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.
48,622 skills from 2,355 repositories · updated 9 hours ago
48,622 skills
- terraform-policyhashicorp/agent-skillsWrite, test, or convert Terraform Policy files (.policy.hcl, .policytest.hcl, Sentinel→tfpolicy). Triggers: policy.hcl, policytest, convert sentinel, tfpolicy, write a policy.OfficialDevOpsNo warnings★ 911↓ —
- concurrent-brancheskajisho5/ffmpeg-skillResolve conflicts and merges when several branches are open against one repo at the same time — the hotspot files every change must touch (registry manifests, a single version field, shared tool config, one aggregated test module, tracked build output), union-vs-recompute-vs-rebuild as three different correct resolutions, generated artifacts that must never be merged, non-deterministic serialization that makes every branch conflict, renumbered identifiers that git cannot show you, and why a clean auto-merge is not a passing test. Use when rebasing or merging a long-lived branch, resolving conflict markers, reviewing a merge commit, deciding what a repo should commit vs generate, or setting up a repo that will take parallel contributions.TestingNo warnings★ 4.2K↓ —
- get-pr-commentsmichael-denyer/pstack-claudeFetch and summarize review comments from the active pull requestEngineeringNo warnings★ 3.7K↓ —
- azure-image-builderhashicorp/agent-skillsBuild Azure managed images and Azure Compute Gallery images with Packer. Use when creating custom images for Azure VMs.OfficialDevOpsNo warnings★ 911↓ —
- principle-guard-the-context-windowmichael-denyer/pstack-claudeApply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.ProductivityNo warnings★ 3.7K↓ —
- tao-finetune-clipNVIDIA/skillsCLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT deployment. Use when fine-tuning or training CLIP, running zero-shot classification, computing image embeddings, or deploying CLIP to ONNX/TensorRT. This is a single-action model skill; do not use it for an iterative weak-attribute improvement loop that keeps retraining and evaluating until progress stops, which belongs to tao-run-deft-pas.DevOpsNo warnings★ 3.8K↓ —
- create-verification-skillmichael-denyer/pstack-claudeGenerate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", "make a driver skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.DesignNo warnings★ 3.7K↓ —
- hormuz-straithimself65/finance-skillsCheck the live status of the Strait of Hormuz from the Hormuz Strait Monitor dashboard: open, restricted, or closed status, tanker transits vs normal, stranded vessels, Brent price impact, war-risk insurance levels, cargo throughput, tanker freight rates, diplomatic developments, and global trade impact. Use this skill whenever the user asks about the Strait of Hormuz or the Persian Gulf in the context of oil, shipping, or geopolitical risk — whether Hormuz is open, chokepoint or transit disruption, Gulf tanker traffic, war-risk premiums, Middle East shipping routes, or energy supply-chain risk.ProductivityNo warnings★ 3.5K↓ —
- gsd:spikedavepoon/buildwithclaudeSpike an idea through experiential exploration, or propose what to spike next (frontier mode)OtherNo warnings★ 3.7K↓ —
- exa-cost-tuningjeremylongshore/tons-of-skills-marketplaceControl Exa spend through endpoint selection, bounded result and content work, per-key budgets, and response-derived cost evidence. Use when operating or reviewing this Exa boundary. Trigger with "Exa cost tuning", "review Exa cost tuning", or "fix Exa cost tuning".EngineeringNo warnings★ 2.9K↓ —
- hermes-tweetdavepoon/buildwithclaudeUse Hermes Tweet when a Claude Code workflow needs a source-aware handoff to Hermes Agent for X/Twitter research, account context, monitoring, or approval-gated actions through the native Hermes Agent plugin.ScienceNo warnings★ 3.7K↓ —
- whybacknotprop/pstackUse for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.DevOpsNo warnings★ 3.3K↓ —
- sharpenbacknotprop/pstackMake a task deeper, not bigger, then rewrite the prompt. Use for /sharpen.ProductivityNo warnings★ 3.3K↓ —
- gsd:research-phasedavepoon/buildwithclaudeResearch how to implement a phase (standalone - usually use /gsd:plan-phase instead)ScienceNo warnings★ 3.7K↓ —
