Claude Skills by gaelic-ghost

Configure, run, secure, and troubleshoot Hermes Agent messaging gateways, platform adapters, webhooks, API server, long-lived profiles, and remote deployments across built-in and custom channels.

Install, update, migrate to, configure, run, secure, and troubleshoot Hermes Agent across its CLI, TUI, desktop, dashboard, profiles, tools, skills, memory, models, goals, voice, sessions, worktrees, and terminal backends.

Configure and troubleshoot Zed Agent, ACP External Agents, and Terminal Threads. Use for Zed Skills, MCP, profiles, permissions, registry installs, custom agents, and ACP logs.

Coordinate bounded worker tasks with a launch envelope, report-back, escalation, and synthesis contract. Use before spawning, resuming, steering, cancelling, or closing subagents.

Observe suspicious content in a disposable environment. Use when execution, process ancestry, file changes, persistence, network behavior, payloads, or user interaction need measurement after static analysis with isolation and teardown.

Analyze a suspicious artifact without executing it. Use for binaries, apps, packages, archives, scripts, libraries, extensions, firmware, or payloads when metadata, signatures, imports, strings, resources, and obfuscation need inspection.

Prepare a verified disposable Linux or macOS analysis lab from an approved isolation decision. Use before active research to control host integration, networking, baseline, monitoring, evidence export, reset, and teardown.

Prepare language-model training, preference, red-team, or evaluation datasets. Use when collecting, filtering, deduplicating, templating, splitting, or auditing examples for provenance, leakage, consent, or sensitive data.

Preserve security evidence before analysis, containment, or remediation changes it. Use for artifacts, volatile host state, vulnerability validation, records, logs, screenshots, commands, hashes, timelines, and reproducible handoffs.

Build an Apple Push to Talk channel experience with system controls, ephemeral PTT pushes, audio-session ownership, and an app-owned communication backend.

Set up, run, and improve Python tests in uv projects and workspaces. Use for pytest configuration, focused and package-targeted runs, fixtures, parametrization, async and integration tests, coverage, CI parity, or failure triage.

Recover from an incident by eradicating compromise and restoring service. Use when hosts, identities, applications, cloud resources, network controls, or data need rebuild, patching, rotation, repair, validation, and return to service.

Write a security assessment or penetration-test report from evidence. Use when findings, scope, methodology, limitations, impact, remediation, retest criteria, and an executive explanation need calibrated reporting.

Route repository work to focused Git, GitHub, documentation, worktree, settings, or release workflows. Use first when a request spans several repository operations or the correct owner is unclear.

Research one macOS security control on an exact build, separating public contracts, private evidence, and hypotheses. Use for TCC, sandbox, entitlements, Gatekeeper, XProtect, Hardened Runtime, SIP, or system-policy changes.

Design causal research into model activations, features, attention, residual streams, probes, and circuits. Use when locating behavior, testing a direction or feature, comparing layers, or reproducing interpretability research.

Route an ambiguous cybersecurity request before tools run. Use for suspicious files, links, messages, host behavior, malware, vulnerability reports, authorized pentests, incidents, threat hunting, detection work, or security advice.

Inspect a scoped live site in Safari through Safari Technology Preview's local MCP server. Use for Safari-specific DOM, console, network, screenshot, accessibility, performance, interaction, responsive, or print-media evidence.

Define authorization, targets, rules, safety controls, and stop conditions before active security testing. Use for penetration tests, scans, exploit validation, web or API tests, network probing, bug bounty, or agent-driven testing.

Automate repeatable Hopper analysis with its installed Python SDK or extension APIs. Use for deterministic queries, controlled annotations, structured exports, or a scriptable document operation with a checkpointed evidence trail.

Select isolation before inspecting or executing untrusted content. Use for local analysis, a container, Linux or macOS VM, remote sandbox, or spare device with defined network, mounts, credentials, snapshots, evidence export, and teardown.

Plan, build, and validate Slack workspace apps with OAuth, Events API, interactivity, slash commands, modals, and Socket Mode.

Plan, build, and validate consent-aware SMS, MMS, and RCS business messaging agents, including sender setup, webhooks, rich content, delivery, and fallback.

Add, review, or migrate AWS integrations in server-side Swift using Soto as the standard SDK, with one shared AWSClient per application or Lambda environment and explicit single-owner shutdown.

Configure or diagnose SourceKit-LSP across SwiftPM, compilation databases, and build servers. Use for completion, navigation, refactoring, diagnostics, semantic tokens, indexing, generated files, or editor-client failures.

