All authors
gaelic-ghost avatar

Claude Skills by gaelic-ghost

github.com/gaelic-ghost
398 skillsA× 396F× 20 installs151 views
Choose Macos Virtualization ShapeA

Choose the smallest macOS-hosted boundary for development, compatibility, or authorized security research. Use when deciding among the host, containers, container machine, full Linux or macOS VMs, remote systems, or physical Macs.

ai-agentsrustswift
0
7
Choose Model Lab WorkflowA

Route language-model training, data, evaluation, checkpoint, representation, steering, ablation, jailbreak, tool-calling, Apple-runtime, and benchmark requests. Use when the primary workflow or Socket owner is unclear.

ai-agentspythonswift
0
7
Choose Platform IntegrationA

Choose a supported chat, calling, business-messaging, or collaboration integration before implementation. Use for Discord, Telegram, Slack, Teams, WhatsApp Business, SMS/MMS/RCS, Google Meet, iMessage collaboration, and Apple VoIP.

ai-agentsgoapi
0
7
Choose Swift Language ToolingA

Choose SwiftSyntax, compiler, SourceKit, SourceKitten, IndexStoreDB, or SourceKit-LSP by information and project model. Use before Swift tooling work when Swiftly and Xcode may resolve different binaries.

ai-agentsgoswift
0
7
Cloud Deployment Routing WorkflowA

Choose a cloud deployment path before implementation. Route AWS work to the official AWS Agent Toolkit and Azure work to Microsoft's Azure Skills plugin while keeping credentials, regions, and mutation boundaries explicit.

ai-agentsgoswift
0
7
Communication Notifications WorkflowA

Implement Apple communication and Time Sensitive notifications with intent donation, Focus behavior, and a bounded Notification Service Extension processing path.

ai-agentsgodocumentation
0
7
Compare Model CheckpointsA

Compare base, adapter, merged, quantized, converted, or intervention-derived checkpoints. Use when selecting an artifact, investigating regression, verifying packaging, or balancing quality, safety, size, and runtime.

ai-agentsrails
0
7
Connect Hopper McpA

Connect an installed Hopper MCP server safely from Codex or Hermes for document navigation, assembly, pseudocode, strings, procedures, and cross-references with a private profile, read-only allowlist, approvals, and data boundaries.

ai-agentspythongo
0
7
Contain And Recover MacosA

Contain a macOS threat and verify recovery. Use for isolation, process or service containment, credential response, persistence removal, quarantine, restore, erase/reinstall, monitoring, and return-to-service decisions.

ai-agentsrustgo
0
7
Contain Security IncidentA

Contain an active or credible incident across hosts, identities, applications, cloud resources, networks, or data. Use when access, execution, exfiltration, fraud, destruction, or repeated compromise needs authorized interruption.

ai-agentssecurity
0
7
Conversation State Human HandoffA

Plan conversation identity, state, consent, escalation, transcript, and human-handoff behavior for bots and business messaging agents.

ai-agents
0
7
Coordinate External AgentsA

Coordinate independently operated external agents through durable handoffs. Use when work crosses hosts, sessions, accounts, services, queues, boards, pull requests, or human-owned task systems and cannot rely on an in-run subagent result.

ai-agentsapi
0
7
Coordinate Worktrees And ThreadsA

Assign worktree, branch, write, validation, integration, and cleanup ownership before parallel repository work. Use when a worker will inspect or modify repository state outside the coordinator's worktree.

ai-agentsgit
0
7
Default Communication App WorkflowA

Plan iOS and iPadOS default messaging, calling, dialer, and carrier messaging app roles while separating documented system integrations from an app-owned macOS companion implementation.

ai-agentsgodocumentation
0
7
Design Model ExperimentA

Design a reproducible model experiment with hypotheses, controls, baselines, metrics, budgets, provenance, artifacts, and stop conditions. Use before model work whose results must support a decision.

ai-agentsbash
0
7
Design N8n Agent WorkflowA

Design safe n8n workflows with deterministic routing, credentials, idempotency, recovery, local-model checks, drafts, and exact approval gates.

