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 505–528 of 45,575 skills

Review EndstateAUse when the user asks to review changes, review a diff, sanity-check a PR before merge, or verify uncommitted work against Endstate's locked contracts and principles. Trigger phrases include "review my changes", "review the diff", "sanity check this branch", "check against contracts", "review before PR". Repo-scoped to the Endstate engine.toolsgogitVotes: 0GitHub stars: 108
ShortcutsAManage and interact with macOS Shortcuts. Use this skill when the user wants to list available shortcuts, view a shortcut in the Shortcuts app, or run a shortcut. Supports running shortcuts with or without input parameters.toolsbashapiVotes: 0GitHub stars: 3
Agent HandsAHuman-rate mouse and keyboard for a real Chromium browser, including one you launched or attached to yourself. Use when acting on a site where the user is logged in with real credentials AND automated-looking input could get that account banned or rate-limited — banking, mail, ad platforms, SEO tools, marketplaces, social, CRM, hosting dashboards. Also use whenever the browser is not one agent-browser started, because agent-browser cannot attach to it at all. Triggers include "log into", "my ...toolsgobashVotes: 0GitHub stars: 2
CoreACore agent-hands usage guide. Read before running any agent-hands command.toolspythonrustVotes: 0GitHub stars: 2
User TestingATesting AudioBash from the perspective of non-technical users, with focus on Electron, terminal emulation, and audio recording edge cases. ---toolspythongoVotes: 0GitHub stars: 6
.ClaudeAThis documents the complete process for releasing a new version of AudioBash for both Windows and macOS.toolsbashnodeVotes: 0GitHub stars: 6
ApplyAApply to the queued jobs. Use when the user says /apply, "start applying", "run the applier", or asks to submit applications from the queue. Fills each form in the runner's own Chrome window with JEV, page by page, hands what is left to Claude, verifies, and submits only forms that are ready.toolsgobashVotes: 0GitHub stars: 5
Adversarial ReviewAFast two-pass adversarial code review. A Code Adversary subagent red-teams a diff or PR to find the concrete bug, then a separate Findings Adversary subagent with a clean context tries to refute every finding to cut false positives. Use for routine changes where a full staff review is overkill, or as the review gate inside ship-it.toolsbashcode-reviewVotes: 0GitHub stars: 5
Add CommandAThis skill should be used when the user asks to "add a CLI command", "create a subcommand", "add a new command", or mentions "new CLI command", "new subcommand", or "command-line tool". Provides scaffolding guidance for implementing a new CLI subcommand with argument parsing, validation, and tests.toolsgoapiVotes: 0GitHub stars: 11
Altairsim MbasicARules for Microsoft MBASIC (BASIC-80 5.21) under CP/M on an altairsim machine — how to type or paste a BASIC program so that no line is lost, when to wait for `Ok`, how to leave the line editor after a `Syntax error`, and how to load, save and stop a program. Use this whenever a task types at the MBASIC `Ok` prompt, enters or runs a `.BAS` program, or a typed BASIC line arrives changed (a lost first digit, two lines joined into one).toolsgogitVotes: 0GitHub stars: 2
Altairsim HostbridgeARules for the altairsim host bridge utilities `R`, `W` and `HDIR`, which copy files between the host folder and a CP/M disk in a running altairsim machine. Use this whenever a task moves a file into or out of a CP/M guest — a source file to assemble, a `.COM` or `.HEX` to bring back, a `.BAS` program — when `R` or `W` gives an error, when a disk does not have the utilities, and before you use a host tool such as cpmtools on a disk image.toolsVotes: 0GitHub stars: 2
Altairsim Cpm TextARules for a text file that a CP/M program will read on an altairsim machine — CR/LF line ends, the 8.3 name, and the Ctrl-Z that ends the file. Use this whenever you create or edit a file on the host that goes into CP/M (an `.ASM` or `.MAC` source, a `.BAS` program, a `.SUB` or `.TXT` file), whenever you bring a text file back from CP/M, and when an assembly makes nothing or a BASIC program arrives as one line.toolsgoVotes: 0GitHub stars: 2
HandsfreeAKeep the current agent moving on an already-authorized task while CI, tests, reviews, or other asynchronous work finishes. Arm a native same-conversation wake every 10 minutes for at most 3 hours, check live evidence, advance the nearest milestone, and cancel the wake when work ends. Use for "handsfree", "watch this run and continue", or "keep checking CI without my nudges".toolsgoshellVotes: 0GitHub stars: 5
Ogp Separating Quantum Inspired OptimizationAUse when OGP separates classical heuristics from QAOA depth barriers.toolsgoVotes: 0GitHub stars: 3
Mts Slds Multi Timescale SwitchingAUse when inferring regime-specific neural timescales from population recordings. MTS-SLDS method.toolsgoVotes: 0GitHub stars: 3
Precision Gated Mbrl ExcavatorAPrecision-gated model-based RL for real robots - probabilistic dynamics ensemble learned from scratch on hardware with sampling-based MPC, progress reward conditioned on path accuracy (precision gates speed). Use for sample-efficient learning on heavy machinery, precision tracking under actuation dynamics, or direct-on-hardware RL without demonstrations.toolsgoVotes: 0GitHub stars: 3
Arxiv 2610 01161 My Fault Self Diagnosis As Credit AssignmentAResearch paper: My FAULT: Self-Diagnosis as Credit Assignment in Self-Evolving Agentic Reinforcement Learning. Proposes FAULT (Self-Diagnosis-guided Terminal Credit Redistribution) that turns diagnosed errors into explicit step-level credit anchored by terminal outcomes, solving credit assignment in long-horizon agentic RL tasks.toolsgoVotes: 0GitHub stars: 3
Arxiv 2609 38482 Panda A Decentralized Architecture With Flexible OAPANDA: A Decentralized Architecture with Flexible Orchestration for Scalable, Fault-Tolerant Multi-Agent Systems (arXiv: 2609.38482)toolsrustgoVotes: 0GitHub stars: 3
Arxiv 2609 30971 Scihorizon Elab Agentic Protocol Task CompilerAResearch paper: SciHorizon-eLab: An Agentic Protocol-to-Task Compiler for Scalable Benchmarking.toolsgoVotes: 0GitHub stars: 3
Roam Agent GuidanceAReview and maintain the technical instructions Roam gives coding agents: shipped skills, tool descriptions, preset guidance and generated instruction blocks. Use for stale, unreachable or misleading usage guidance, not product persuasion, general repo exploration or runtime defect repair.toolsshellperformanceVotes: 0GitHub stars: 19
Latex RescueADiagnose and repair LaTeX build failures in local projects or supplied logs. Make minimal source fixes, preserve scientific content and reference keys, and report actual build evidence and unresolved errors.toolsshellbashVotes: 0GitHub stars: 19
UltraworkA5-phase 17-step Phase Gate orchestrationtoolsVotes: 0GitHub stars: 46
ToolsAShow available skills, agents, and their statustoolsVotes: 0GitHub stars: 46
RalphARalph - persistent self-referential execution loop wrapping ultrawork with a spawned independent judgetoolsbashgitVotes: 0GitHub stars: 46