1,848 free skills
AI & ML skills
Skills for AI/ML work — LLM prompt engineering, RAG pipelines, vector databases, fine-tuning, and agent orchestration.
Sourced from real, public repositories — synced daily, never invented.
1,848 free skills
Skills for AI/ML work — LLM prompt engineering, RAG pipelines, vector databases, fine-tuning, and agent orchestration.
Sourced from real, public repositories — synced daily, never invented.
15 tools across six categories
13 of them never send your data anywhere
Free · No signup · No trial clock
SEE THE DIRECTORY
regex-vs-llm-structured-text
mitamarcelo/everything-claude-code
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
regex-vs-llm-structured-text
rianico/harness-zkx
>-
regex-vs-llm-structured-text
siniyayousuf/everything_claudecode
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
regex-vs-llm-structured-text
bjornjee/skills
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
regex-vs-llm-structured-text
loulanyue/awesome-claude-notes
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
regex-vs-llm-structured-text
pytrak89/everything-claude-code-v2
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
regex-vs-llm-structured-text
khanhhuyenngo985-sys/character-scene-design-skills
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
regex-vs-llm-structured-text
pey-sjitech/ecc
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
regex-vs-llm-structured-text
oruga420/claude-code-skills
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
regex-vs-llm-structured-text
sehoon787/my-claude
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
regex-vs-llm-structured-text
mrebrahim/everything-claude-code
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
regex-vs-llm-structured-text
burgebj/claude_everything
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
regex-vs-llm-structured-text
danielnguyenfinhub/ecc
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
regex-vs-llm-structured-text
iamkarp/claude-code-dotfiles
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
regex-vs-llm-structured-text
yimengfan/claude-code-for-unity3d
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
regex-vs-llm-structured-text
k1lgor/mega-mind-skills
Decision framework and hybrid implementation for regex vs LLM text parsing. Use when parsing structured text (forms, logs, tables) to optimize cost and accuracy.
regex-vs-llm-structured-text
lidge-jun/cli-jaw-skills
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
regex-vs-llm-structured-text
partha7364/everything-claude-code
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
ticket-overview
yassimba/loom
Beads/BV ticket map with ASCII dependencies and product context. Use when the user asks for: (1) the complete issue graph, (2) roadmap workstreams and execution leverage, or (3) what a set of tickets is building.
totp-provider-api
paldom/2fa-agents
Fetches 2FA codes from a managed provider's API or CLI - 1Password, Bitwarden, HashiCorp Vault's TOTP engine, 2FAuth - so the seed never lands on this machine. Use when the user wants an OTP from a password manager or team-shared 2FA, or asks whether Google Authenticator or another provider has a usable API. Not for local seed files, keychain storage, or offline code generation.
bitwarden-credential-management
tamirdresher/squad-skills
Secure credential management for AI agents via official Bitwarden MCP server and bw CLI. Agents can store and retrieve secrets without exposing the entire vault. All access is audited.
runtime-cli-scripting
ortus-boxlang/skills
Use this skill when writing BoxLang CLI scripts and classes, handling command-line arguments, using the BoxLang REPL, running action commands (compile, cftranspile, featureaudit), detecting runtime context, and leveraging CLI-specific built-in functions.
optimization-expert
luokai25/luo_os-v_0.1
Expert-level optimization knowledge. Use when working with linear programming, convex optimization, nonlinear programming, integer programming, dynamic programming, gradient methods, duality theory, or optimization algorithms. Also use when the user mentions 'linear programming', 'simplex method', 'convex optimization', 'Lagrangian', 'KKT conditions', 'gradient descent', 'Newton method', 'integer programming', 'dynamic programming', 'duality', 'Bellman equation', or 'branch and bound'.
portfolio-monitor
dzianisv/financial-advisor-agents
Living DISCIPLINE monitor over an already-reviewed equity book (CSV with theses + written triggers). Pulls live prices via yfinance, computes extension vs 200d MA (euphoria gauge) and % from 52-week high, detects which written triggers in Price_Flag/Next_Step have FIRED or are NEAR (best-effort regex, requires literal $; handles macro proxies BTC/Brent/oil/TON), flags EUPHORIA (>30% above 200dMA + HIGH AI_Bubble_Fragility), UNACTIONED SELL, and CONCENTRATION (>10% of book). Emits stocks/monitor-report-<date>.md: what needs action now, sorted by $. Materially-changed positions are then handed to multi-lens-quorum (separate agent step) for the buy/sell/hold call. Run: python3 scripts/portfolio_monitor.py --csv <file> --out <dir>. Triggers: monitor my portfolio, what changed in my book, did any triggers fire, check my holdings for euphoria or concentration, portfolio discipline check. Discipline not alpha; notification-only; never trades.
