Critique mode), [**build your own recipes**](#-workflow-recipes--chain-skills-into-one-flow) on the Workflow Canvas, ground skills in your real data, and [**`/red-team`**](skills/red-team-review/SKILL.md) any plan. Now **175 skills**, 15 eval-scored. See the [changelog](#-changelog).
27
+ **🆕 Latest release (v22.2.0 — Studio, Auto-Agent & an editor extension):** create a skill in your browser with [**Skill Studio**](https://mohitagw15856.github.io/pm-claude-skills/studio.html) (→ one-click PR), let the [**✨ Auto-Agent**](https://mohitagw15856.github.io/pm-claude-skills/agent.html) plan and run a skill chain from a plain goal, and use the [**VS Code / Cursor extension**](vscode-extension/) to insert skills in your editor. Builds on the v22.1 Skills Hub. **175 skills**, 15 eval-scored. See the [changelog](#-changelog).
28
28
 
29
29
  ### ▶ See it in action — [try the live Skill Playground](https://mohitagw15856.github.io/pm-claude-skills/)
30
30
 
@@ -105,7 +105,7 @@ Individual skills are great. **Chaining** them is the superpower. A *recipe* run
105
105
 
106
106
  → Full detail and how to add your own in [**WORKFLOWS.md**](WORKFLOWS.md). Recipes run as slash commands in Claude Code, or over MCP via the `get_workflow` tool.
107
107
 
108
- **Or build your own visually.** The [**Workflow Canvas**](https://mohitagw15856.github.io/pm-claude-skills/canvas.html) lets you drag any skills into a custom chain and run it in the browser — each step's output feeds the next. Like n8n, but for professional thinking.
108
+ **Or build your own visually.** The [**Workflow Canvas**](https://mohitagw15856.github.io/pm-claude-skills/canvas.html) lets you drag any skills into a custom chain and run it in the browser — each step's output feeds the next. Like n8n, but for professional thinking. Don't know which skills to use? The [**✨ Auto-Agent**](https://mohitagw15856.github.io/pm-claude-skills/agent.html) takes a plain-English goal, picks the right skills, and runs the chain for you.
109
109
 
110
110
  [![Workflow Canvas — drag skills into a chain and run it, each step feeding the next](web/docs-assets/canvas-demo.gif)](https://mohitagw15856.github.io/pm-claude-skills/canvas.html)
111
111
 
@@ -159,7 +159,9 @@ That's not luck — it's a [self-improving pipeline](scripts/improve-skill.mjs)
159
159
 
160
160
  [![Compare mode — the same prompt with and without the skill, side by side](web/docs-assets/compare-demo.gif)](https://mohitagw15856.github.io/pm-claude-skills/)
161
161
 
162
- **Already have a draft?** Flip on **📝 Critique mode** in the Playground — paste your existing PRD/roadmap/update and get a rubric score, ranked gaps, and a redline graded against the skill's framework. And before you ship, run [**`/red-team`**](skills/red-team-review/SKILL.md) to stress-test the plan against a room of hostile expert personas.
162
+ **Already have a draft?** Flip on **📝 Critique mode** in the Playground — or use the standalone [**Grade your work**](https://mohitagw15856.github.io/pm-claude-skills/grade.html) tool — to paste an existing PRD/roadmap/update and get a rubric score, ranked gaps, and a redline graded against the skill's framework. Before you ship, run [**`/red-team`**](skills/red-team-review/SKILL.md) to stress-test the plan against a room of hostile expert personas.
163
+
164
+ This whole thing is an open, reproducible **[benchmark for AI professional work](https://mohitagw15856.github.io/pm-claude-skills/benchmark.html)** — and it's *eval-gated*: every contributed skill is auto-checked for structure and scored on the rubric. The easiest way to add one is **[Skill Studio](https://mohitagw15856.github.io/pm-claude-skills/studio.html)** — describe a skill in your browser, generate a compliant `SKILL.md`, and open a pull request in one click ([or use the form →](https://github.com/mohitagw15856/pm-claude-skills/issues/new?template=submit-skill.yml)).
163
165
 
164
166
  ---
165
167
 
@@ -258,6 +260,8 @@ There are two kinds of support. **Native `SKILL.md` agents** read the file as-is
258
260
  auto-discover skills from the `description` frontmatter. **Other tools** take the markdown
259
261
  body as a system prompt — for those we ship ready-made [exports](#ready-to-use-exports).
260
262
 
263
+ **In your editor (VS Code / Cursor):** the [**`vscode-extension/`**](vscode-extension/) brings all 175 skills into the Command Palette — search and *insert a skill as context* for Copilot/Cursor chat, copy it, or open it in the Playground.
264
+
261
265
  | Platform | How it works | Auto-trigger? |
262
266
  |---|---|---|
263
267
  | **Claude Code** (CLI / desktop / web / IDE) | Native. Install via the plugin marketplace; Claude loads a skill automatically when your request matches its description. | ✅ Yes |
@@ -547,7 +551,7 @@ More templates will follow. If you want to contribute one, see the [template con
547
551
 
548
552
  ## 📋 Changelog
549
553
 
550
- **Latest: v22.0.0 — Closing the Loop.** Skills now **improve themselves** (eval → critique → rewrite, kept only if the score rises), you can **grade your own drafts** (Critique mode), **ground skills in your real data**, **build your own recipes** on the Workflow Canvas, and **red-team any plan**. The eval harness caught three weak skills and the fix lifted them 2.0 → 4.75/5. Now **175 skills**, 15 eval-scored.
554
+ **Latest: v22.2.0 — Studio, Auto-Agent & editor extension.** Skill Studio (browser authoring → one-click PR), the Auto-Agent (goal → planned skill chain), and a VS Code / Cursor extension. Builds on **v22.1.0 (the Skills Hub)** and **v22.0.0 (Closing the Loop)**. Now **175 skills**, 15 eval-scored.
551
555
 
552
556
  Full [Keep a Changelog](https://keepachangelog.com/)-format history — every release back to the start — is in **[CHANGELOG.md](CHANGELOG.md)**.
553
557
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "pm-claude-skills",
3
- "version": "22.0.0",
3
+ "version": "22.2.0",
4
4
  "type": "module",
5
5
  "description": "175 professional Agent Skills (SKILL.md) + subagents + slash commands for Claude, ChatGPT, Gemini, Cursor, Codex & Hermes. Install into any AI coding tool with: npx pm-claude-skills add --agent <tool>.",
6
6
  "keywords": [
@@ -59,6 +59,7 @@
59
59
  "build:workflows": "node scripts/build-workflows.mjs",
60
60
  "build:samples": "node scripts/build-samples.mjs",
61
61
  "build:pages": "node scripts/build-skill-pages.mjs",
62
+ "build:community": "node scripts/build-community.mjs",
62
63
  "build:og": "node scripts/build-og-images.mjs",
63
64
  "skill-of-the-week": "node scripts/skill-of-the-week.mjs",
64
65
  "check": "node scripts/skillcheck.mjs && node scripts/build-exports.mjs --check && node scripts/build-workflows.mjs --check && node web/build-skills.mjs && node scripts/build-samples.mjs && git diff --exit-code -- web/skills.json web/samples.json",