- alchemy-cost-tuningjeremylongshore/tons-of-skills-marketplaceGovern Alchemy compute usage and spend with current account evidence, workload attribution, budgets, and reversible optimizations. Use when forecasting or reducing Alchemy cost. Trigger with "Alchemy cost", "Alchemy compute units", or "reduce Alchemy spend".OtherNo warnings★ 2.9K↓ —
- speckit-planforyourhealth111-pixel/Vibe-SkillsGenerate technical implementation plans from feature specifications. Use after creating a spec to define architecture, tech stack, and implementation phases. Creates plan.md with detailed technical design.PlanningNo warnings★ 3.8K↓ —
- abridge-hello-worldjeremylongshore/tons-of-skills-marketplaceRun a bounded Abridge smoke test through the documented user workflow using an approved test encounter and no invented API. Use when validating a new tenant or pilot cohort. Trigger with "smoke test Abridge".TestingNo warnings★ 2.9K↓ —
- gsd:validate-phasedavepoon/buildwithclaudeRetroactively audit and fill Nyquist validation gaps for a completed phaseOtherNo warnings★ 3.7K↓ —
- networkxforyourhealth111-pixel/Vibe-SkillsComprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python. Use when working with network/graph data structures, analyzing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualizing network topologies. Applicable to social networks, biological networks, transportation systems, citation networks, and any domain involving pairwise relationships.ScienceNo warnings★ 3.8K↓ —Also in 1 other repo
- gsd:session-reportdavepoon/buildwithclaudeGenerate a session report with token usage estimates, work summary, and outcomesProductivityNo warnings★ 3.7K↓ —
- ramp-rate-limitsjeremylongshore/tons-of-skills-marketplaceImplement a shared Ramp request budget with rolling-window throttling, bounded retries, pagination, and 504 recovery. Use when clients receive 429 or 504 responses or share one outbound IP. Trigger with "Ramp rate limit" or "Ramp 429".OtherNo warnings★ 2.9K↓ —
- memoryjeremylongshore/tons-of-skills-marketplaceUse when sharpening a perception or observation you ALREADY formed about conversation state, user behavior, drift, emotional shifts, or cross-turn patterns. Trigger phrases include "what did you notice about X", "the user keeps doing Y", "I sense something has changed", "is the user X-ing", "what does this pattern suggest", "what shifted across our turns", "am I missing something here", "why did the conversation move from X to Y", or any moment requiring verification of whether a felt signal is real or projection. The skill calls the memory MCP tool to retrieve a perception scaffold (perception failure, detection procedure, suppression vectors) that SHARPENS an observation you already have. It is NOT a substitute for observing first. Do NOT trigger for fact extraction, summarization, list-making, factual lookups, or write-heavy memory tasks (storing/retrieving structured data). Memory harness is filter/perception oriented; calling on write-heavy tasks produces scaffold paralysis.ProductivityNo warnings★ 2.9K↓ —
- benchmark-checklistmichael-denyer/pstack-claudeVet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benchmark or report a speedup or regression you measured.OtherNo warnings★ 3.7K↓ —
- architectbacknotprop/pstackSketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.PlanningNo warnings★ 3.3K↓ —
upstream-patches
pulumi/agent-skills
OfficialDevOpsUpdated 2 days ago
From the author
Create, amend, remove, and rebase patches for Terraform provider submodules using `./scripts/upstream.sh`. Use when `upgrade-provider` or manual patch work needs owning-patch lookup, patch conflict fixes, patch/hunk removal, or upstream rebase.
Install
npx skills add pulumi/agent-skills --skill upstream-patches -a claude-code
Installs to .claude/skills/upstream-patches/ · 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 onlyNo network use seenLicence: APACHE-2.0
Safety checks on SKILL.md
No warnings.
Why 90
Security100
Provenance100
Maintenance100
Licence100
Adoption33
Files (3)
- SKILL.md
- agents/openai.yaml
- use_cases.yaml