optimization-expert
luokai0/ai-agent-skills-by-luo-kai
Expert-level optimization knowledge. Use when working with linear programming, convex optimization, nonlinear programming, integer programming, dynamic programming, gradient methods, duality theory, or optimization algorithms. Also use when the user mentions 'linear programming', 'simplex method', 'convex optimization', 'Lagrangian', 'KKT conditions', 'gradient descent', 'Newton method', 'integer programming', 'dynamic programming', 'duality', 'Bellman equation', or 'branch and bound'.
couchbase-columnar
celticht32/couchbase-skills-for-claude.ai
Design and use Couchbase Capella Columnar, the columnar analytics database service. Use whenever the user asks about Capella Columnar, columnar analytics, Columnar instance, Columnar vs Analytics service, Columnar collections, Columnar links to operational data, Columnar SQL++, Columnar pricing, when to use Columnar vs the Analytics service, or 'I need to run analytical queries on my Couchbase data.' Distinct from the cb-analytics-* skills (which cover the Couchbase Analytics Service embedded in Couchbase Server / Capella operational clusters) — Capella Columnar is a separate, standalone columnar database product on Capella. Use proactively when the user needs OLAP-scale analytics, BI tool integration, or columnar storage for analytical workloads.
casegraph-integrate
caphtech/casegraph
Use when integrating CaseGraph with external tools (markdown importer, optional sinks like Todoist / GitHub Issues, workers such as shell / local-llm / code-agent) or when verifying or recovering storage. Trigger on references to `cg import markdown`, `cg sync push|pull`, `cg worker run`, `cg validate`, `cg validate storage`, `cg cache rebuild`, `cg events verify|export`, `cg migrate`, `env_allowlist`, `approval_policy`, or phrases like "import markdown", "sync pull", "run a worker", "rebuild the cache", "verify events", "run migration". For day-to-day graph reading or editing use casegraph; for AI-authored graph changes use casegraph-patch.
casegraph
caphtech/casegraph
Use when reading, manually authoring, or analyzing a CaseGraph workspace through the `cg` CLI. Trigger on references to `.casegraph/`, `cg case`, `cg node`, `cg edge`, `cg task`, `cg frontier`, `cg blockers`, `cg analyze`, `cg case view`, or phrases like "show the case", "what's blocked", "analyze impact", "create a case", "show the frontier". Do NOT use for AI-proposed graph changes (use casegraph-patch) or for importer/sink/worker/storage recovery (use casegraph-integrate).
parse-cv
aibot88/sec_skill_store
Pre-process a CV/profile file (PDF, DOCX, ODT, RTF) into plain text BEFORE feeding it to the LLM context. Reduces token cost by 5-10x on long CVs and yields more reliable extraction than reading binary PDFs directly via multimodal vision. The Assistente calls this skill on every uploaded document in `$JHT_HOME/profile/sources/` before populating `candidate_profile.yml`. For images (jpg/png of paper CV) skip this skill — read them via vision directly (the LLM is multimodal). For unsupported formats the skill exits non-zero and the Assistente asks the user for an alternative.
cv-vehicle-counting
sandeeprdy1729/skill_galaxy
Master cv vehicle counting with comprehensive coverage of concepts, implementation, optimization, and production best practices. Essential skill for professionals working in ai-ml.
cv-medical-image-segmentation
sandeeprdy1729/skill_galaxy
Master cv medical image segmentation with comprehensive coverage of concepts, implementation, optimization, and production best practices. Essential skill for professionals working in ai-ml.
cv-lip-sync-generation
sandeeprdy1729/skill_galaxy
Master cv lip sync generation with comprehensive coverage of concepts, implementation, optimization, and production best practices. Essential skill for professionals working in ai-ml.
fluid-dynamics
synthetic-sciences/openscience
Computational fluid dynamics — Navier-Stokes solvers, lid-driven cavity, channel flow, vortex methods, turbulence statistics, drag/lift computation. Spectral and finite-difference methods for incompressible and compressible flows.
