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.
49,421 skills from 2,375 repositories · updated 3 minutes ago
49,421 skills
- jetson-generate-kbNVIDIA/skillsBuild a per-target knowledge-base markdown next to the active profile by walking the BSP root and source tree. Use after init-image / init-source; not for editing profile fields.MediaNo warnings★ 3.8K↓ —
- kiro-steeringgotalab/cc-sddManage {{KIRO_DIR}}/steering/ as persistent project knowledgeOtherNo warnings★ 3.8K↓ —
- i4h-workflow-e2eNVIDIA/skillsRun the maintained workflow data-to-policy pipeline from recording through checkpoint validation. Use for full end-to-end requests; do not use for one individual stage.TestingNo warnings★ 3.8K↓ —
- doca-flow-tuneNVIDIA/skillsUse this skill when the user is tuning a live or captured `doca-flow` pipeline with `doca_flow_tune` — snapshotting pipe / counter / KPI state, picking a tuning axis (rule placement, resource hints / table sizing, HW-offload mode) and a matching measurement (rule-install rate, lookup latency, hardware-counter delta), running offline or online (read-only or state-changing) modes, reading the dumper CSV / analyze JSON / visualize mermaid, or applying a recommendation back into the Flow program. Trigger even when the user does not explicitly mention "doca_flow_tune" — typical implicit phrasings include "Flow rule-install rate is low on BlueField", "table sizing looks wrong for this pipe", "tune visualize step is empty", "before/after counters don't move", or "which doca-flow knob does this recommendation hit". Refuse and route elsewhere for writing the doca-flow application, DOCA install, or streaming Flow telemetry — those belong to other skills.DataNo warnings★ 3.8K↓ —
- kiro-debuggotalab/cc-sddInvestigate implementation failures using root-cause-first debugging. Use when an implementer is blocked, verification fails, or repeated remediation does not converge.EngineeringNo warnings★ 3.8K↓ —Also in 7 other repos
- paid-ads-linkedinnowork-studio/notfair-pluginAudit, diagnose, plan, and safely operate connected LinkedIn Ads accounts through the NotFair MCP, with an export-based fallback. Use for LinkedIn advertising, sponsored content, lead-generation forms, job-title or company targeting, campaign groups, creatives, conversions, lead quality, budgets, bids, or approved LinkedIn campaign changes.MarketingNo warnings★ 4.1K↓ —
- rag-blueprintNVIDIA/skillsNVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, configure, troubleshoot, debug, fix, shutdown, stop, or tear down any RAG feature or service (Agentic RAG, VLM, guardrails, query rewriting, models, search, ingestion, observability, summarization, reasoning, and more).DevOpsNo warnings★ 3.8K↓ —
- doca-urom-svcNVIDIA/skillsOperate the DOCA UROM Service container on BlueField Arm for remote memory operations (puts, gets, atomics, collectives) enqueued by a paired host using `doca-urom`: pull the NGC image, choose the UCX component, size queues, configure Comch pairing, and align host and service versions. SECURITY: the service has no standalone access control; Comch pairing and RDMA permissions are the boundary. Pair only intended hosts, expose least-privilege memory regions, and verify both views before start. Trigger for slow UCX collectives, unexpected NOT_PERMITTED, or missing completions. Do not use for host application code, MPI/UCX integration design, or DOCA install.SecurityNo warnings★ 3.8K↓ —
- doca-benchNVIDIA/skillsRun `doca_bench` (DOCA 2.7.0 or newer) to measure throughput, bulk latency, precision latency, or maximum bandwidth for RDMA, Compress, AES-GCM, SHA, DMA, EC, Ethernet, Comch, or GPUNetIO on a host or BlueField Arm. Use it to discover enabled benchmark libraries, capture a reproducible command/version/device/environment baseline, compare stable runs against a declared tolerance, or diagnose configuration, device-binding, workload-precondition, and measurement failures. Trigger for requests such as measuring BlueField compression speed, NIC RDMA throughput, crypto latency, or a pre-upgrade baseline. Do not use for application end-to-end timing, custom benchmark code, DOCA installation, or binary patches.FinanceNo warnings★ 3.8K↓ —
