Browse Skills — Page 101

dreidimensionale-marke

Klotzkette/claude-fuer-deutsches-recht

3D-Formmarken fuer Flakons und Schuhformen: § 3 II MarkenG technische Funktion, EuGH Louboutin C-163/16 (roter Sohlen-Absatz), EuG T-508/08 Lego (technisch bedingte Form). Unterscheidungskraft 3D-Zeichen, Verkehrsdurchsetzung Flakons. Laedt, wenn der Nutzer 'Formmarke', '3D-Marke', 'Flakon Marke', 'Schuhform Marke' oder 'dreidimensionale Marke' sagt.

drift

elophanto/EloPhanto

Complete Drift Protocol SDK for building perpetual futures, spot trading, and DeFi applications on Solana. Use when building trading bots, integrating Drift markets, managing positions, or working with vaults.

dringlichkeitsmarker

Klotzkette/claude-fuer-deutsches-recht

Erkennt Fristen und Eile-Signale in Mandantenanfragen: Hauptverhandlung naechste Woche, Kuendigungsfrist laeuft, Haftungsfalle, Zwangsvollstreckung, Insolvenzantrag. Setzt Dringlichkeitsstufe HOCH/MITTEL/NIEDRIG und markiert: Anwalt muss sofort anrufen statt auf E-Mail zu warten. Laedt wenn der Nutzer 'Dringlichkeit pruefen', 'Frist erkannt', 'Sofortmassnahme Mandant', 'Fristproblem Erstanfrage' oder 'Eilbedarf Anfrage' sagt.

drip-jobs-automation

ComposioHQ/awesome-claude-skills

"Automate Drip Jobs tasks via Rube MCP (Composio). Always search tools first for current schemas."

dripcel-automation

ComposioHQ/awesome-claude-skills

"Automate Dripcel tasks via Rube MCP (Composio). Always search tools first for current schemas."

drittlandstransfer-pruefung

Klotzkette/claude-fuer-deutsches-recht

Prueft Datenuebermittlungen in Drittlaender nach Art. 44 ff. DSGVO: Angemessenheitsbeschluesse (USA: EU-US Data Privacy Framework 2023, UK, Schweiz), Standardvertragsklauseln (SCC 2021 Module 1 bis 4), Transfer Impact Assessment nach EuGH C-311/18 Schrems II, BCR und Ausnahmen nach Art. 49 DSGVO.

drive-agent-personas

prisma/prisma-next

Library of agent personas — named bias-frames that other skills load to shift execution-time defaults. Skills name a persona by ID (e.g. "Adopt the architect persona"), and this skill resolves that ID to the persona doc that frames the executor for the rest of the task. Use when authoring a new skill that needs a particular reviewer/implementer/orchestrator stance, or when an existing skill instructs you to adopt a named persona.

drive-alliance-ma-and-strategic-investments

Significant-Gravitas/skills-catalog

Use when a partner could become equity or ownership: target screens, seven-lane diligence, the investment memo, and the corp-dev handoff.

drive-create-plan

prisma/prisma-next

>

drive-create-project

prisma/prisma-next

>

drive-create-spec

prisma/prisma-next

>

drive-discussion

prisma/prisma-next

Drops the agent into a structured Q&A mode that iterates with the user toward a complete understanding of a topic, then documents the outcome (project spec, plan, decision record, or whatever shape fits). The agent adopts one or more personas from the `drive-agent-personas` library — named explicitly by the user, or inferred from conversation context and announced. Typical use is design work at the start of a task, or mid-implementation when a load-bearing assumption has been falsified. Use ONLY when the user explicitly invokes this skill (e.g. "discussion mode", "pressure-test this", "let's design this", "design mode", "tech design mode", "product mode", "pm mode", "challenge my idea"). Never auto-invoke.

drive-motivation

wondelai/skills

Design motivation systems using Autonomy, Mastery, and Purpose (AMP) for products and teams. Use when the user mentions "intrinsic motivation", "gamification isnt working", "rewards arent working", "autonomy", "mastery", "purpose-driven", "my team is disengaged", or "how do I motivate people". Also trigger when designing onboarding progression, fixing broken gamification, or building team structures that sustain high performance. Covers why carrot-and-stick fails and how to build progress systems. For habit-forming product loops, see hooked-ux. For retention behavior design, see improve-retention.

