aid
AI-Distiller wrapper for code analysis - refactoring, security, performance, architecture.
Skill by EndUser123
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/enduser123-aid
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/aid
What's inside
- Skill name
aid- Description
- AI-Distiller wrapper for code analysis - refactoring, security, performance, architecture.
- License
- MIT
- Instructions
- 100 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- capabilities-and-examples.md · references/
- integration-and-technical.md · references/
SKILL.md (first lines)
# AI-Distiller (aid) - Code Analysis Skill ## Purpose Interface to AI-Distiller (aid.exe) for intelligent code distillation — extracting essential structure while preserving semantic information for LLM consumption. Provides comprehensive code analysis including refactoring, security, performance, architecture, and documentation. ## Project Context ### Constitution / Constraints - **Solo-dev constraints apply** (CLAUDE.md) - **No enterprise patterns**: Recommend solo-appropriate solutions, not complex abstractions - **Truthfulness required**: Report findings accurately, don't sugarcoat technical debt - **Evidence-based analysis**: Specific file locations and line numbers, not speculation - **READ-BEFORE-WRITE**: Always explore existing code before recommending changes ### Technical Context - **Python wrapper**: `$__CSF_ROOT/src\commands\aid\aid.py` - **aid.exe location**: `$__CSF_ROOT/tools\ai-distiller-optimized\aid.exe` - **AI-Distiller Version**: v1.3.1 (built 2025-06-21) - **Output location**: `P://.aid/[ANALYSIS-TYPE].[timestamp].[filename].md` - **Supported languages**: Python, TypeScript, JavaScript, Go, Rust, Java, C#, Kotlin, C++, PHP, Ruby, Swift - **Compression ratio**: 60-90% size reduction while preserving semantic information ### Architecture Alignment - Uses structured subcommands (refactor, arch, security, perf, best, bugs, docs, diagrams, flow, multi, git) - Integrates with CSF NIP ecosystem (aid-status, aid-security, aid-performance, aid-diagrams) - Results saved with timestamps for traceability ## Your Workflow 1. **Identify analysis type** — Determine which subcommand fits user need (refactor, security, perf, arch, etc.) 2. **Set visibility level** — Use --private/--protected/--internal as appropriate 3. **Choose output format** --format md|text|jsonl|xml, and optionally --stdout 4. **Execute aid.exe** — Run via wrapper with appropriate arguments 5. **Locate results** — Check `P://.aid/` for timestamped output files 6. **Present findings** — Summarize key insights with file:line citations ## Validation Rules - **Before refactoring recommendations**: Verify analysis was actually run on current code - **Before security claims**: Ensure --private flag was used if needed - **Before architectural changes**: Verify findings with actual file reads - **Filter all recommendations**: Apply SoloDevConstitutionalFilter (no enterprise bloat) - **Report accurately**: Don't sugarcoat technical debt or severity ### Prohibited Actions - Sugarcoating technical debt severity - Recommending patterns without proven need or director approval - Ignoring security vulnerabilities - Making claims without reading actual files first ## When to Use Use `/aid` when you need to: - Analyze code for refactoring opportunities (technical debt, SOLID violations) - Generate architecture diagrams and visualizations - Perform security audits (OWASP Top 10 focus) - Identify performance bottlenecks - Create comprehensive documentation - Generate structured analysis workflows - Analyze git history with AI insights ## Quick Reference | Shortcut | Purpose | Example | |----------|---------|---------| | `refactor` | Refactoring analysis | `/aid refactor src/main.py` | | `arch` | Codebase architecture | `/aid arch . --format md` | | `security` | Security audit (OWASP) | `/aid security . --private` | | `perf` | Performance analysis | `/aid perf src/` | | `best` | Best practices review | `/aid best core.py` | | `bugs` | Bug hunting | `/aid bugs .` | | `docs` | Documentation | `/aid docs file.py` | | `diagrams` | Mermaid diagrams (10x) | `/aid diagrams src/` | | `flow` | Analysis workflow | `/aid flow . --stdout` | | `multi` | Multi-file docs | `/aid multi src/` | | `git` | Git history | `/aid git 50` | ## Advanced Options | Option | Purpose | |--------|---------| | `--format md|text|jsonl|xml` | Output format | | `--stdout` | Print to stdout (in addition to file) | | `--private/--protected/--internal` | Visibility control | | `--implementation` | Include function bodies | | `--include "*.py,*.ts"` | File patterns to include | | `--exclude "*test*"` | File patterns to exclude | ## Output Location Results saved to `P://.aid/[ANALYSIS-TYPE].[timestamp].[filename].md` ## Reference Files | File | Contents | |------|----------| | `references/capabilities-and-examples.md` | Key capabilities (refactoring, security, perf, arch, docs), git mode, use-case examples | | `references/integration-and-technical.md` | CSF NIP integration, technical details (version, languages, compression), constitutional notes |
From EndUser123/search-research, MIT.
