refactor(cli): update CLI documentation and add deprecation warning to skill commands (#2711)

Author: enesgules

.changeset/great-apples-like.md

@@ -0,0 +1,5 @@
+---
+"ctx7": patch
+---
+
+Add deprecation warning to skill commands

docs/clients/cli.mdx

@@ -1,12 +1,11 @@
 ---
 title: CLI
-description: The ctx7 CLI — fetch library documentation, manage skills, and configure Context7 MCP from your terminal
+description: The ctx7 CLI — fetch library documentation and configure Context7 MCP from your terminal
 ---
 
 The `ctx7` CLI is the command-line interface for Context7. It does three things:
 
 - **Fetch library documentation** — resolve any library by name and query its up-to-date docs directly in your terminal, without opening a browser
-- **Manage AI coding skills** — install, search, generate, and remove skills from the Context7 registry
 - **Configure Context7 MCP** — set up the MCP server for Claude Code, Cursor, or OpenCode with a single command
 
 The CLI is useful both as a standalone tool (fetching docs while you code) and as a setup utility (wiring up Context7 for your AI coding agent).
@@ -191,7 +190,7 @@ If you installed the CLI itself with `npm install -g ctx7`, remove that separate
 
 ## Authentication
 
-Most commands work without authentication. Log in to unlock skill generation and higher rate limits on documentation commands.
+Most commands work without authentication. Log in to unlock higher rate limits on documentation commands.
 
 ### Commands
 
@@ -222,178 +221,17 @@ export CONTEXT7_API_KEY=your_key
 | Feature                                                  | Required                                                                     |
 | -------------------------------------------------------- | ---------------------------------------------------------------------------- |
 | `ctx7 library` / `ctx7 docs`                             | No — login gives higher rate limits                                          |
-| `ctx7 skills install / search / suggest / list / remove` | No                                                                           |
-| `ctx7 skills generate`                                   | Yes                                                                          |
 | `ctx7 setup`                                             | Yes — unless `--api-key` is passed (`--oauth` also skips login for MCP mode) |
 
 ---
 
-## Skills
-
-Manage AI coding skills from the Context7 registry. See [Skills](/skills) for a full explanation of what skills are, the registry, trust scores, and skill file structure.
-
-### ctx7 skills install
-
-Install skills from any GitHub repository. Repository format is `/owner/repo`.
-
-```bash
-# Interactive — pick from a list
-ctx7 skills install /anthropics/skills
-
-# Install a specific skill by name
-ctx7 skills install /anthropics/skills pdf
-
-# Install all skills without prompting
-ctx7 skills install /anthropics/skills --all
-```
-
-**Target a specific AI coding assistant:**
-
-```bash
-ctx7 skills install /anthropics/skills pdf --claude      # Claude Code
-ctx7 skills install /anthropics/skills pdf --cursor      # Cursor
-ctx7 skills install /anthropics/skills pdf --universal   # Universal (.agents/skills/)
-ctx7 skills install /anthropics/skills pdf --antigravity
-ctx7 skills install /anthropics/skills pdf --all-agents  # Universal + all vendor-specific locations
-```
-
-**Install globally** (available across all projects):
-
-```bash
-ctx7 skills install /anthropics/skills pdf --global
-ctx7 skills install /anthropics/skills --all --global
-ctx7 skills install /anthropics/skills pdf --global --universal --yes
-ctx7 skills install /anthropics/skills pdf --global --all-agents --yes
-```
-
-<Note>
-  When installing to multiple clients, the skill files are created in your primary client's
-  directory and symlinked to the others.
-</Note>
-
-Alias: `ctx7 si /anthropics/skills pdf`
-
-### ctx7 skills search
-
-Find skills across all indexed repositories by keyword. Shows an interactive list — select to install directly.
-
-```bash
-ctx7 skills search pdf
-ctx7 skills search typescript testing
-ctx7 skills search react nextjs
-```
-
-Alias: `ctx7 ss pdf`
-
-### ctx7 skills suggest
-
-Auto-detects your project dependencies and recommends relevant skills from the registry.
-
-```bash
-# Scan current project
-ctx7 skills suggest
-
-# Target a specific client
-ctx7 skills suggest --claude
-ctx7 skills suggest --cursor
-
-# Install suggestions globally
-ctx7 skills suggest --global
-```
-
-Scans: `package.json`, `requirements.txt`, `pyproject.toml`, `Cargo.toml`, `go.mod`, `Gemfile`.
-
-Alias: `ctx7 ssg`
-
-### ctx7 skills generate
-
-Generate a custom skill tailored to your stack using AI. **Requires login.**
-
-```bash
-ctx7 skills generate
-
-# Generate and install to a specific client
-ctx7 skills generate --claude
-ctx7 skills generate --cursor
-ctx7 skills generate --universal
-
-# Generate as a global skill
-ctx7 skills generate --global
-```
-
-**Generation flow:**
-
-1. Describe the expertise you want (e.g., "OAuth authentication with NextAuth.js")
-2. Select relevant libraries from search results
-3. Answer 3 clarifying questions to focus the skill
-4. Review the generated skill and request changes if needed
-5. Choose where to install it
-
-<Tip>
-  Describe best practices and constraints, not step-by-step tutorials. "TypeScript strict mode
-  patterns" generates a more useful skill than "how to write TypeScript."
-</Tip>
-
-**Weekly limits:** Free accounts get 6 generations/week, Pro accounts get 10.
-
-Aliases: `ctx7 skills gen`, `ctx7 skills g`
-
-### ctx7 skills list
-
-View skills installed in your project or globally.
-
-```bash
-ctx7 skills list                   # All detected clients
-ctx7 skills list --claude
-ctx7 skills list --cursor
-ctx7 skills list --global
-```
-
-### ctx7 skills info
-
-Preview all available skills in a repository without installing.
-
-```bash
-ctx7 skills info /anthropics/skills
-```
-
-### ctx7 skills remove
-
-Uninstall a skill by name.
-
-```bash
-ctx7 skills remove pdf
-ctx7 skills remove pdf --claude
-ctx7 skills remove pdf --global
-```
-
-Aliases: `ctx7 skills rm`, `ctx7 skills delete`
-
----
-
-## Shortcuts
-
-| Shortcut          | Full command           |
-| ----------------- | ---------------------- |
-| `ctx7 si`         | `ctx7 skills install`  |
-| `ctx7 ss`         | `ctx7 skills search`   |
-| `ctx7 ssg`        | `ctx7 skills suggest`  |
-| `ctx7 skills i`   | `ctx7 skills install`  |
-| `ctx7 skills s`   | `ctx7 skills search`   |
-| `ctx7 skills ls`  | `ctx7 skills list`     |
-| `ctx7 skills rm`  | `ctx7 skills remove`   |
-| `ctx7 skills gen` | `ctx7 skills generate` |
-| `ctx7 skills g`   | `ctx7 skills generate` |
-
----
-
 ## Telemetry
 