ai-agentsnoderails
0
7
Diagnose Apple EntitlementsA

Trace Apple entitlements across project source, account/profile authorization, final signed main or nested code, and runtime policy or consent. Use for missing or rejected entitlements, export-only failures, helpers, and re-signing.

ai-agentsswiftapi
0
7
Discord App WorkflowA

Plan, build, and validate Discord apps, bots, commands, interactions, Gateway event handling, and Activities using current Discord documentation.

ai-agentsdocumentation
0
7
Dockerized Service Release Deployment WorkflowA

Create a Dockerized-service release contract with clean GitHub Actions builds, main-anchored tags, immutable digest manifests, published-release deployments, production approval, health checks, and exact-digest rollback.

ai-agentsrustgo
0
7
Evaluate Jailbreak ResilienceA

Evaluate authorized jailbreak and prompt-injection resilience with reproducible attacks, budgets, graders, and side-effect boundaries. Use for controlled checkpoints, local harnesses, or explicitly authorized systems.

ai-agents
0
7
Evaluate Language ModelA

Design repeatable language-model capability, quality, behavior, regression, or safety evaluations. Use when creating cases and graders, comparing a treatment with a baseline, or deciding whether a checkpoint passes.

ai-agentsgogit
0
7
Evaluate Tool Calling ModelA

Evaluate tool selection, arguments, schemas, execution, observation use, recovery, and side effects. Use when comparing tool-capable checkpoints, prompts, parsers, agent loops, function schemas, or harnesses.

ai-agents
0
7
File Provider And Finder Sync WorkflowA

Choose File Provider for Apple remote-storage synchronization or scoped macOS Finder Sync UI. Use when a feature needs cloud-backed files or Finder decoration without confusing Finder Sync with a sync engine.

ai-agentsgoswift
0
7
Fine Tune Language ModelA

Plan supervised fine-tuning, LoRA, QLoRA, or full-parameter training with reproducible evaluation gates. Use when adapting a checkpoint or choosing precision, adapters, optimization, checkpointing, or resume behavior.

ai-agentsrailsapi
0
7
Git WorkflowA

Safely inspect and perform everyday Git work: branches, focused commits, history, integration, conflicts, worktrees, and recovery. Use for local version-control tasks that are not GitHub settings or release publication.

ai-agentsgitsecurity
0
7
Github Collaboration WorkflowA

Prepare and maintain GitHub pull requests, reviews, issues, CI triage, and durable handoffs. Use for collaboration work after local Git changes exist; not for GitHub settings or release publication.

ai-agentsgoshell
0
7
Google Meet Collaboration WorkflowA

Plan and validate Google Meet add-ons, conference REST integrations, event subscriptions, artifacts, and preview media API work.

ai-agentsgoapi
0
7
Harden MacosA

Review and improve macOS defensive posture. Use for updates, XProtect and Gatekeeper, FileVault, firewall, remote access, accounts, background items, privacy, backups, credentials, and monitoring after a security assessment or incident.

ai-agentstestingapi
0
7
Hermes Agent CompatibilityA

Audit Socket-to-Hermes compatibility across Agent Skills, Codex plugins, MCP, hooks, apps, agents, and Hermes extension systems. Use for skill exports, config translations, and Hermes adapter decisions.

ai-agentspythongo
0
7
Hunt Security IndicatorsA

Hunt scoped systems and telemetry for supplied indicators or behaviors. Use for hashes, paths, domains, addresses, accounts, processes, persistence, ATT&CK behaviors, cloud events, or incident expansion with explicit scope and validation.

ai-agentssecurity
0
7
Imessage App And Collaboration WorkflowA

Build an iMessage app or collaboration feature with Messages extensions, interactive message sessions, and Shared with You without implying server-side access to personal conversations.

ai-agentsgobackend
0
7
Inspect Macos PersistenceA

Inspect macOS persistence and recurring execution without deleting evidence. Use for login items, launch agents or daemons, extensions, profiles, shell startup files, scheduled tasks, browser extensions, helpers, and startup behavior.

ai-agentsshell
0
7
Inspect Macos Runtime ActivityA

Correlate suspicious macOS process, file, network, permission, and log activity. Use for unexpected processes, downloads, open files, DNS, privacy prompts, alerts, file mutations, injected executables, and Endpoint Security evidence.