- regression-hunttrailofbits/skillsUse when investigating regressions in PRs or commits, coordinating a regression campaign, or resuming saved progress.FinanceNo warnings★ 8K↓ —
- tao-launch-workflowNVIDIA/skillsThe mandatory pre-launch gate and four-verb execution contract for every TAO workflow or action. Invoke BEFORE launching anything side-effecting — AutoML, train, evaluate, inference, export, TensorRT engine generation, or DEFT/application workflows — on any execution platform. Covers platform selection, credentials, image confirmation, dataset intake, preflight, the launch review, job records, monitoring, and failure/retry classification. Trigger phrases include "train this model", "run AutoML", "launch on SLURM/docker/k8s/brev/virtualenv", "evaluate my checkpoint", "start a TAO job".ProductivityNo warnings★ 3.8K↓ —
- security-researchcode-yeongyu/oh-my-openagentTeam Mode security research skill. Orchestrates 3 vulnerability hunters and 2 PoC engineers to audit a codebase in parallel, prove exploitability, classify root causes, and calibrate severity by actual exploitability. Use for security review, vulnerability research, exploitability audit, pre-release security check, threat model validation, and `/security-research`. Triggers: 'security-research', 'security research', 'security review', 'vulnerability audit', 'exploitability audit', '보안 리뷰', '취약점 감사'.SecurityNo warnings★ 70.7K↓ —
- gsd:ui-reviewdavepoon/buildwithclaudeRetroactive 6-pillar visual audit of implemented frontend codeDesignNo warnings★ 3.7K↓ —
- launch-feedback-synthesizeraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "triage launch feedback", "cluster reviews, comments, and board posts into themes", or "set up a you asked, we shipped loop"; produces a feedback theme digest (frequency, severity, representative quotes per theme), an open→planned→started→completed/declined status loop with duplicate-merge and notification rules, shipped-change announcement material, and a compliant social-proof harvest protocol (never incentivized store reviews). Not for repurposing or amplifying the harvested proof — use content-amplifier; not for executing testimonial outreach threads — use outreach-manager. 反馈分诊/状态环/社证收割/评测合规LegalNo warnings★ 3.1K↓ —
- principle-redesign-from-first-principlesmichael-denyer/pstack-claudeApply when integrating a new requirement into an existing design.DesignNo warnings★ 3.9K↓ —
- yt-ideationjeremylongshore/tons-of-skills-marketplaceGenerate filmable YouTube video ideas, explain their evidence and priority, and save user selections for briefing. Use when planning content from research or a topic. Trigger with "video ideas", "what should I make next" or "brainstorm videos".MediaNo warnings★ 2.9K↓ —
- kermt-monitorNVIDIA/skillsCheck progress for a detached KERMT run (pretrain, finetune, or any kermt_run_detached invocation). Reads run.json, queries docker for container state, tails the pretrain/finetune log, and parses progress lines (epoch, step, val loss).DevOpsNo warnings★ 3.8K↓ —
- narrative-quality-auditoraaron-he-zhu/aaron-marketing-skillsUse when the user asks to "audit our brand narrative" or "is this message on-canon"; runs separate typed TALE truth, system, or effectiveness profiles and never averages them into one composite. Checks differentiation, canon, landing consistency, and evidence integrity. Not for launch readiness — use launch-readiness-auditor; not for social operations — use social-quality-auditor. 品牌叙事分层审计/发布前一致性放行OtherNo warnings★ 3.1K↓ —
- planejeremylongshore/tons-of-skills-marketplacePlane is a team behavior observatory — synthesize Plane API data into observations about how teams actually behave under pressure, not just ticket state. Five compound commands surface cycle velocity vs. plan, stale-ticket ownership churn, reviewer gate strength, stated-vs-actual priority drift, and cross-project workload concentration. Reads from the live mcp__plane MCP server when present; documentation-only otherwise. Use when investigating "why is this team's plan diverging from reality", auditing cycle health, finding orphan tickets, identifying review bottlenecks, or onboarding to a new project. Trigger with "/plane-cycle-velocity", "/plane-stale-tickets", "/plane-reviewer-gate-strength", "/plane-priority-drift", "/plane-cross-project-load", "audit Plane cycle", "team behavior plane", "how is my team behaving".PlanningNo warnings★ 2.9K↓ —
