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.
47,966 skills from 2,309 repositories · updated 9 hours ago
47,964 skills
- offensive-jwtSnailSploit/Claude-RedJWT attack methodology for penetration testers. Covers algorithm confusion (alg:none, RS256→HS256), weak HMAC secret brute force, kid parameter injection (SQLi, path traversal), jku/x5u/jwk header injection, JWKS cache poisoning, JWS/JWE confusion, timing attacks, and mobile JWT storage extraction. Use when testing JWT-based authentication, hunting auth bypass via token manipulation, or evaluating JWT implementation security in web or mobile apps.SecurityNo warnings★ 9.9K↓ —
- ip-as-logoanbeime/skillGenerate extremely simple, cute, personified square character images with rounded heavy forms, two purposeful character colors, one solid background color, and a dominant lower-corner composition. Use when creating an animal, creature, robot, ghost, plant, object, or other character image, including when the agent should infer three product-relevant directions and propose six independent candidates for approval.MediaNo warnings★ 8.9K↓ —
- offensive-edr-evasionSnailSploit/Claude-Redclaude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a structured SKILL.md file that primes Claude with expert-level methodology for a specific attack surface — from SQLi to shellcode, EDR evasion to exploit development.SecurityNo warnings★ 9.9K↓ —
- offensive-parameter-pollutionSnailSploit/Claude-Redclaude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a structured SKILL.md file that primes Claude with expert-level methodology for a specific attack surface — from SQLi to shellcode, EDR evasion to exploit development.SecurityNo warnings★ 9.9K↓ —
- mission-slice-sopmvschwarz/openrigUse when starting, building, handing off, restoring, or closing a mission or slice under the default lightweight SDLC.OtherNo warnings★ 8.3K↓ —
- rdd-defect-workflowGentleman-Programming/gentle-aiTrigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill switch, bounded review defects. Guide work.ProductivityNo warnings★ 8.1K↓ —Also in 1 other repo
- offensive-supply-chainSnailSploit/Claude-RedComprehensive offensive methodology for software supply chain attacks covering the full kill chain from reconnaissance through exploitation. Addresses dependency confusion across npm, PyPI, and NuGet ecosystems where internal registry override allows an attacker to inject malicious packages that shadow private dependencies. Covers typosquatting techniques for popular packages, compromised package injection via maintainer account takeover or social engineering, and build system attacks through Makefile injection, setup.py install hooks, and npm postinstall scripts. Extends into CI/CD artifact tampering where build outputs are replaced or modified in transit, code signing abuse through stolen or self-signed certificates, upstream repository compromise via commit injection or force-push to trusted repos, and container image supply chain attacks including base image trojaning and registry confusion. Maps to MITRE ATT&CK T1195.001 (Supply Chain Compromise: Compromise Software Dependencies and Development Tools) anDevOpsNo warnings★ 9.9K↓ —
- offensive-crypto-attacksSnailSploit/Claude-RedSystematic methodology for identifying and exploiting cryptographic implementation weaknesses in real-world applications. Covers padding oracle attacks against CBC-mode ciphers with PKCS7 padding (Vaudenay's original attack through modern padbuster automation), ECB mode exploitation including block cut-and-paste and byte-at-a-time decryption, hash length extension attacks against SHA1/SHA256/MD5-based MACs using HashPump, RSA vulnerabilities including small public exponent, common modulus, Bleichenbacher PKCS1v1.5 padding oracle, and Coppersmith's method for partial key recovery. Addresses weak PRNG exploitation targeting time-seeded generators and Mersenne Twister MT19937 state recovery from observed outputs, timing side-channel attacks against comparison operations, nonce reuse in AES-GCM leading to authentication key recovery, and key derivation weaknesses including insufficient iteration counts and missing salts. Primary tooling includes padbuster, RsaCtfTool, hashpump, and PyCryptodome for building custoFinanceNo warnings★ 9.9K↓ —