drive-orchestrate-plan

prisma/prisma-next

>

drive-pr-description

prisma/prisma-next

Generates PR descriptions by analyzing git diffs between the current branch and the default branch. Use when the user requests a PR description, pull request summary, or commit message for a squash merge.

drive-pr-local-review

prisma/prisma-next

Generate local PR/branch review artifacts for the current branch vs its base — an in-repo canonical spec (if present) or an inferred review `spec.md`, plus `system-design-review.md`, `code-review.md`, and `walkthrough.md`. Multi-persona — adopts `tech-lead` as orchestrator, transitions to `architect` for the system-design pass, to `principal-engineer` for the code-review pass, then reloads `tech-lead` for the walkthrough and synthesis. Writes artifacts to disk (next to the in-repo spec when present, otherwise under `wip/`). Use when the user asks for a local PR/branch review, a code review, a system-design review, to "review this branch", or to produce written review docs. Do not modify implementation code.

drive-pr-walkthrough

prisma/prisma-next

Write an intent-first walkthrough (semantic narrative) of a PR/branch or commit range - the overall purpose, the sequence of conceptual steps, the concrete behavior changes, and links to both implementation touchpoints and tests as evidence. Use during branch/PR review when the user asks for a walkthrough, narrative of changes, semantic diff, intent of commits, or “what changed and why” (not a file-by-file diff recap).

drive9

vm0-ai/vm0-skills

drive9.ai network filesystem for AI agents with semantic search, auto-embedding, and tiered storage on top of db9 + S3. Use when the user wants agent-accessible files with natural-language search, zero-copy rename/copy, or persistent context across sessions.

driving-claude-code-sessions

obra/claude-session-driver

Use when acting as a project manager that delegates tasks to other coding-agent sessions (Claude Code, Codex, or Pi) - launch workers, assign them work, monitor progress, review their tool calls, and collect results

drizzle

bobmatnyc/claude-mpm-skills

Type-safe SQL ORM for TypeScript with zero runtime overhead

drizzle-migrations

bobmatnyc/claude-mpm-skills

Migration-first database development workflow using Drizzle ORM for TypeScript/J...

drizzle-orm

EpicenterHQ/epicenter

Drizzle ORM patterns: schema definitions, Drizzle Kit migrations, query builders, type branding, custom types, SQLite, Postgres, D1, and Turso/libSQL boundaries. Use when mentioning Drizzle, drizzle-orm, DB schemas, migrations, branded column types, or typed SQL queries.

drizzle-orm-expert

tranhieutt/software_development_department

Provides Drizzle ORM schema design, query patterns, migrations, and TypeScript integration for SQL databases. Use when working with Drizzle files (schema.ts, drizzle.config.ts) or when the user mentions Drizzle ORM or drizzle-kit.

drizzle-orm-expert-v2

diegosouzapw/awesome-omni-skills

Drizzle ORM Expert workflow skill. Use this skill when the user needs Expert in Drizzle ORM for TypeScript \u2014 schema design, relational queries, migrations, and serverless database integration. Use when building type-safe database layers with Drizzle and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

drizzle-orm-patterns

giuseppe-trisciuoglio/developer-kit

Provides comprehensive Drizzle ORM patterns for schema definition, CRUD operations, relations, queries, transactions, and migrations. Proactively use for any Drizzle ORM development including defining database schemas, writing type-safe queries, implementing relations, managing transactions, and setting up migrations with Drizzle Kit. Supports PostgreSQL, MySQL, SQLite, MSSQL, and CockroachDB.

drizzle-studio

TerminalSkills/skills

>-

drohende-zahlungsunfaehigkeit-paragraph-18-inso

Klotzkette/claude-fuer-deutsches-recht

§ 18 InsO drohende Zahlungsunfähigkeit: Prognosezeitraum 24 Monate, Wahrscheinlichkeitsmaßstab überwiegend wahrscheinlich, Abgrenzung zu § 17 InsO und § 19 InsO, Bedeutung als StaRUG-Zugangstor und Haftungsgrenze.

dromo-automation

ComposioHQ/awesome-claude-skills

"Automate Dromo tasks via Rube MCP (Composio). Always search tools first for current schemas."