- cdf-simulationNVIDIA/skillsComponent-owned guidance for CDF Simulation requests submitted directly or through Airflow-triggered DIG Flow Catalog prompts — golden THT board, THT pin-geometry variation, good/clean SMT images, structural pose defects, and solder texture defects, from a board USD. Turns one matched prompt into one validated `cdf.CDFJob` build and its compiled JobOrder payload; it never executes a render itself. Requires a caller-supplied board USD and output root, asks for either when missing from an interactive request, and resolves optional details with fixed, documented defaults.MediaNo warnings★ 3.8K↓ —
- message-system-architectaaron-he-zhu/aaron-marketing-skillsUse when the user asks to "author our durable brand message hierarchy", "build the brand message house that seeds the canon", or "define the main narrative, three pillars, and tagline for the whole brand"; produces the DURABLE brand message system — main narrative, three value pillars, per-persona proof points (each labeled Measured / User-provided / '[needs source]'), and the tagline/one-liner — that seeds the narrative-registry canon and from which every per-launch house derives. Not for a single launch's message house or PR-FAQ — use message-house-builder; not for claim adjudication — use offer-claims-registry; not for the change-narrative arc itself — use strategic-narrative-designer. 品牌消息屋/主叙事/三支柱/标语/持久叙事 canonPlanningNo warnings★ 3.1K↓ —
- reasoningjeremylongshore/tons-of-skills-marketplaceUse BEFORE answering analytical, diagnostic, planning, or multi-step reasoning questions. Trigger phrases include "should I X or Y", "why is X happening", "what's the best approach", "what are the tradeoffs", "help me think through", "diagnose", "root cause", "plan/design X", "what are the implications of", "compare these approaches". Also fires on cross-domain analysis, strategy questions, architecture decisions, or anything requiring multiple factors to be weighed before responding. The skill calls the reasoning MCP tool to retrieve a cognitive scaffold (named failure pattern, executable procedure, suppression vectors, falsification test) the model absorbs internally before generating its response. Catches causal shortcuts, premature conclusions, generic templates, and surface pattern matching that produce confidently-wrong answers. Do NOT trigger for simple factual lookups, syntax questions, file reads, code execution, or restating the user's input.TestingNo warnings★ 2.9K↓ —
- cdf-anomalygenNVIDIA/skillsUse when running the CDF AnomalyGen pipeline over a defect dataset — mask placement, fine-tuning, synthetic defect-image generation (SDG), evaluation, quality refinement, and pseudo-labeling — even when the user names only one stage.MediaNo warnings★ 3.8K↓ —
- vastai-rate-limitsjeremylongshore/tons-of-skills-marketplaceDiagnose and design bounded Vast.ai CLI and REST traffic around per-endpoint, per-identity rate limits and the absence of Retry-After headers. Use when implementing polling, batch automation, or 429 recovery. Trigger with: "handle Vast.ai 429", "reduce Vast.ai polling", "set Vast.ai retry policy".DesignNo warnings★ 2.9K↓ —
why
backnotprop/pstack
DevOpsUpdated yesterday
From the author
Use 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.
Install
npx skills add backnotprop/pstack --skill why -a claude-code
Installs to .claude/skills/why/ · 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: MIT
Safety checks on SKILL.md
No warnings.
Why 90
Security100
Provenance82
Maintenance100
Licence100
Adoption56
Files (13)
- SKILL.md
- references/epistemics.md
- references/investigator-prompt.md
- references/source-playbook.md
- references/sources/code-archaeology.md
- references/sources/databricks.md
- references/sources/datadog.md
- references/sources/incident-postmortem.md
- references/sources/linear.md
- references/sources/notion.md
- references/sources/sentry.md
- references/sources/slack.md
- +1 more