ai-agentssecurity
0
7
Leaf Rendered Web WorkflowA

Plan, implement, test, and diagnose Leaf-rendered Vapor sites and HTML email with typed contexts, layouts, partials, custom tags, escaping, accessibility, assets, caching, and rendering tests.

developmentjavascriptrust
0
7
Linux Development Vm WorkflowA

Prepare and reset persistent Linux development guests on macOS. Use when comparing container machine, Lima or Colima, and full VMs for distros, init systems, services, custom boot, disks, Rosetta, or nested virtualization.

ai-agentsrustswift
0
7
Macos Development Vm WorkflowA

Prepare and reset clean macOS development guests on Apple silicon. Use for restore-image compatibility, VM identity, installation, resources, OS-version testing, signing, privacy, and disposable macOS research guests.

ai-agentsrusttesting
0
7
Macos Privacy Permissions WorkflowA

Diagnose macOS privacy permissions from the operation and responsible executable. Use for Accessibility, Automation, Developer Tools, recording or input, protected data, Full Disk Access, PPPC, prompts, Settings, resets, and helpers.

ai-agentsgoswift
0
7
Macos Sandbox File Access WorkflowA

Design and diagnose macOS file access. Use for App Sandbox, App Groups, user selection, security-scoped bookmarks across relaunches, helpers or extensions, stale access, TCC overlap, POSIX or ACL, Data Vault, and SIP denials.

ai-agentssecuritydocumentation
0
7
Mailkit WorkflowA

Design macOS MailKit extensions for content blocking, message actions, compose sessions, and message security with explicit privacy, capability, target, and validation boundaries. Use when a macOS app needs to extend Apple Mail.

ai-agentsrustgo
0
7
Maintain Agent PluginsA

Create or align agent plugin repositories, install deterministic managed FSX plugin maintenance, and validate or apply the whole plugin set through exactly two aggregate Just commands.

ai-agentspythongo
0
7
Maintain Github RepositoryA

Audit or align a GitHub repository's server-side settings, rulesets, security automation, Dependabot, and sign-off policy. Use for server-side GitHub policy work, not ordinary local Git commits, PR collaboration, or releases.

ai-agentsgitapi
0
7
Maintain Project AgentsA

Maintain AGENTS.md as the agent-policy member of the canonical four-document repository suite.

ai-agentsrailsdocumentation
0
7
Maintain Project ContributingA

Maintain CONTRIBUTING.md as the contributor-facing member of the canonical four-document repository suite.

ai-agentsrailsdocumentation
0
7
Maintain Project ReadmeA

Maintain README.md as the product-facing member of the canonical four-document repository suite.

ai-agentsrailsdocumentation
0
7
Maintain Project RepoA

Install or refresh deterministic FSX repository maintenance, maintain all four canonical project documents, validate and synchronize repository assets, and operate protected-main releases.

ai-agentspythonshell
0
7
Maintain Project RoadmapA

Maintain ROADMAP.md as the planning member of the canonical four-document repository suite.

ai-agentsrailsgit
0
7
Map Malware BehaviorA

Map observed malicious behavior to MITRE ATT&CK techniques. Use when analysis, telemetry, incident evidence, or a report needs a behavior map for detection, response, or communication without inferring an actor or campaign.

ai-agents
0
7
Operate A2a Agent IntegrationA

Connect, expose, validate, and troubleshoot Agent2Agent (A2A) peers. Use for Agent Cards, peer authentication, message and task lifecycles, streaming, push notifications, or Hermes A2A across process, machine, or framework boundaries.

ai-agentsrustgo
0
7
Operate Acp Agent IntegrationA

Install, launch, validate, and diagnose existing ACP agents across Zed, Xcode, and other clients. Use for registry discovery, custom launch commands, auth, capabilities, sessions, and logs.

ai-agentsgoapi
0
7
Operate Agentic Security ToolsA

Operate security tools through an AI agent with explicit authority boundaries. Use when an agent may invoke CLIs, GUI apps, browser automation, MCP servers, scanners, sandboxes, or containment actions with constrained approvals and logging.

ai-agentsrustrails
0
7