Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
47,935 skills from 2,309 repositories · updated 8 minutes ago
10,097 skills
- ase-meta-whyrse/aseFive-Whys Root-Cause Analysis.OtherNo warnings★ 60↓ —
- scenario-roblox-gameplayscenario-labs/skillsUse when building Roblox gameplay systems: NPC or enemy AI that patrols, chases and attacks, state machines or behavior trees, 'NPC pathfinding stuck', 100 zombies lag the server, hitboxes, melee combos, M1 combat, 'hits register twice', raycasts, Spherecast, Shapecast, guns and projectiles, 'bullets go through walls', knockback and stun, LinearVelocity, VectorForce or AlignPosition movers, replacing BodyVelocity, cars and vehicles with suspension, 'car flips', VehicleSeat, network ownership of NPCs and vehicles, round loops, BindToSimulation logic.OtherNo warnings★ 1.2K↓ —
- ase-meta-eli5rse/aseExplain a topic in "Explain Like I'm 5" (ELI5) style, optionally grounded in Internet/Web facts. Use when the user wants a topic explained in a very simple, child-friendly way, or mentions "eli5" or "explain like I'm 5".OtherNo warnings★ 60↓ —
- PagerDuty On-CallWYRE-AI/msp-claude-pluginsPagerDuty on-call model: schedules with rotation layers, restrictions, the computed final schedule, and overrides; escalation policy tiers and timeouts; on-call entry fields; and the schedule, escalation policy, and team MCP tools.OtherNo warnings★ 52↓ —
- feedbacklool-ventures/founder-skillsSend feedback about founder-skills — report a bug, suggest an idea, ask for help, or share a win. Drafts your message and gives you a link to submit; nothing is sent automatically.OtherNo warnings★ 51↓ —
- slime-rl-trainingKalarisLabs/research-agent-skillsProvides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.OtherNo warnings★ 79↓ —
- ca-overridearbiterForge/codeArbiterSanctioned, logged bypass of a gate or hard rule — one audit line, then proceed.OtherNo warnings★ 149↓ —
- motherduck-load-datamotherduckdb/agent-skillsLoad files, object storage, dataframes, or external databases into MotherDuck with bulk ingestion. Use for any import of data into MotherDuck.OtherNo warnings★ 62↓ —
- ConnectWise Automate ScriptsWYRE-AI/msp-claude-pluginsConnectWise Automate script management: script types (PowerShell, batch, VBScript, Shell), script folders, script execution on computers, parameter handling and validation, execution status polling, and result/history retrieval.OtherNo warnings★ 52↓ —
- Liongard SystemsWYRE-AI/msp-claude-pluginsLiongard systems — the assets discovered by inspections — plus their detail data (raw configuration JSON with historical snapshots), dataprint extraction via JMESPath expressions, and the v2 Asset Inventory identity and device profiles that correlate one entity across multiple inspectors.OtherNo warnings★ 52↓ —
- msvc-clOutlineDriven/outline-driven-developmentUse when building C or C++ on Windows with cl.exe or clang-cl: GCC-to-MSVC flag translation, /MT versus /MD, PDB output, or an LNK error. Not for MinGW cross builds from Linux: use cross-gcc.OtherNo warnings★ 55↓ —
- ca-add-deparbiterForge/codeArbiterVet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs.OtherNo warnings★ 149↓ —
- assistant-juridique-droit-travaillawve-ai/awesome-legal-skillsOrchestrateur multi-rôles en droit du travail français (salarié, employeur, audit, conseil, veille, formation). Charger pour toute consultation prud'homale, rédaction d'actes (non-concurrence, transaction, avertissement), audit de contrat ou d'accord d'entreprise, calcul d'indemnités, conformité CCN, CSE, CDD, harcèlement, temps de travail, veille chambre sociale ou audit social, avec traçabilité obligatoire des sources.OtherNo warnings★ 913↓ —
- PagerDuty ServicesWYRE-AI/msp-claude-pluginsPagerDuty service catalog: service statuses, integrations and integration keys as event sources, alert grouping modes, upstream/downstream service dependencies, and maintenance windows.OtherNo warnings★ 52↓ —
- decision-lifecyclearbiterForge/codeArbiterRecord user-decided ADRs or inspect their health read-only. Preserve attribution and acceptance evidence.OtherNo warnings★ 149↓ —
- simulink-frequency-responsematlab/simulink-agentic-toolkitEstimate frequency response from Simulink models using frestimate. Use when frequency response should be obtained from simulation rather than model linearization.OtherNo warnings★ 1.3K↓ —
- post-merge-cleanuparbiterForge/codeArbiterClean up an already-merged local branch after proving containment. Confirm each discard and preserve unique work.OtherNo warnings★ 149↓ —
- HaloPSA InvoicesWYRE-AI/msp-claude-pluginsHaloPSA invoices as a read-only MCP surface: listing by client or date range, filtering by payment and send status, retrieving line-item detail on a single invoice, and the reporting and reconciliation workflows built on them.OtherNo warnings★ 52↓ —
- praise-before-worklovstudio/skills落实用户“每次帮我肝活之前先夸夸我”的个人协作偏好。新任务开工前，先明确、具体地赞美用户，再开展工作。显式调用本 Skill 时，即使用户只说“你好”也要给出能明显感受到的夸奖；普通进度更新不重复。OtherNo warnings★ 73↓ —
- finishing-a-development-brancharbiterForge/codeArbiterOpen a PR or finish branch disposition; route CI watching and post-merge cleanup to their owners. Merge and discard need explicit authority.OtherNo warnings★ 149↓ —
- deepline-enginegetaero-io/gtm-eng-skillsBuild, publish, and verify a Deepline Play as a durable state machine over Customer DB tables, including a small paid pilot. Invoke this skill explicitly when the user asks to build an engine.OtherNo warnings★ 72↓ —
- Datto RMM SitesWYRE-AI/msp-claude-pluginsDatto RMM site management: site hierarchy and identifiers, proxy and patch-window settings, site-scoped device/alert queries, and create/update/delete operations for client locations.OtherNo warnings★ 52↓ —
- shippoAnil-matcha/awesome-muse-connectorsGet multi-carrier shipping rates, buy postage labels, track parcels, and refund labels via Shippo. Trigger phrases: shippo, shipping label, postage, shipping rates, track package.OtherNo warnings★ 1.4K↓ —
- motherduck-connectmotherduckdb/agent-skillsSet up or troubleshoot MotherDuck connections, the MotherDuck MCP server in AI clients, authentication, client runtimes, and read scaling.OtherNo warnings★ 62↓ —Also in 1 other repo
model-pruning
KalarisLabs/research-agent-skills
OtherUpdated yesterday
From the author
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.
Install
npx skills add KalarisLabs/research-agent-skills --skill model-pruning -a claude-code
Installs to .claude/skills/model-pruning/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Instructions onlyUses the networkLicence: MIT
Safety checks on SKILL.md
No warnings.
Why 82
Security100
Provenance62
Maintenance100
Licence100
Adoption32
Files (3)
- SKILL.md
- references/production-deployment.md
- references/wanda.md