drone-site-survey

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction

Process drone survey data for construction sites. Generate orthomosaics, DEMs, point clouds, calculate volumes, track progress, and integrate with BIM models for comparison.

droneci-migration

github/actions-migrations-via-copilot

Drone CI migration to GitHub Actions — syntax mappings and the migration report template for Pipelines, plugins, services, secrets, triggers, multi-platform pipelines. Load with `migration-core` when migrating Drone CI sources to GitHub Actions.

dropbox

zapier/connectors

Agent-callable Dropbox tools — upload, organize, find, and share files and folders. Use when the user wants to manage Dropbox content (save, move, search, share, list, or read files), including requests that don't name Dropbox explicitly, e.g. "save this report to my cloud storage" or "share that folder with Sam".

dropbox

obra/muse-skills

>-

dropbox-automation

benjaminasterA/antigravity-awesome-skills

Automate Dropbox file management, sharing, search, uploads, downloads, and folder operations via Rube MCP (Composio). Always search tools first for current schemas.

dropbox-automation-v2

diegosouzapw/awesome-omni-skills

Dropbox Automation via Rube MCP workflow skill. Use this skill when the user needs Automate Dropbox file management, sharing, search, uploads, downloads, and folder operations via Rube MCP (Composio). Always search tools first for current schemas and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.

dropbox-sign

vm0-ai/vm0-skills

Dropbox Sign (formerly HelloSign) API for electronic signatures. Use when user mentions "Dropbox Sign", "HelloSign", "e-signature", "send for signature", or "signature request".

dropbox-sign-automation

ComposioHQ/awesome-claude-skills

"Automate Dropbox Sign tasks via Rube MCP (Composio). Always search tools first for current schemas."

dropcontact-automation

ComposioHQ/awesome-claude-skills

"Automate Dropcontact tasks via Rube MCP (Composio). Always search tools first for current schemas."

dropshipping-product-research

nexscope-ai/eCommerce-Skills

Product research for dropshipping businesses. Identify profitable products with reliable suppliers, healthy margins, and manageable competition. Evaluates shipping times, return risk, and marketing viability.

drug_indication_mapping

InternScience/scp

Drug-Indication Mapping - Map drug indications: ChEMBL drug indications, FDA indications, OpenTargets drug associations, and literature. Use this skill for clinical informatics tasks involving get drug indication by id get indications by drug name get associated drugs by target name pubmed search. Combines 4 tools from 4 SCP server(s).

drug_metabolism_study

InternScience/scp

Drug Metabolism Study - Study drug metabolism: FDA metabolism data, ChEMBL metabolism records, PubChem compound data, and clinical pharmacology. Use this skill for drug metabolism tasks involving get metabolism by id get pharmacokinetics by drug name get compound by name get clinical pharmacology by drug name. Combines 4 tools from 3 SCP server(s).

drug_repurposing_screen

InternScience/scp

Drug Repurposing Screening - Screen existing drugs for new indications by querying FDA indications, ChEMBL mechanisms, and OpenTargets drug-disease associations. Use this skill for drug discovery tasks involving get indications by drug name get mechanism of action by drug name get drug by name get associated drugs by target name. Combines 4 tools from 3 SCP server(s).

drug_safety_profile

InternScience/scp

Comprehensive Drug Safety Profile - Build a complete drug safety profile by combining FDA adverse reactions, boxed warnings, drug interactions, and contraindications. Use this skill for pharmacology tasks involving get adverse reactions by drug name get boxed warning info by drug name get drug interactions by drug name get contraindications by drug name. Combines 4 tools from 1 SCP server(s).

drug_target_identification

InternScience/scp

Drug Target Identification Pipeline - Identify drug targets for a disease by querying OpenTargets for associated targets, then retrieve detailed target info from ChEMBL and protein data from UniProt. Use this skill for drug discovery tasks involving get associated targets by disease efoId get target by name get general info by protein or gene name. Combines 3 tools from 3 SCP server(s).

drug_target_structure

InternScience/scp

Drug-Target Structural Biology - Integrate drug and target structure: get drug from ChEMBL, target structure from PDB, dock them, and predict ADMET. Use this skill for structural pharmacology tasks involving get drug by name retrieve protein data by pdbcode quick molecule docking pred molecule admet. Combines 4 tools from 3 SCP server(s).

