Browse Skills
44756 skills found
pytorch-model-cli.md
13
1
export
pytorch-model-cli
2
from
"letta-ai/skills"
from
"letta-ai/skills"
3
Guidance for creating standalone CLI tools that perform neural network inference by extracting PyTorch model weights and reimplementing inference in C/C++. This skill applies when tasks involve converting PyTorch models to standalone executables, extracting model weights to portable formats (JSON), implementing neural network forward passes in C/C++, or creating CLI tools that load images and run inference without Python dependencies.
2026-01-21
dispatching-parallel-agents.md
13
1
export
dispatching-parallel-agents
2
from
"withzombies/hyperpowers"
from
"withzombies/hyperpowers"
3
Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently
2026-01-21
wrangler-coder.md
13
1
export
wrangler-coder
2
from
"majesticlabs-dev/majestic-marketplace"
from
"majesticlabs-dev/majestic-marketplace"
3
This skill guides Cloudflare Workers and Pages development with Wrangler CLI. Use when creating Workers, configuring D1 databases, R2 storage, KV namespaces, Queues, or deploying to Cloudflare Pages.
2026-01-22
web-browser.md
13
1
export
web-browser
2
from
"majesticlabs-dev/majestic-marketplace"
from
"majesticlabs-dev/majestic-marketplace"
3
Browser automation using browser-cdp CLI. Control Chrome, Brave, or Edge browsers for testing, scraping, and web interaction. Uses your real browser (not test mode) for authentic sessions.
2026-01-22
kv-store-grpc.md
13
1
export
kv-store-grpc
2
from
"letta-ai/skills"
from
"letta-ai/skills"
3
Guidance for building gRPC-based key-value store services in Python. This skill should be used when tasks involve creating gRPC servers, defining protocol buffer schemas, or implementing key-value storage APIs with gRPC. Covers proto file creation, code generation, server implementation, and verification strategies.
2026-01-21
model-extraction-relu-logits.md
13
1
export
model-extraction-relu-logits
2
from
"letta-ai/skills"
from
"letta-ai/skills"
3
Guidance for extracting weight matrices from black-box ReLU neural networks using only input-output queries. This skill applies when tasked with recovering internal parameters (weights, biases) of a neural network that can only be queried for outputs, particularly two-layer ReLU networks. Use this skill for model extraction, model stealing, or neural network reverse engineering tasks.
2026-01-21
politique-confidentialite.md
13
1
export
politique-confidentialite
2
from
"lawvable/awesome-legal-skills"
from
"lawvable/awesome-legal-skills"
3
Guide complet pour la rédaction de politiques de confidentialité conformes au RGPD. Contient les recommandations CNIL 2020, un template de référence et les bonnes pratiques. À utiliser lors de la rédaction ou révision d'une politique de confidentialité pour un site web ou une application.
2026-01-21
ln-362-build-auditor.md
13
1
export
ln-362-build-auditor
2
from
"levnikolaevich/claude-code-skills"
from
"levnikolaevich/claude-code-skills"
3
Build health audit worker (L3). Checks compiler/linter errors, deprecation warnings, type errors, failed tests, build configuration issues. Returns findings with severity (Critical/High/Medium/Low), location, effort, and recommendations.
2026-01-21
ln-120-reference-docs-creator.md
13
1
export
ln-120-reference-docs-creator
2
from
"levnikolaevich/claude-code-skills"
from
"levnikolaevich/claude-code-skills"
3
Creates reference documentation structure + smart documents (ADRs/Guides/Manuals) based on TECH_STACK. Only creates justified documents (nontrivial technology choices). L2 Worker in ln-100-documents-pipeline.
2026-01-21
pptx.md
13
1
export
pptx
2
from
"lawvable/awesome-legal-skills"
from
"lawvable/awesome-legal-skills"
3
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
2026-01-21
ln-130-tasks-docs-creator.md
13
1
export
ln-130-tasks-docs-creator
2
from
"levnikolaevich/claude-code-skills"
from
"levnikolaevich/claude-code-skills"
3
Creates task management documentation (docs/tasks/README.md + kanban_board.md). L2 Worker in ln-100-documents-pipeline. Sets up Linear integration and task tracking rules.
2026-01-21
llm-inference-batching-scheduler.md
13
1
export
llm-inference-batching-scheduler
2
from
"letta-ai/skills"
from
"letta-ai/skills"
3
Guidance for optimizing LLM inference request batching and scheduling problems. This skill applies when designing batch schedulers that minimize cost while meeting latency and padding constraints, involving trade-offs between batch count, shape selection, and padding ratios. Use when the task involves grouping requests by sequence lengths, managing shape compilation costs, or optimizing multi-objective scheduling with hard constraints.
