Tools & Automation

CLI tools, utilities, converters, workflow automation, and productivity helpers

skills in category: 45,575
pages available: 1,899

Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.

Open in full browser

Browse tools & automation skills

Showing 529–552 of 45,575 skills

OrchestrateAAutomated CLI-based parallel agent execution — spawn subagents via Gemini CLI, coordinate through MCP Memory, monitor progress, and run verificationtoolsVotes: 0GitHub stars: 46
DeepinitAProject harness initialization — Generate AGENTS.md, ARCHITECTURE.md, docs/ structuretoolsVotes: 0GitHub stars: 46
Ui DenseADense UI posture — maximum information density with clear hierarchy. Use when building or reworking admin dashboards, data tables and grids, ops or monitoring views, settings-heavy panels, debug inspectors, state or log viewers, and multi-pane tool UIs someone drives all day.toolsgoshellVotes: 0GitHub stars: 3
Surface Write TargetsARecipe for making an existing surface agent-writable via manifest writeTargets. Use when asked to 'let agents write/update/fill X on this page', 'add write targets', or 'wire apply_surface_write', or for an avalanche-campaign item. NOT for a brand-new surface (use surface-authoring).toolsrustgoVotes: 0GitHub stars: 3
Surface CheckATHE full UI surface checklist (S1–S18) run on one assigned surface. Use for a named surface check, `/surface-check <surface>`, or a claimed `surface-certification` Work Loop item. NOT for fleet selection or claims (use surface-certification-loop).toolstypescriptgoVotes: 0GitHub stars: 3
Surface AuthoringALifecycle for AI Matrx agent-aware UI surfaces. Use when creating a surface in features/surfaces/manifests/, or completing or repairing one that is partial, stubbed, unregistered, missing runtime context or context menus, or not agent-wired. NOT for certifying a surface (use surface-check).toolsgoshellVotes: 0GitHub stars: 3
Create Tool RendererACustom chat display for an MCP or agent tool's result, DB-loaded from tool_ui by default. Use when adding or customizing a tool visualization, making a tool result look good, rendering MCP tool output, or authoring a renderer for a tool that shows the generic view.toolsgoshellVotes: 0GitHub stars: 3
Context Menu V3AThe universal v3 right-click menu (EditableContextMenu / NonEditableContextMenu). Use when adding a right-click menu to a surface, fixing a fake menu with no Copy or Export, a missing Download as Markdown, or a bespoke per-surface menu. NOT for an assigned rollout shard (use context-menu-rollout).toolsgoshellVotes: 0GitHub stars: 3
Context Menu RolloutAFleet worker contract for wiring assigned files to the v3 right-click menu. Use when handed files from pnpm check:context-menu, or told to 'wire the menu on X', 'do your assigned rows', or 'clear your shard'. NOT for an unassigned one-off menu wiring (use context-menu-v3).toolsrustgoVotes: 0GitHub stars: 3
tmt-game-generatorAGenerate a complete, playable The Modding Tree (TMT) incremental/idle game from scratch — interview the user, write a data-driven design brief, scaffold from the bundled TMT template, generate mod.js and layer code, run static checks, do a balance walkthrough, and hand off test instructions. Use when the user asks to make, build, or generate an incremental game, idle game, clicker game, prestige tree, or modding-tree game from scratch, or explicitly mentions The Modding Tree / TMT.toolspythongoVotes: 0GitHub stars: 3
SecretsAUse a credential held in a charter vault — a database password, API token, kubeconfig, SSH key or server login — without its value entering the conversation. Use when a task needs a secret, when asked to store one, or before running any command that requires a credential.toolsrustgoVotes: 0GitHub stars: 6
PersonaAAdopt, create, or route work to a charter persona — a role with its own charter, memory and vault. Use when asked to act as a role, to switch or create a persona, or when deciding which persona a piece of work belongs to.toolsgoshellVotes: 0GitHub stars: 6
Windags DecomposerAFirst-party three-pass planning protocol that converts a ProblemUnderstanding into a revisioned decomposition proposal: typed nodes, reasoned edges, uncertainty records, candidate skills, and topological waves. A DAG is not an execution proof; confidence values are not probabilities without calibration. NOT for execution, runtime admission, or formal HTN proofs.toolsgonodeVotes: 0GitHub stars: 2
