docs: add Claudeception meta-skill documentation

Add documentation for blader/Claudeception - a meta-skill that
auto-generates skills from Claude Code session discoveries.

Changes:
- guide/ultimate-guide.md: New section 5.5 "Automatic Skill Generation"
- machine-readable/reference.yaml: claudeception + claudeception_guide entries
- README.md: Add Skills category with Claudeception reference
- CHANGELOG.md: Document addition in Unreleased

Source: Community contribution via Laurent Dosdat

Co-Authored-By: Claude <noreply@anthropic.com>

CHANGELOG.md

@@ -6,6 +6,17 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
 ## [Unreleased]
 
+### Added
+
+- **Claudeception documentation** — Meta-skill for automatic skill generation
+  - **Repository**: [blader/Claudeception](https://github.com/blader/Claudeception) by Siqi Chen (@blader)
+  - **What it does**: Monitors Claude Code sessions and auto-extracts discoveries into reusable skills
+  - **Validated use case**: `pre-merge-code-review` skill auto-generated from debugging workflow
+  - **Documentation added**:
+    - `guide/ultimate-guide.md` Section 5.5: "Automatic Skill Generation: Claudeception" (~45 lines)
+    - `machine-readable/reference.yaml`: `claudeception` + `claudeception_guide` entries
+  - **Source**: Community contribution via Laurent Dosdat
+
 ---
 
 ## [3.11.1] - 2026-01-22

README.md

@@ -233,6 +233,8 @@ claude-code-ultimate-guide/
 
 **Security Hooks** (15): [dangerous-actions-blocker](./examples/hooks/bash/dangerous-actions-blocker.sh), [prompt-injection-detector](./examples/hooks/bash/prompt-injection-detector.sh), [unicode-injection-scanner](./examples/hooks/bash/unicode-injection-scanner.sh), [output-secrets-scanner](./examples/hooks/bash/output-secrets-scanner.sh)...
 
+**Skills** (1): [Claudeception](https://github.com/blader/Claudeception) — Meta-skill that auto-generates skills from session discoveries ⭐
+
 **Utility Scripts**: [session-search.sh](./examples/scripts/session-search.sh), [audit-scan.sh](./examples/scripts/audit-scan.sh)
 
 **GitHub Actions**: [claude-pr-auto-review.yml](./examples/github-actions/claude-pr-auto-review.yml), [claude-security-review.yml](./examples/github-actions/claude-security-review.yml), [claude-issue-triage.yml](./examples/github-actions/claude-issue-triage.yml)

guide/ultimate-guide.md

@@ -5093,6 +5093,49 @@ git clone https://github.com/antonbabenko/terraform-skill.git terraform
 
 If you create specialized skills for other domains (DevOps, data science, ML/AI, etc.), consider sharing them with the community through similar repositories or pull requests to existing collections.
 
+### Automatic Skill Generation: Claudeception
+
+**Repository**: [blader/Claudeception](https://github.com/blader/Claudeception)
+**Author**: Siqi Chen (@blader) | **Stars**: 1k+ | **License**: MIT
+
+Unlike traditional skill repositories, Claudeception is a **meta-skill** that generates new skills during Claude Code sessions. It addresses a fundamental limitation: *"Every time you use an AI coding agent, it starts from zero."*
+
+#### How It Works
+
+1. **Monitors** your Claude Code sessions via hook activation
+2. **Detects** non-obvious discoveries (debugging techniques, workarounds, project-specific patterns)
+3. **Writes** new skill files with Problem/Context/Solution/Verification structure
+4. **Retrieves** matching skills in future sessions when similar contexts arise
+
+#### Validated Use Case
+
+A user reported Claudeception auto-generated a `pre-merge-code-review` skill from their actual workflow—transforming an ad-hoc debugging session into a reusable, automatically-triggered skill.
+
+#### Installation
+
+```bash
+# User-level installation
+git clone https://github.com/blader/Claudeception.git ~/.claude/skills/claudeception
+
+# Project-level installation
+git clone https://github.com/blader/Claudeception.git .claude/skills/claudeception
+```
+
+See the [repository README](https://github.com/blader/Claudeception) for hook configuration.
+
+#### Considerations
+
+| Aspect | Recommendation |
+|--------|----------------|
+| **Governance** | Review generated skills periodically; archive or merge duplicates |
+| **Overhead** | Hook-based activation adds evaluation per prompt |
+| **Scope** | Start with non-critical projects to validate the workflow |
+| **Quality gates** | Claudeception only persists tested, discovery-driven knowledge |
+
+#### Why It's Notable
+
+This skill demonstrates the **skill-that-creates-skills** pattern—a meta-approach where Claude Code improves itself through session learning. Inspired by academic work on reusable skill libraries (Voyager, CASCADE, SEAgent, Reflexion).
+
 ### DevOps & SRE Guide
 
 For comprehensive DevOps/SRE workflows, see **[DevOps & SRE Guide](./devops-sre.md)**:

machine-readable/reference.yaml

@@ -102,6 +102,9 @@ deep_dive:
   design_patterns_skill_stacks: "React, Angular, NestJS, Vue, Express, RxJS, Redux, ORMs"
   community_skills_cybersec: 4947
   community_skills_iac: 5030
+  # Automatic skill generation (meta-skill)
+  claudeception: "https://github.com/blader/Claudeception"
+  claudeception_guide: 5095
   # DevOps/SRE Guide (guide/devops-sre.md)
   devops_sre_guide: "guide/devops-sre.md"
   devops_fire_framework: "guide/devops-sre.md:50"