 The CLI collects anonymous usage data to help improve the product. To disable:
 
 ```bash
 # For a single command
-CTX7_TELEMETRY_DISABLED=1 ctx7 skills search pdf
+CTX7_TELEMETRY_DISABLED=1 ctx7 docs /facebook/react "useEffect examples"
 
 # Permanently — add to ~/.bashrc or ~/.zshrc
 export CTX7_TELEMETRY_DISABLED=1
@@ -404,12 +242,6 @@ export CTX7_TELEMETRY_DISABLED=1
 ## Next Steps
 
 <CardGroup cols={2}>
-  <Card title="Browse Skills" icon="magnifying-glass" href="https://context7.com/skills">
-    Explore the skills registry
-  </Card>
-  <Card title="Skills Guide" icon="book" href="/skills">
-    Learn about skill file structure, trust scores, and the registry
-  </Card>
   <Card title="Claude Code" icon="terminal" href="/clients/claude-code">
     Set up Context7 in Claude Code
   </Card>

docs/docs.json

@@ -28,7 +28,6 @@
           "adding-libraries",
           "library-updates",
           "api-guide",
-          "skills",
           "tips"
         ]
       },
@@ -234,4 +233,4 @@
       }
     ]
   }
-}
+}

docs/howto/verification.mdx

@@ -28,7 +28,6 @@ This badge appears on:
 - Your library's main page
 - Search results
 - Library listings and tables
-- Skills associated with your library
 
 ## How to Get Verified
 
@@ -40,7 +39,6 @@ Libraries are automatically verified when they meet certain quality thresholds:
 
 - **High trust score**: Libraries with a trust score of 9 or above. Trust score is calculated based on the GitHub organization/user profile, considering factors like total stars, number of repositories, account age, recent activity, followers, and profile completeness.
 - **Top 100 libraries**: Most-used libraries by API requests
-- **Top 100 skills**: Libraries with the most-installed skills
 
 Automatic verification is checked daily. If your library qualifies, it will be verified automatically without any action required.
 
@@ -121,13 +119,6 @@ You can check your library's verification status on the admin page:
 | **Verified** | Green badge displayed, full verification benefits |
 | **Not Verified** | No badge, apply to get verified |
 
-## Skills and Verification
-
-Skills inherit the verification status of their parent library. When your library is verified:
-
-- All skills associated with your library display the verified badge
-- Skills rank higher in skill search results
-
 ## FAQ
 
 ### How long does manual verification take?
@@ -151,7 +142,7 @@ Automatic verification is recalculated daily. If your library no longer meets th
 
 ### My library is popular but not verified. Why?
 
-Automatic verification considers multiple factors including trust score, usage statistics, and skill installs. When you apply manually, Context7 also checks quality criteria like GitHub stars, popularity ranking, and referring domains. If you believe your library meets any of these thresholds, please apply manually and the check will run immediately.
+Automatic verification considers multiple factors including trust score and usage statistics. When you apply manually, Context7 also checks quality criteria like GitHub stars, popularity ranking, and referring domains. If you believe your library meets any of these thresholds, please apply manually and the check will run immediately.
 
 ## Need Help?
 

docs/security/data-safety.mdx

@@ -12,7 +12,6 @@ Context7 indexes documentation from public and private sources. To prevent malic
 
 - **Robust Detection** — Content is analyzed using a classifier tailored for Context7 to identify prompt injection attempts and malware-related patterns
 - **Targeted Validation** — Suspicious content is subjected to additional checks
-- **Skills.md Handling** — A separate but related detection pipeline is used for [Skills](/skills) files, adapted to their distinct structure and intent
 - **Continuous Monitoring** — Flagged content is tracked and reviewed on an ongoing basis
 - **Regular Updates** — Detection logic is updated to address evolving attack methods and new injection techniques