dq-cli-command
ryanmiville/dq
Add or modify dq CLI subcommands in this repo. Use when implementing a new pipeline stage, wiring clap command parsing, following the plan-appending command pattern, or adding TOML fixture coverage for command behavior.
dx-harness
derek-x-wang/skills
Guide projects to create an internal CLI tool ("dx") that streamlines development workflows for both humans and AI agents. Use when starting a new project, setting up a monorepo, adding internal tooling, creating developer scripts, or when someone asks about project CLIs, developer experience tools, or "dx" packages. Also use when creating a project-level "dx" skill that documents the CLI for AI consumption.
schriftsatzkern-substantiierung
klotzkette/claude-fuer-deutsches-recht
Wenn es um Schriftsatzkern Substantiierung in Fachanwalt Agrarrecht geht: erstellt den passenden Entwurf aus Sachverhalt, Norm, Beweis und Antrag; liefert einen verwertbaren Entwurf mit Anträgen, Begründung und Anlagenlogik.
instance-storage-patterns
microsoft/amplifier-bundle-skills
>
obsidian-rag-bridge
mbeacom/productivity-skills
Use to retrieve from an Obsidian vault by combining its link graph/tags with local semantic search: produce a candidate note set (official obsidian CLI, or rg fallback) and feed it to local-rag's --allowlist. For writing notes, Bases, or Canvas, use the kepano/obsidian-skills plugin instead.
motion-typewriter
wcc723/claude-skill-design-gallery
Use when generating a single-file HTML page for the 「島嶼共鳴 2026」music festival with typewriter effect on hero and paragraph reveal. Triggers on typewriter、打字機效果、char-by-char reveal、cursor blink.
edge-fm-benchmark-report
windog-labs/edge-fm-x
Generate detailed benchmark reports inside this edge-fm repo, covering configurable Qwen2.5 LLM/VLM model matrices on CUDA. The default fair comparison remains Transformers vs EdgeFM(cuda-graph) vs TRT-Edge-LLM for LLM, while VLM currently uses Transformers vs EdgeFM(cuda-graph). Use when the user asks for benchmark指标、性能对比、详细报告、cuda-graph vs TRT-Edge-LLM analysis, VLM benchmark reports, or wants the existing tests/engine/test_qwen2_generate.py benchmark flow wrapped into a repeatable local workflow.
prc-fin-006-payroll-monthly
kriptoburak/profitrise-sop-system
Monthly payroll-processing SOP per HK Employment Ordinance — wages within 7 days of period end, 713 average-wage rule for leave/holiday pay, 15 statutory holidays for 2026. Use to run the monthly payroll cycle.
pragmatic-fp
paopun20/paopaoskillpacks
>
fp-ts-pragmatic-v2
diegosouzapw/awesome-omni-skills
Pragmatic Functional Programming workflow skill. Use this skill when the user needs A practical, jargon-free guide to fp-ts functional programming - the 80/20 approach that gets results without the academic overhead. Use when writing TypeScript with fp-ts library and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
alert-tuning
roodlicht/accans-sec-skills
SOC alert-tuning workflow — false-positive reduction via targeted suppressions (rule-id + reason + expiry), baseline learning, rule retirement, severity recalibration, and metrics (alert volume, mean-time-to-triage, fatigue index). Prevents detection collapse without losing coverage.
ralph-loop
lofibrainwav/mandeok
Generate copy-paste bash scripts for Ralph Wiggum/AI agent loops (Codex, Claude Code, OpenCode, Goose). Use when asked for a “Ralph loop”, “Ralph Wiggum loop”, or an AI loop to plan/build code via PROMPT.md + AGENTS.md, SPECS, and IMPLEMENTATION_PLAN.md, including PLANNING vs BUILDING modes, backpressure, sandboxing, and completion conditions.
pinescript-builtins
kasperchengh/multicharts-powerlanguage
Use when writing Pine Script logic with built-in namespaces — ta.* (averages, oscillators, crossovers), strategy.* (orders, position info), request.* (multi-timeframe), math.*, str.*, array.*, color.*, bar state, symbol info.
typegpu
wushqd/framevideo
TypeGPU and raw WebGPU adapter patterns for FrameVideo. Use when creating GPU-rendered compositions with TypeGPU, raw WebGPU, WGSL fragment shaders, compute pipelines, liquid glass effects, particle systems, or any canvas layer driven by navigator.gpu that responds to FrameVideo fv-seek events.
book-rag-push
joshuashepherd/my-skills
>