drug_warning_report

InternScience/scp

Drug Warning Intelligence Report - Generate drug warning report: ChEMBL drug warnings, FDA boxed warnings, adverse reactions, and environmental warnings. Use this skill for pharmacovigilance tasks involving get drug warning by id get boxed warning info by drug name get adverse reactions by drug name get environmental warning by drug name. Combines 4 tools from 2 SCP server(s).

drug-discovery

NousResearch/hermes-agent

>

drug-discovery-search

swaruplab/operon

End-to-end drug discovery platform combining ChEMBL compounds, DrugBank, targets, and FDA labels. Natural language powered by Valyu.

drug-interaction-checker

aipoch/medical-research-skills

Check for interactions between multiple medications, including severity classification and mechanism explanations.

drug-labels-search

swaruplab/operon

Search FDA drug labels with natural language queries. Official drug information, indications, and safety data via Valyu.

drug-photo

swaruplab/operon

Medication photo to personalised PGx dosage card via Claude vision — snap a pill, get genotype-informed guidance

drug-repurposing-study-planner

aipoch/medical-research-skills

Design evidence-discovery and validation workflows for drug repurposing studies by integrating disease mechanisms, drug-target logic, expression reversal, real-world evidence, and validation routes into a closed-loop study blueprint.

drug-screening-docking

InternScience/scp

Comprehensive drug screening pipeline from molecular filtering through QED/ADMET criteria to protein-ligand docking, identifying promising drug candidates.

drug-target-evidence-landscape

aipoch/medical-research-skills

Organizes the evidence and competitive landscape around a drug, target, or pathway by separating disease relevance, tractability, preclinical evidence, clinical evidence, modality fit, and crowding. Always map what is biologically supported, what is druggable, what has actually advanced, and what remains strategically open. Never confuse target relevance with druggability, preclinical activity with clinical promise, or narrative excitement with validated development maturity. Never fabricate references, trial status, approval status, company activity, or asset metadata.

drugbank-database

aipoch/medical-research-skills

Programmatic access to DrugBank drug and target data; use when you need to download, parse, and analyze DrugBank XML for properties, interactions, pathways, and pharmacology.

drugbank-database-access

jaechang-hits/SciAgent-Skills

Parse local DrugBank XML for drug info, interactions, targets, and properties. Search by ID/name/CAS, extract DDIs with severity, map targets/enzymes/transporters, compute SMILES similarity. Primary via local XML; REST API rate-limited (3k/month dev). For live bioactivity use chembl-database-bioactivity; for compound properties use pubchem-compound-search.

drugbank-search

swaruplab/operon

Search DrugBank comprehensive drug database with natural language queries. Drug mechanisms, interactions, and safety data powered by Valyu.

drugsda-admet

InternScience/scp

Predict the ADMET (absorption, distribution, metabolism, excretion, and toxicity) properties of the input molecules.

drugsda-compound-retrieve

InternScience/scp

Retrieve SMILES strings from PubChem using compound names.

drugsda-data-valid

InternScience/scp

Check if the input protein sequence or molecule SMILES string is valid.

drugsda-denovo-sampling

InternScience/scp

Generate new molecules de novo.

drugsda-dleps

InternScience/scp

Calculate disease reversal scores for the provided molecules relative to a specific disease.

drugsda-drug-likeness

InternScience/scp

Compute the drug-likeness metrics (QED score and Number of violations of Lipinski's Rule of Five) of the input candidate molecules (SMILES format).

drugsda-esmfold

InternScience/scp

Use ESMFold model to predict 3D structure of the input protein sequence.

drugsda-file-transfer

InternScience/scp

Implement data transmission between the local computer and the MCP Server using Base64 encoding

drugsda-linker-sampling

InternScience/scp

Generate new molecules sampling from the input two warhead fragments.

drugsda-mol-properties

InternScience/scp

Calculate different types of molecular properties based on SMILES strings, covering basic physicochemical properties, hydrophobicity, hydrogen bonding capability, molecular complexity, topological structures, charge distribution, and custom complexity metrics, respectively.

drugsda-mol-similarity

InternScience/scp

Compute the Tanimoto similarities between a target molecule and a list of candidate molecules using Morgan fingerprints.

drugsda-mol2mol-sampling

InternScience/scp

Generate new molecules sampling from the input molecule.