More from EndUser123/search-research
- 0.479score
crawl
EndUser123
Ingest websites into QMD wiki collections for semantic search via /search and /explore.
SkillCFreshness: CClaude Code +9 - 0.479score
find
EndUser123
Local intelligent find — searches only local data stores (CKS, CHS, CDS, code, docs, skills).
SkillCFreshness: CClaude Code +9 - 0.476score
chs
EndUser123
Dedicated chat history search with summarization, workspace aliases, tool filtering, context preview, session stats, and branch filtering
SkillCFreshness: CClaude Code +9 - 0.476score
research
EndUser123
Canonical research workflow using deterministic capability routing, local and external evidence gathering, source opening, assessment, and provenance-bound…
SkillCFreshness: CClaude Code +9 - 0.475score
gitpack
EndUser123
Pack a code or markdown directory (or a scattered set of files) into compact LLM-context files using only stdlib — AST for Python, regex signatures for…
SkillCFreshness: CClaude Code +9 - 0.474score
note
EndUser123
Add a deliberate entry to your constitutional knowledge system (CKS).
SkillCFreshness: CClaude Code +9 - 0.474score
keep
EndUser123
Alias for /note — add a deliberate entry to your constitutional knowledge system (CKS).
SkillCFreshness: CClaude Code +9 - 0.473score
gitingest
EndUser123
Ingest GitHub repos into NotebookLM — clone, slice, and upload in one pipeline.
SkillCFreshness: CClaude Code +9 - 0.470score
export-session
EndUser123
Export the current (or specified) Claude Code session chain to a markdown file.
SkillCFreshness: CClaude Code +9 - 0.469score
web
EndUser123
Web research with multiple providers and intelligent result synthesis
SkillCFreshness: CClaude Code +9 - 0.469score
chs-eval
EndUser123
Run golden-case retrieval evaluation against the CHS database and report per-case + mean recall
SkillCFreshness: CClaude Code +9 - 0.469score
context7
EndUser123
Docs-as-Code: Fetch fresh, version-specific documentation via Context7 API.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 23, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/EndUser123/search-research
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from EndUser123
- 0.521score
evidence-driven-experiment-loop
EndUser123
Manage evidence-first experiments, benchmarks, performance optimization, A/B comparisons, repeated evidence gathering, live-run decisions, and fresh-agent…
SkillBFreshness: BClaude Code +9 - 0.516score
preflight
EndUser123
Build an evidence-backed inventory before planning, reviewing, or implementing non-trivial changes to hooks, skills, plugins, entrypoints, defaults, state…
SkillBFreshness: BClaude Code +9 - 0.490score
go
EndUser123
Use when a user asks to run /go, execute the next planned task, process a tasks.json queue, or drive a bounded SDLC task through enforced evidence gates.
SkillBFreshness: BClaude Code +9 - 0.479score
find
EndUser123
Local intelligent find — searches only local data stores (CKS, CHS, CDS, code, docs, skills).
SkillCFreshness: CClaude Code +9 - 0.479score
crawl
EndUser123
Ingest websites into QMD wiki collections for semantic search via /search and /explore.
SkillCFreshness: CClaude Code +9 - 0.476score
chs
EndUser123
Dedicated chat history search with summarization, workspace aliases, tool filtering, context preview, session stats, and branch filtering
SkillCFreshness: CClaude Code +9
Cite this page
aid skill. Agent Mart. https://agentmart.dev/skills/enduser123-aid (last updated 2026-10-24)