Implement and evaluate activation steering, representation engineering, logit changes, or weight-space interventions. Use when changing model behavior without ordinary fine-tuning or sweeping layer, strength, and persistence choices.

Inspect Swift toolchain selection, driver jobs, diagnostics, AST, SIL, LLVM IR, dependencies, modules, and interfaces. Use for compiler behavior, lowering, build-job, or emitted-artifact investigations.

Plan and validate SwiftPM build or command plugins, macros, package traits, generated sources, permissions, and Xcode handoffs. Use for Package.swift extension work or Swiftly/Xcode capability differences.

Query Swift types, USRs, documentation, occurrences, references, and relationships with SourceKit, SourceKitten, index stores, and IndexStoreDB. Use for file-local semantics or project-wide symbol questions.

Parse, inspect, generate, or transform source with SwiftParser and SwiftSyntax while preserving fidelity. Use for Swift codemods, structural linting, generators, syntax-aware edits, or macro trees without inferred types.

Plan, build, and validate Microsoft Teams bots and agents with Teams SDK or Microsoft 365 Agents SDK, Microsoft Entra, Adaptive Cards, and tenant deployment boundaries.

Plan, build, and validate Telegram Bot API integrations, webhooks or polling, inline interactions, and Mini Apps.

Test authorized network services with bounded discovery and protocol-aware validation. Use for hosts, ranges, ports, TLS, banners, versions, authentication, exposure, segmentation, configuration, packet evidence, or vulnerability checks.

Test an authorized web application or API using OWASP guidance. Use for authentication, authorization, sessions, input, schemas, business logic, file handling, server-side requests, configuration, transport, errors, and data exposure.

Triage a suspected incident across endpoints, identities, applications, cloud resources, networks, or data. Use when an alert, compromise, disruption, unauthorized access, malware, credential concern, or exposure needs scope and ownership.

Safely classify suspicious files, archives, installers, packages, scripts, documents, profiles, browser extensions, URLs, QR codes, messages, and nested payloads before execution. Use when someone needs the smallest safe next analysis step.

Triage a vulnerability report, scanner result, advisory, CVE, PoC, bug bounty, ticket, or researcher note. Use when affected versions, credibility, prerequisites, evidence, applicability, validation, and exposure must be established.

Guide remote-first tvOS SwiftUI and UIKit decisions: focus navigation, Large Text, Apple TV capability gates, and TVMLKit migration. Use for Apple TV interaction, focus geometry, accessibility, or platform-boundary questions.

Guide tvOS media playback: AVKit-first player choice, custom escalation, remote commands, Now Playing, and validation. Use for AVPlayerViewController, MPRemoteCommandCenter, playback focus, or media-control boundaries.

Create Ghidra projects for compiled artifacts. Use for import, loader and analyzer choices, listings, functions, symbols, types, references, graphs, decompiler review, scripts, headless analysis, PyGhidra, comparisons, and archives.

Use Hopper on macOS for disassembly, graphs, pseudocode, Objective-C and Swift presentation, procedure and type edits, extensions, and debugging. Use for document setup, navigation, annotation, evidence, comparison, and discovery.

Use and troubleshoot Nous Research services with Hermes Agent, including Nous Portal inference, Tool Gateway backends, Nous Chat, subscription proxy, and Hermes Cloud hosted deployment.

Use installed Objective-See macOS security tools as evidence adapters. Use for KnockKnock, BlockBlock, LuLu, ProcessMonitor, FileMonitor, WhatsYourSign, TaskExplorer, or related tools with explicit permissions, limits, and ownership.

Validate a vulnerability claim in an authorized environment. Use for scanner candidates, advisories, CVEs, PoCs, source concerns, configuration weaknesses, or regressions with a safe proof and controls.

Build and diagnose custom macOS and Linux VM hosts with Apple's Virtualization framework. Use for platform and boot configuration, devices, VM bundles, lifecycle, save and restore, UI, entitlements, and framework errors.

Build a native Apple VoIP calling app by separating CallKit or LiveCommunicationKit, PushKit, AVFAudio, SIP or WebRTC transport, and call-state ownership.

Design and repair secure inbound events, webhooks, interactions, retries, acknowledgements, and delivery observability for messaging and collaboration platforms.

Plan and validate official WhatsApp Business messaging integrations, including onboarding, webhooks, conversation policy, templates, consent, and provider boundaries.