Skill-uri pentru agenți pe care le poți verifica înainte să le instalezi
Skill-uri SKILL.md publice din depozite GitHub cu peste 50 de stele și de la producători, scanate și evaluate. Instalează oricare dintre ele cu o singură comandă în Claude Code, Cursor, Codex, GitHub Copilot sau Gemini CLI.
46.700 de skill-uri din 2.243 de depozite · actualizat acum 19 ore
5.684 de skill-uri
- receiving-code-reviewadriannoes/awesome-agentic-aiUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementationInginerieFără avertismente★ 77↓ —
- hunt-mfa-bypassadriannoes/awesome-agentic-aiHunt MFA / 2FA bypass — 7 distinct patterns. (1) MFA not enforced on sensitive endpoints (password change, email change accept without MFA challenge), (2) MFA-step skip via direct navigation to post-login URL, (3) MFA-token replay (same code accepted twice), (4) brute-force the 6-digit OTP without rate limit (10^6 attempts at server speed), (5) race condition on OTP validation, (6) recovery-code dump via /api/me, (7) backup factor downgrade (SMS factor with no rate limit). Plus the chain: cookie theft + password oracle + no step-up = ATO without MFA challenge. Detection: trace auth flow in Burp, find every state transition, check if MFA is middleware-gated vs per-endpoint, check OTP entropy and rate limit on OTP-validate. Validate: attacker session reaching post-MFA state. Use when hunting auth bypass, MFA flows, chaining primitives toward ATO.InginerieFără avertismente★ 77↓ —
- setup-pre-commitadriannoes/awesome-agentic-aiSet up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.InginerieFără avertismente★ 77↓ —
- typescript-best-practicesadriannoes/awesome-agentic-aiTypeScript best practices. Use when reading or editing any .ts or .tsx file.InginerieFără avertismente★ 77↓ —
- unslothKalarisLabs/research-agent-skillsProvides guidance on fine-tuning large language models with Unsloth, a library for faster, lower-memory training using LoRA and QLoRA, based on its official documentation (references/llms-txt.md). Use when setting up LoRA or QLoRA fine-tuning of an LLM with Unsloth, reducing GPU memory use during training, looking up Unsloth features or APIs, debugging Unsloth training code, or learning Unsloth best practices. Not for general model training with plain Hugging Face Transformers or PEFT without Unsloth.InginerieFără avertismente★ 65↓ —
- outlinesKalarisLabs/research-agent-skillsGenerates guaranteed-valid structured output from LLMs with Outlines (dottxt.ai), constraining token sampling via finite state machines for JSON schemas, Pydantic models, regex, choice lists, and integer/float types, on Transformers, llama.cpp, vLLM, and limited OpenAI backends. Use when you need output that always parses as valid JSON or matches a regex. Use when extracting typed data into Pydantic models from a local model. Use when classifying text into a fixed set of categories. Use when running batch structured generation on vLLM or Transformers. Use when controlling token sampling at the grammar level. Not for API models needing automatic retries (use Instructor).InginerieFără avertismente★ 65↓ —
- instructorKalarisLabs/research-agent-skillsExtracts structured, validated data from LLM responses using the Instructor Python library with Pydantic response models, including nested models, enums, custom validators, automatic retries with validation error feedback, and streaming of partial objects or iterables. Works with Anthropic, OpenAI, and local Ollama models. Use when pulling typed fields or entities out of free text, when classifying text into fixed categories, when an LLM must return JSON that passes schema validation, when failed extractions need automatic retry, or when streaming partial structured results. Not for prompt optimization (use DSPy) or building multi-step chains (use LangChain).InginerieFără avertismente★ 65↓ —
- input-sanitization-validationwpultimatesecurity/WordPress-Security-SkillsUse when reading any external input in WordPress — $_GET, $_POST, $_REQUEST, $_COOKIE, REST params, shortcode/block attributes, option/meta values, or remote API responses. Unslashes then sanitizes to the correct type (sanitize_text_field, sanitize_email, absint, sanitize_key, wp_kses_post, esc_url_raw) and validates values against expected sets. Apply proactively before storing or using any untrusted value.InginerieFără avertismente★ 53↓ —
- commitnitinjain999/platform-skillsAnalyze git diffs or staged changes and generate conventional commit messages that explain WHY a change was made. Supports auto-detecting type and scope, intelligent file staging, and interactive overrides. Use when asked to "write a commit message", "generate a commit", "describe my changes", "commit this", "summarize my diff", or "/commit".InginerieFără avertismente★ 70↓ —Apare și în 1 alt depozit
- debugnitinjain999/platform-skillsStructured platform troubleshooting — classifies the problem layer, collects evidence, forms a root-cause hypothesis, and proposes a fix with validation and rollback steps.InginerieFără avertismente★ 70↓ —Apare și în 1 alt depozit