- applying-a-permission-policymvschwarz/openrigUse before launching a team during agent-guided setup, or when a user asks to configure OpenRig command permissions, reduce repeated native approval prompts, or apply a selected rig/seat permission policy.OtherNo warnings★ 8.3K↓ —
- seat-continuity-and-handovermvschwarz/openrigUse when replacing a seat's occupant (rebuild/handover/swap), reasoning about stable-seat-identity vs fluid-occupant-identity, choosing an old-occupant disposition (retire/advise/shadow), or recording provenance for an occupant change. Two independent outcomes (continuityOutcome + seatBindingOutcome) and the 5 failure modes that prevent silent dishonesty.OtherNo warnings★ 8.3K↓ —
- agent-operated-workflowsmvschwarz/openrigUse when a bounded real-world procedure has a deterministic happy path but brownfield, variable, or partially knowable state; when an operation must resume from verified evidence; or when deciding whether agent judgment or ordinary code should own a procedure's control loop.EngineeringNo warnings★ 8.3K↓ —
- baoyu-article-illustratorJimLiu/baoyu-skillsAnalyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style × Palette three-dimension approach. Use when user asks to "illustrate article", "add images", "generate images for article", or "为文章配图".MediaNo warnings★ 27.1K↓ —
- cognitive-doc-designGentleman-Programming/gentle-aiDesign docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.DesignNo warnings★ 8.1K↓ —Also in 1 other repo
- borzoiaipoch/open-sciencePredict genome-wide functional tracks (RNA-seq, CAGE, DNase, ChIP) from DNA sequence with Borzoi. Use this skill when: (1) Scoring the regulatory effect of a variant on expression/accessibility, (2) Generating predicted coverage tracks for a locus, (3) Prioritising non-coding variants by predicted track delta.ScienceNo warnings★ 5.4K↓ —
- esmfold2aipoch/open-scienceBiohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al. 2026, github.com/Biohub/esm). Single-sequence and MSA modes; protein, DNA, RNA, ligand (CCD/SMILES), modified residues. FoldBench Ab-Ag 50-55%, PPI 70-77% DockQ-pass. Also covers the ESMC-{300M,600M,6B} protein language models from the same release: masked-LM logits, hidden states, mutation scoring, contact prediction, and the SAE interpretability head. MIT-licensed weights on HuggingFace org `biohub`. Use this skill when: (1) Predicting complex structures with single-sequence input, (2) Validating designed binders with ESMFold2-Fast, (3) Running ESMFold2 with MSA input, (4) Getting ESMC embeddings or per-residue mutation scores, (5) Choosing kernel backend and sampling-step settings for paper-faithful throughput.ScienceNo warnings★ 5.4K↓ —
- mirrord-chaosmetalbear-co/mirrordHelp users chaos test their app with mirrord: inject artificial latency or connection errors into a mirrord session's outgoing traffic via per-session chaos rules managed with the `mirrord chaos` CLI. Use when a user wants to add latency or delay to outgoing connections or a dependency (e.g. a slow database), simulate connection failures (reset, timed out, refused), test app behavior under degraded network conditions, or wire chaos rules into CI test runs. Always use this skill instead of the deprecated _experimental_.latency mirrord config option.TestingNo warnings★ 5.4K↓ —
- customizeaipoch/open-scienceUse when the user wants to create or manage a Specialist agent or create, revise, publish, or delete a Skill through the conversational `/Customize` entry. Routes Skill work to the internal skill-creator and handles Specialist work through the JavaScript host.agents SDK.PlanningNo warnings★ 5.4K↓ —
