salverius-tech/introspection
home/dot_agents/adapters/claude/skills/introspection/SKILL.md
Meta-improvement patterns for analyzing interactions and improving rulesets. Triggers: /introspect, reviewing interactions, analyzing conversation patterns, improving CLAUDE.md, self-improvement, meta-learning.
tools
Updated May 17, 2026
$ install --global
skillsauthnpx skillsauth add salverius-tech/dotfiles introspectionInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 17, 2026, 4:49 AM145.1s1 file scanned
SKILL.md
- name:
- introspection
- description:
- Meta-improvement patterns for analyzing interactions and improving rulesets. Triggers: /introspect, reviewing interactions, analyzing conversation patterns, improving CLAUDE.md, self-improvement, meta-learning.
Auto-activate when: User mentions /introspect, reviewing interactions, analyzing conversation patterns, improving CLAUDE.md, self-improvement, or meta-learning.
Read ~/.agents/skills/introspection/knowledge.md for the full guidelines. Note: the path is ~/.agents, not ~/.claude.
Claude-Specific: Checkpoint Management
The /introspect --full command uses a checkpoint file to enable incremental analysis:
Location: .claude/INTROSPECTION_CHECKPOINT
Format:
YYYY-MM-DDTHH:MM:SSZ
Behavior:
- First run: Analyze all available history (up to 7 days)
- Subsequent runs: Only analyze new messages since checkpoint
- Updated after each
--fullanalysis completes - Not updated for current-session-only analysis
Claude-Specific: Target File Guidelines
| Content Type | Target File | Rationale |
|--------------|-------------|-----------|
| Project-wide rules | CLAUDE.md | Shared with team |
| Repo-specific knowledge | CLAUDE.local.md | Current project context |
| Personal preferences | ~/.claude/CLAUDE.md | Applies to all projects |
| Domain procedures | .claude/skills/[name]/SKILL.md | Conditional loading |
| Reusable workflows | .claude/commands/[name].md | User-invoked |
| Micro-procedures | CLAUDE.local.md Custom Agents | Quick inline reference |
| Session learnings | .session/feature/*/LESSONS.md | Feature-specific |
Claude-Specific: Command Integration
| Command | Relationship |
|---------|--------------|
| /optimize-ruleset | Focuses on ruleset structure; /introspect focuses on interaction patterns |
| /analyze-skills | Focuses on skill activation; /introspect can recommend new skills |
| /snapshot | Captures session state; /introspect analyzes for improvements |
| /commit | After introspection changes, use to commit updates |
Related Skills
salverius-tech/skill-creator
testing
VerifiedTrustedCommunity
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
SKILL.mdUpdated May 17, 2026
salverius-tech/ruleset-optimization
testing
VerifiedTrustedCommunity
Guidelines for optimizing Claude rulesets and instruction files (CLAUDE.md, settings.json) using context efficiency principles. Includes strategies for skill extraction, progressive disclosure, token savings calculation, and deduplication. Manually invoke when optimizing rulesets, reducing context size, extracting content to skills, or improving ruleset organization.
SKILL.mdUpdated May 17, 2026
salverius-tech/ptc-orchestration
tools
VerifiedTrustedCommunity
Activate when user needs multi-URL scraping, browser automation pipelines, or efficient tool orchestration to reduce API round-trips and context usage.
SKILL.mdUpdated May 17, 2026
salverius-tech/home/dot_claude/skills/hooks-cross-platform
development
VerifiedTrustedCommunity
# Cross-Platform Hooks and Status Scripts Guidelines for writing Claude Code hooks and status scripts that work on Windows (PowerShell, Git Bash), WSL, and Linux. ## Activation Activate when: - Creating or modifying files in `.claude/hooks/` - Creating or modifying `.claude/claude-status` - Writing shell scripts that will run in Claude Code context - Debugging hook execution failures ## Critical Rules ### 1. Shebang Lines **Bash scripts**: Always use `#!/usr/bin/env bash` (NOT `#!/bin/bash
SKILL.mdUpdated May 17, 2026