Total Skills
17
Author Profile: CruxExperts
Skills published by CruxExperts with real stars/downloads and source-aware metadata.
Total Stars
51
Total Downloads
0
Skills Performance
Comparison chart based on real stars and downloads signals from source data.
ls-agentq-transport
3
Stars
3
Downloads
0
ls-communication-and-tools
3
Stars
3
Downloads
0
ls-context
3
Stars
3
Downloads
0
ls-cron-orchestrator
3
Stars
3
Downloads
0
ls-decision-tree-workflow
3
Stars
3
Downloads
0
ls-framework-audit
3
Stars
3
Downloads
0
ls-humanizer
3
Stars
3
Downloads
0
ls-kilo-boss-orchestrator
3
Stars
3
Downloads
0
Published Skills
ls-agentq-transport
Agent Q bidirectional transport client - file_drop ship/ingest, mail pull/ship (including strict gpg preencrypted), registry validation, queue-pending, archive-prune. Use when shipping or ingesting sealed PRD manifests between agents over shared folders or mail; when editing agent_trust_registry, manifest.schema.json, or agentq CLI.
Repository SourceNeeds Review
ls-communication-and-tools
Communication and response guidelines, tool selection and enhancement, periodic context updates. Use for user communication style, choosing tools, MCP/context updates.
Repository SourceNeeds Review
ls-context
Localsetup v3 framework context - overview, invariants, and skills index. Load first when working in a repo that uses Localsetup v3. Use when starting work in this repo or when user asks about framework rules.
Repository SourceNeeds Review
ls-cron-orchestrator
Manage cron from a repo-local manifest: time triggers, on-boot-with-delay, sequenced tasks; create, remove, reorder, install.
Repository SourceNeeds Review
ls-decision-tree-workflow
Decision tree / reverse prompt workflow - AI prompts user one question at a time with 4 options (A-D), preferred choice + rationale. Use only when the user explicitly asks for 'decision tree', 'run the decision tree', 'reverse prompt', or 'reverse prompt workflow'.
Repository SourceNeeds Review
ls-framework-audit
Run doc, link, skill matrix, and version/facts checks before release. Single entrypoint script; output to user-specified path only; no in-repo default. Use when user says 'run audit', 'run framework audit', or before release.
Repository SourceNeeds Review
ls-humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
Repository SourceNeeds Review
ls-kilo-boss-orchestrator
Orchestrate Kilo headless boss-worker execution with repo-local state, watchdog leases, consensus validation, and safety gates. Use when running multi-agent autonomous loops that require planning, delegation, verifier checks, and high/critical discrepancy adjudication.
Repository SourceNeeds Review
ls-linux-patcher
Create safe Linux server patching and Docker update plans. Use when the user asks to update, patch, or upgrade Linux servers, check maintenance readiness, plan package updates, plan Docker Compose refreshes, or coordinate multi-host maintenance. The bundled helper is plan-only; PatchMon API execution is unavailable until a tested Python client is added.
Repository SourceNeeds Review
ls-mail-protocol-control
Provide full SMTP and IMAP account control for delegated mailboxes with attachment-first MIME handling and full-envelope encryption. Use when an agent must read, send, organize, decrypt, and manage mailbox state with strict admin controls.
Repository SourceNeeds Review
ls-public-repo-identity
Public repo identity - use in README and published repos. For real identity details, use a local-only identity file that is not committed. Use when editing README*, CONTRIBUTING*.
Repository SourceNeeds Review
ls-scrapling
Host-first Scrapling integration skill: install or upgrade Scrapling via pipx, run single-URL extractions (simple and structured), and manage adapter and version refresh flows, with Docker as an optional escape hatch.
Repository SourceNeeds Review
ls-skill-normalizer
Normalize skills already in the tree using _localsetup/docs/SKILL_NORMALIZATION.md: documents first, tooling second, with user choice for platform-specific skills. Use when normalizing one or more skills in _localsetup/skills/ after import, copying, or batch review.
Repository SourceNeeds Review
ls-skill-sandbox-tester
Test skills in an isolated sandbox before production. Run after vetting and normalization (not right after import). Creates a unique temp sandbox when the skill needs read/write; runs smoke checks; on failure uses ls-debug-pro to iterate until fixed; no writes to repo until user approves. Use when validating a skill after it is framework-compliant, testing a skill end-to-end, or ensuring it runs correctly on all supported platforms.
Repository SourceNeeds Review
ls-skill-vetter
Security-first skill vetting for AI agent skills. Use before installing any skill from public registries (e.g. skill hubs, GitHub) or other sources. Checks for red flags, permission scope, and suspicious patterns.
Repository SourceNeeds Review
ls-task-skill-matcher
Match user tasks to installed Localsetup skills, recommend top matches, and run single-task or batch skill-selection flow with minimal interruption. Delegates complementary public-skill discovery to ls-skill-discovery.
Repository SourceNeeds Review
ls-tdd-guide
Test-driven development workflow with test generation, coverage analysis, and multi-framework support
Repository SourceNeeds Review