2026-01-21
bn-fit-modify.md
13
1
export
bn-fit-modify
2
from
"letta-ai/skills"
from
"letta-ai/skills"
3
Guide for Bayesian Network tasks involving structure learning, parameter fitting, intervention, and sampling. This skill should be used when working with pgmpy or similar libraries to recover DAG structures from data, fit conditional probability distributions, perform causal interventions (do-calculus), or sample from modified networks.
2026-01-21
command-patterns.md
13
1
export
command-patterns
2
from
"majesticlabs-dev/majestic-marketplace"
from
"majesticlabs-dev/majestic-marketplace"
3
Advanced patterns for generating high-quality Claude Code commands. Used by /new-command.
2026-01-22
verification-before-completion.md
13
1
export
verification-before-completion
2
from
"withzombies/hyperpowers"
from
"withzombies/hyperpowers"
3
Use before claiming work complete, fixed, or passing - requires running verification commands and confirming output; evidence before assertions always
2026-01-21
event-sourcing-coder.md
13
1
export
event-sourcing-coder
2
from
"majesticlabs-dev/majestic-marketplace"
from
"majesticlabs-dev/majestic-marketplace"
3
Record domain events and dispatch to inbox handlers for side effects, audit trails, and activity feeds. Use when building activity logs, syncing external services, or decoupling event creation from processing. Triggers on event recording, audit trails, activity feeds, or inbox patterns.
2026-01-22
learning-sdk-integration.md
13
1
export
learning-sdk-integration
2
from
"letta-ai/skills"
from
"letta-ai/skills"
3
Integration patterns and best practices for adding persistent memory to LLM agents using the Letta Learning SDK
2026-01-21
mteb-retrieve.md
13
1
export
mteb-retrieve
2
from
"letta-ai/skills"
from
"letta-ai/skills"
3
This skill provides guidance for semantic similarity retrieval tasks using embedding models (e.g., MTEB benchmarks, document ranking). It should be used when computing embeddings for documents/queries, ranking documents by similarity, or identifying top-k similar items. Covers data preprocessing, model selection, similarity computation, and result verification.
2026-01-21
break-filter-js-from-html.md
13
1
export
break-filter-js-from-html
2
from
"letta-ai/skills"
from
"letta-ai/skills"
3
This skill provides guidance for XSS filter bypass tasks where the goal is to craft HTML payloads that execute JavaScript despite sanitization filters. Use this skill when tasks involve bypassing HTML sanitizers (like BeautifulSoup), exploiting parser differentials between server-side sanitizers and browsers, or security testing/CTF challenges involving XSS filter evasion.
2026-01-21
cancel-async-tasks.md
13
1
export
cancel-async-tasks
2
from
"letta-ai/skills"
from
"letta-ai/skills"
3
Guidance for implementing proper asyncio task cancellation with signal handling in Python. This skill applies when implementing concurrent task runners that need graceful shutdown, handling KeyboardInterrupt/SIGINT in asyncio contexts, or managing task cleanup when using semaphores for concurrency limiting. Use when tasks involve asyncio.gather, CancelledError handling, or cleanup of tasks that haven't started execution.
2026-01-21
ln-111-root-docs-creator.md
13
1
export
ln-111-root-docs-creator
2
from
"levnikolaevich/claude-code-skills"
from
"levnikolaevich/claude-code-skills"
3
Creates 4 root documentation files (CLAUDE.md, docs/README.md, documentation_standards.md, principles.md). L3 Worker invoked by ln-110-project-docs-coordinator.
2026-01-21
pdf.md
13
1
export
pdf
2
from
"lawvable/awesome-legal-skills"
from
"lawvable/awesome-legal-skills"
3
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
2026-01-21
cancel-async-tasks.md
13
1
export
cancel-async-tasks
2
from
"letta-ai/skills"
from
"letta-ai/skills"
3
Guidance for implementing asyncio task cancellation with proper cleanup, especially for handling keyboard interrupts (Ctrl+C). This skill should be used when tasks involve asyncio cancellation, signal handling, or graceful shutdown of concurrent Python tasks.
2026-01-21
fixing-bugs.md
13
1
export
fixing-bugs
2
from
"withzombies/hyperpowers"
from
"withzombies/hyperpowers"
3
Use when encountering a bug - complete workflow from discovery through debugging, bd issue, test-driven fix, verification, and closure
2026-01-21