MCP App StoreMCP App Store
from anti-distill2,015
Cleans and anonymizes employee SKILL.md files by removing sensitive, tacit, and proprietary details while preserving structure for safe submission.
This skill automates 'anti-distillation' — it scans SKILL.md or related colleague-skill documents and removes or generalizes core tacit knowledge (pitfalls, judgement calls, internal contacts) so the resulting file looks complete but omits sensitive proprietary details. It supports English and Chinese, provides previewed classifications (SAFE/DILUTE/REMOVE/MASK), and outputs both a cleaned submission-ready skill and a private backup containing the original sensitive material.
Use when you must submit skill documentation to an external reviewer or public repo but need to keep internal knowledge private. Also helpful before sharing colleague-authored skills, preparing handoffs, or creating sanitized public demos.
Best used with agents that support file Read/Write/Edit and shell operations — Claude Code, similar multi-tool agents, and assistants with file access.
Anti-distill is a skill for cleaning/anonymizing employee SKILL.md files by removing sensitive, tacit, and proprietary knowledge while preserving structure. It's a pure-prompt skill with no executable scripts — everything is driven by detailed instructions in the SKILL.md. The documentation is extensive and well-structured with clear steps, classification rubrics, and validation rules. However, it references external prompt files (classifier.md, diluter_work.md, diluter_persona.md, diluter_general.md) via ${CLAUDE_SKILL_DIR}/prompts/ that are not bundled, meaning the skill won't work fully without those files. The skill's purpose is niche — helping employees sanitize internal knowledge docs before sharing — which is a specific use case with limited broad appeal. No security issues detected: no shell commands, no network calls, no credential handling, and it explicitly avoids destructive operations (suggests backups before overwrites).
Interesting concept — 'anti-distillation' to protect tacit knowledge from being extracted. The skill is well-documented with clear workflows, validation steps, and edge case handling. However, the missing prompt files are a significant gap: the skill instructs the agent to 'refer to' external files that aren't included, so the classification and dilution logic can't actually be followed as written. Security is strong — no commands, no network access, no data exfiltration. Usefulness is limited to a niche audience (employees forced to share skill files who want to sanitize them), and the concept itself raises ethical questions about intent, though the skill itself is just a text-processing tool.
Reverse Engineer
Provides step-by-step guidance and best practices for binary reverse engineering: static analysis, dynamic tracing, disassembly, and documentation workflows for
Sandbox0 Integration
Guidance and templates for integrating Sandbox0 sandboxing into AI agents — CLI/SDK patterns, templates, volumes, network policy, and deployment choices.
Chinese Software Copyright Application
Generate complete Chinese software copyright application materials (application form, code documentation, user manual, design docs) and export them to PDF from
CTF Write-up Generator
Generate a concise, reproducible submission-style CTF writeup with a one-path solution script, metadata, and a short checklist for fast verification.
GRC & Compliance (ServiceNow)
Guides Governance, Risk & Compliance (GRC) work in ServiceNow: policies, controls, risk records, audits and ES5 script examples for automating GRC workflows.
Verifying Markdown Formatting
Checks Markdown files for structural and stylistic formatting issues (headings, lists, code blocks, links) and applies deterministic fixes.
Code Spec Backfill
Identify missing function-level contracts and backfill docstrings and type annotations; report ambiguous gaps with misuse scenarios. Incremental, state-driven w
Azure External Attack Surface Management
Provides expert guidance for Azure External Attack Surface Management (EASM): quotas, configuration, integrations, and exporting inventory to analytics platform