MCP App StoreMCP App Store
from wizards-of-the-ghosts96
Discover live services, background jobs, data stores, and hidden dependencies in an environment and return a prioritized map with confidence notes.
Locate Animals or Plants is a discovery skill that surveys an environment to find active services, scheduled jobs, data stores, queues, and dependency roots. It traces relationships between discovered components and returns a live-system map, a shortlist of likely roots and chokepoints, and a confidence note about stale or unobservable entries.
A metaphorically-named skill for service/dependency discovery that provides only vague, high-level instructions with no scripts, no concrete commands, and no implementation. The SKILL.md reads more like a creative writing exercise than a functional skill — agents would naturally discover services without it. No security concerns since there's nothing executable.
Essentially a creative prompt wrapper around service discovery. No scripts, no references, no actionable steps. The skill spec compliance is minimal — frontmatter exists but the body is too thin to be practically useful.
Symbol — Policy Tagging / Semantic Marker
Define and apply named policy 'symbols' (machine-readable tags) that trigger enforcement actions like audit logging, throttling or compliance gates when conditi
Arcana (Technical Mechanism Analysis)
Explain how systems, protocols, or architectures actually work under the hood and surface non-obvious implications and failure modes.
History — Temporal Investigation
Performs structured reconstruction of how a system, decision, or codebase arrived at its current state: timelines, key decision points, and contextual analysis
Hypnotic Pattern
Design short-lived attention-capture patterns (progress indicators, micro-rewards, visual anchors) to hold focus during bounded flows without creating addictive
Fear (Pre-mortem & Risk Amplifier)
Structured pre-mortem generator that amplifies plausible worst-case scenarios, ranks failure modes, and produces concrete mitigation recommendations.
Greater Invisibility
Plan and execute live changes with minimal user-visible noise using feature flags, shadow writes, progressive rollout, and operator-visible signals.
Power Word Kill
Emergency containment skill: guidance and guarded procedure for immediate hard termination of processes, services, or accounts when graceful options are unavail
Disguise Self
Adapt voice, tone, and presentation of existing content for a target audience without changing facts or meaning.
Zone of Truth
Activate a high-integrity conversation mode where claims must be sourced, uncertainty is labeled, and speculation is explicitly flagged.
Stinking Cloud (Area Denial)
Implement defensive area-denial mechanisms like rate limiting, tarpits, and honeypots to deter unwanted traffic.
NGINX Integration
Integrate with NGINX via the Membrane CLI to query, manage, and proxy requests to NGINX for configuration, logs, and runtime operations.
Starlark Dev
Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.
Sync Production Database to Development
Run a safe, scripted workflow to download production database dumps and restore them into a development environment (download-only and restore options).
Sandbox0 Integration
Guidance and templates for integrating Sandbox0 sandboxing into AI agents — CLI/SDK patterns, templates, volumes, network policy, and deployment choices.
Alpha Forge Pre-Ship Quality Gates
Pre-merge quality gates for PRs that validate RNG determinism, forked URLs, runtime parameter ranges, and manifest synchronization to reduce review cycles.
Canary — Post-Deploy Visual Monitor
Run a short post-deploy monitor that captures screenshots, checks console errors, and compares performance against baselines to detect regressions and page fail
Skill Issue — Skill Auditor
Scan and audit installed agent skills to produce a health report covering inventory, usage, dependency checks, version status, and actionable recommendations.
Evolve — Goal-Driven Improvement Loop
Autonomous improvement loop that selects high-value work, runs a full research-plan-implement (/rpi) cycle, validates changes, and repeats to compound repo impr