- pr-reviewnitinjain999/platform-skillsComprehensive PR review across six dimensions — cost impact, environment drift, ownership gaps, SOC 2 compliance, deprecated API / version hygiene, and rollback feasibility. Each mode inspects the diff and current file state, reports findings with severity, and recommends concrete fixes. Use when preparing a PR for merge, conducting a pre-deployment readiness check, or performing a post-merge risk assessment.InginerieFără avertismente★ 70↓ —Apare și în 1 alt depozit
- gateway-apinitinjain999/platform-skillsMigrate from the retired ingress-nginx controller to Kubernetes Gateway API, and design, debug, and review Gateway API ingress. Covers annotation inventory and risk triage, ingress2gateway conversion, implementation choice (Envoy Gateway default, Cilium, Istio, NGINX Gateway Fabric, AWS Load Balancer Controller), CRD channel and lifecycle, shared-Gateway ownership, cert-manager listener TLS, Flux layering, parallel-run DNS cutover, and rollback. Use when asked to "migrate off ingress-nginx", "convert my Ingresses to HTTPRoute", "set up Gateway API", "why is my HTTPRoute not attached", or "plan the ingress cutover". Flux reconciliation stuck → /platform-skills:gitops. East-west HTTPRoute in a mesh → /platform-skills:linkerd.InginerieFără avertismente★ 70↓ —Apare și în 1 alt depozit
- debug-helperathola/skrillsSystematic debugging approach for identifying and fixing issuesInginerieFără avertismente★ 69↓ —
- deepline-playsgetaero-io/gtm-eng-skillsDeprecated alias. Play work is now part of `deepline-gtm`, and the CLI documents plays itself. Use when a user or script still invokes `/deepline-plays`: immediately load and follow the `deepline-gtm` skill instead. Triggers: play, plays, workflow, waterfall, webhook, cron.InginerieFără avertismente★ 71↓ —
- git-workflowathola/skrillsGit best practices for version control and collaborationInginerieFără avertismente★ 69↓ —
- coding-assistantathola/skrillsProvides coding assistance with best practices and code reviewInginerieFără avertismente★ 69↓ —
- api-designerathola/skrillsDesign RESTful APIs with best practices for consistency and usabilityInginerieFără avertismente★ 69↓ —
- peft-fine-tuningKalarisLabs/research-agent-skillsFine-tunes LLMs with Hugging Face PEFT, using LoRA, QLoRA, IA3, AdaLoRA, prefix tuning, and prompt tuning so that under 1% of parameters are trained. Covers rank, alpha, and target module selection, loading and merging adapters, multi-adapter serving, and integration with TRL SFTTrainer, Axolotl, and vLLM. Use when fine-tuning 7B-70B models on limited GPU memory, when running QLoRA on a single 24GB GPU, when choosing LoRA rank and alpha, when merging or swapping adapters on one base model, or when debugging CUDA OOM or an adapter that does not apply. Not for full fine-tuning of small models under 1B parameters or cases needing all weights updated.InginerieFără avertismente★ 65↓ —
- fable-deslopdsebban/skillsDeletion-first patch minimization. Build grounded review context with the RepoPrompt CE context builder, review it with two independent Oracle lanes, then adjudicate every finding against repository and upstream evidence. Use for /skill:fable-deslop, shrinking an oversized PR, or a deletion-first review before implementation.InginerieFără avertismente★ 68↓ —
- typescript-best-practicesdsebban/skillsTypeScript best practices. Use when reading or editing any .ts or .tsx file.InginerieFără avertismente★ 68↓ —
- principle-minimize-reader-loaddsebban/skillsApply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state in the reader's head; collapse one-caller wrappers and shrink mutable scope.InginerieFără avertismente★ 68↓ —
- maintain-formal-verification-skilldsebban/skillsBring a project's formal verification back in line with the code after the code changes: find the commits that touched verified code, update the model, harness, or properties to describe the code as it is now, rerun, and say whether each failure is drift in the verification or a bug in the code. Use for /skill:maintain-formal-verification-skill, "is the model still true to the code", or after merges and refactors that touched verified code without rechecking it.InginerieFără avertismente★ 68↓ —
- setup-api-keyVapiAI/skillsGuide users through obtaining and configuring a Vapi API key. Use when the user needs to set up Vapi, when API calls fail due to missing keys, or when the user mentions needing access to Vapi's voice AI platform.InginerieFără avertismente★ 67↓ —
- interacting-with-project-runtimernett/gradle-mcpInteracting with a project's JVM runtime through the Kotlin REPL to execute focused probes against project classes and dependencies. Activate when behavior must be observed by running code; use using-gradle for build inspection or task execution.InginerieFără avertismente★ 69↓ —