Task DecomposerATurn a stated outcome into a reviewable task graph with deliverables, decision/unknown nodes, typed dependency reasons, and authority gates. It plans work; it does not execute, schedule, or prove that a DAG can run concurrently. NOT for runtime orchestration or granting effect authority.toolsgonodeVotes: 0GitHub stars: 2
Rust Development WorkflowARun the ordinary Rust edit, compile, lint, and test loop; diagnose ownership and lifetime errors with intent and surrounding code; choose basic error and async test patterns. Use for day-to-day Rust changes in any crate. For library API invariants use advanced-rust-patterns; for structure selection use rust-data-structures-advanced; for measured optimization use rust-performance-and-idioms; for runtime failures use rust-debugging-mastery; for a pd-console pane or GPUI executor boundary use gp...toolstypescriptrustVotes: 0GitHub stars: 2
Research Prior ArtAFind and verify the closest prior work when a research result crosses disciplinary vocabularies. Use before a novelty claim, coined term, contribution paragraph, or related-work section. NOT for doing the proof or experiment, choosing a venue, formatting a submission, or general technical writing.toolsgoVotes: 0GitHub stars: 2
Latex Publication DesignADesign the typography and page grammar of a standalone LaTeX paper or whitepaper: type hierarchy, restrained color, callouts, figure consistency, and rendered-page review. Use when a PDF looks visually weak or a new paper needs a coherent visual system. NOT for the argument or proof, Book-specific edition styles, TikZ figure engineering, compilation, or a committed-PDF registry workflow.toolsgoVotes: 0GitHub stars: 2
Latex Build DiagnosticsACompile and troubleshoot a LaTeX document or project: select the available compiler, read the first log error, resolve references and citations, and verify rendered output. Use for build, render, install-status, or TeX log questions. NOT for source writing, Beamer composition, figure semantics, or a repository's committed-PDF registry and publication process.toolsgoshellVotes: 0GitHub stars: 2
Latex Beamer PresentationsAAuthor or revise Beamer slide decks, including frames, overlays, fragile content, aspect ratio, handout mode, and slide readability. Use for a .tex presentation. NOT for articles, books, whitepaper publication, generic compile failures, or standalone TikZ figures.toolsgoVotes: 0GitHub stars: 2
Dag Skill RegistryACentral catalog of available skills with metadata, capabilities, and performance history. Provides skill discovery and lookup services. Activate on 'skill registry', 'list skills', 'skill catalog', 'available skills', 'skill metadata'. NOT for matching skills to tasks (use dag-semantic-matcher) or ranking (use dag-capability-ranker).toolstypescriptrustVotes: 0GitHub stars: 2
Dag Scope EnforcerARuntime enforcement of file system boundaries and tool access restrictions. Blocks unauthorized operations and logs violations. Activate on 'enforce scope', 'access control', 'boundary enforcement', 'tool restrictions', 'runtime security'. NOT for validation (use dag-permission-validator) or isolation management (use dag-isolation-manager).toolsgodebuggingVotes: 0GitHub stars: 2
Dag RuntimeASpecifies bounded DAG execution contracts and evaluates executor receipts for dispatch, cancellation, joins, and effect reconciliation. Use when an implementation must bind a planned DAG to named runtime controls. NOT for claiming an executor is active, spawning agents, or certifying an effect from a plan.toolspythongoVotes: 0GitHub stars: 2
Dag Result AggregatorACombines and synthesizes outputs from parallel DAG branches. Handles merge strategies, conflict resolution, and result formatting. Activate on 'aggregate results', 'combine outputs', 'merge branches', 'synthesize results', 'fan-in'. NOT for execution (use dag-parallel-executor) or scheduling (use dag-task-scheduler).toolsjavascriptgoVotes: 0GitHub stars: 2
Dag Replay DebuggerADebugs recorded DAG lineage through historical inspection, deterministic decision replay when prerequisites hold, and clearly labeled counterfactual or live re-execution. Activate on "debug DAG", "replay execution", "inspect node state", "compare runs", or "execution diff". NOT for live monitoring (use dag-runtime + websocket-streaming), failure analysis (use dag-ops), or general code debugging.toolsgonodeVotes: 0GitHub stars: 2