- fair-esm2aipoch/open-scienceEmbed proteins with Meta AI's ESM-2 (`fair-esm` package). Use this skill when: (1) Extracting per-residue or per-sequence embeddings for downstream ML, (2) Masked-LM likelihood / mutation effect scoring, (3) Contact prediction from a sequence.OtherNo warnings★ 5.4K↓ —
- hunt-ldapelementalsouls/Claude-BugHunterHunt LDAP Injection and XPath Injection — authentication bypass, blind char-by-char attribute exfiltration, AD user/group enumeration, XML-store XPath bypass. Covers the LDAP special-character set (* ( ) \ NUL /), search-filter-context vs DN-injection, parenthesis-balancing, AND/OR filter logic, and {SSHA}/{CRYPT} userPassword exfil on non-AD directories. Use when target uses LDAP/AD authentication, corporate SSO with a directory backend, an address-book/people-search API, or XML-based data stores queried with XPath.MarketingNo warnings★ 5.4K↓ —
- hunt-cicdelementalsouls/Claude-BugHunterHunt CI/CD pipeline vulnerabilities — GitHub Actions workflow injection (pull_request_target Pwnrequest + ${{ }}-into-shell), self-hosted runner poisoning, OIDC trust-policy abuse, Jenkins script-console RCE and CVE-2024-23897 file read, GitLab CI runner-token registration, Terraform state file leakage, artifact/log secret leakage, pipeline env-var disclosure. Use when target has a public GitHub/GitLab org, exposed CI dashboards (Jenkins/TeamCity/Drone/Argo), or build artifacts/images are reachable.SecurityNo warnings★ 5.4K↓ —
- provider-oracleswiltodelta/remove-ai-watermarksRun hash-bound Google, OpenAI, Microsoft, or Meta watermark-oracle checks for this repository. Use for provider verification, multi-account Gemini checks, SynthID Detector checks at synthid.com, isolated Playwright checks, or recording oracle evidence. Walk the existing plan automatically when a task needs a provider verdict.TestingNo warnings★ 6.2K↓ —
- cloud-integrationsgrafana/skillsSet up, configure, and troubleshoot Grafana Cloud integrations for AWS, Azure, and other cloud providers. Use when the user asks to connect AWS CloudWatch, set up Azure Monitor, configure Confluent Cloud observability, install a Grafana integration, set up hosted exporters, use AWS Firehose for CloudWatch logs, or troubleshoot a cloud integration. Triggers on phrases like "AWS CloudWatch", "Azure Monitor", "Confluent integration", "cloud integration", "hosted exporter", "AWS Firehose", "install integration", "cloud metrics", or "cloud logs".OfficialDevOpsNo warnings★ 297↓ —
- hunt-sharepointelementalsouls/Claude-BugHunterHunt Microsoft SharePoint Server (2013/2016/2019/Subscription Edition) on-prem farms — anonymous endpoint enumeration, version disclosure, legacy SOAP login bypass (Authentication.asmx), ToolShell precondition chain (CVE-2025-53770), SafeControl reflection enumeration via Picker.aspx, NTLM Type-2 AD topology disclosure, custom-branding module discovery, EoL farm permanent-CVE-window exploitation, FormDigest anonymous issuance, file-extension blocklist NOT-an-oracle pattern, custom-zone Forms auth bridging on-prem AD. Use when target has SharePoint headers (SPRequestGuid, X-MS-InvokeApp, X-SharePointHealthScore, MicrosoftSharePointTeamServices) or paths (/_layouts/15/, /_vti_bin/, /_api/, /_catalogs/).SecurityNo warnings★ 5.4K↓ —
- genlayer-cliinternet-court/internet-court-skillUse the GenLayer CLI to deploy, interact with, and debug intelligent contracts.EngineeringNo warnings★ 7K↓ —
openrlhf-training
Orchestra-Research/AI-Research-SKILLs
PlanningUpdated Oct 11, 2026
From the author
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
Install
npx skills add Orchestra-Research/AI-Research-SKILLs --skill openrlhf-training -a claude-code
Installs to .claude/skills/openrlhf-training/ · 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
- Uses sudoLow
Why 91
Security95
Provenance90
Maintenance100
Licence100
Adoption65
Files (5)
- SKILL.md
- references/algorithm-comparison.md
- references/custom-rewards.md
- references/hybrid-engine.md
- references/multi-node-training.md