drugsda-p2rank

InternScience/scp

```python import json from mcp.client.streamable_http import streamablehttp_client from mcp import ClientSession

drugsda-peptide-sampling

InternScience/scp

Generate new peptide molecules sampling from the input peptide sequence.

drugsda-prosst

InternScience/scp

Given a protein sequence and its structure, employ ProSST model to predict mutation effects and obtain the top-k mutated sequences.

drugsda-rgroup-sampling

InternScience/scp

Generate new molecules sampling from the input scaffold.

drugsda-target-retrieve

InternScience/scp

Search the protein information from the input gene name and downloads the optimal PDB or AlphaFold structures.

drumbeat-automation-authoring

microsoft/amplifier-drumbeat

>-

drumbeat-drumpack-authoring

microsoft/amplifier-drumbeat

>-

drumbeat-operations

microsoft/amplifier-drumbeat

>-

ds-mapper

laolaoshiren/claude-code-skills-zh

项目目录结构地图 - 生成带说明的可视化目录树，快速理解任意代码库

dsa-art-34-systemische-risikobewertung

Klotzkette/claude-fuer-deutsches-recht

Skill zur jährlichen Risikobewertung nach Art. 34 DSA durch VLOPs und VLOSEs. Vier Risikoarten: illegale Inhalte; Grundrechte (insbesondere Würde Privatleben Datenschutz Diskriminierungsverbot Meinungsfreiheit Kinderrechte Verbraucherschutz); zivilgesellschaftlicher Diskurs Wahlen öffentliche Sicherheit; geschlechtsspezifische Gewalt Gesundheit Minderjährigenschutz physisches und psychisches Wohlbefinden. Methodik Berichtspflicht Audit-Schnittstelle.

dsa-art-40-forschungsdatenzugang-algorithmen

Klotzkette/claude-fuer-deutsches-recht

Skill zum Forschungsdatenzugang nach Art. 40 DSA. Drei Ebenen: Datenzugang für DSC und Kommission Abs. 1 bis 3; Zugang für vetted researchers Abs. 4 bis 8; öffentlich zugängliche Daten Abs. 12. Antragsverfahren über den DSC am Niederlassungsort. Delegierte VO (EU) 2024/2987 zu Bedingungen und Verfahren. Schutz von Geschäftsgeheimnissen Datenschutz und Sicherheit. Anwaltliche Begleitung beider Seiten.

dsa-vlop-vlose-einordnung-und-pflichten

Klotzkette/claude-fuer-deutsches-recht

Skill zur Einordnung als sehr große Online-Plattform (VLOP) oder sehr große Online-Suchmaschine (VLOSE) nach Art. 33 DSA. Schwellenwert 45 Mio. monatlich aktive Nutzer in der EU; halbjährliche Meldepflicht Art. 24 III DSA; Designation durch die Kommission; Pflichtenkatalog Art. 34 bis 43 DSA: Risikobewertung Audits Compliance-Funktion Transparenz Werbung Empfehlungssysteme Forschungsdatenzugang Krisenmechanismus.

dsar-response

anthropics/claude-for-legal

>

dsb-bestellungspflicht-pruefung

Klotzkette/claude-fuer-deutsches-recht

Pruefraster Bestellungspflicht Datenschutzbeauftragten. EU-Pflichten Art. 37 DSGVO oeffentliche Stelle Kerntaetigkeit umfangreiche regelmaessige Ueberwachung Kerntaetigkeit umfangreiche Verarbeitung besondere Kategorien. Deutsche Erweiterung § 38 BDSG ab 20 Personen die staendig mit automatisierter Verarbeitung beschaeftigt sind. Anforderungen DSB Art. 38 DSGVO Unabhaengigkeit Ressourcen-Pflicht Kenntnisse. Aufgaben Art. 39 DSGVO Beratung Pruefung. Externe vs. interne Bestellung. Interessens-Konflikt-Pruefung EuGH C-453/21 X-FAB Dresden zur Unvereinbarkeit von DSB-Funktion und leitender Verarbeitungs-Verantwortung. Bussgelder Art. 83 DSGVO bei Nicht-Bestellung. Meldung Aufsichtsbehoerde.

dse-loop

wanshuiyin/Auto-claude-code-research-in-sleep

Autonomous design space exploration loop for computer architecture and EDA. Runs a program, analyzes results, tunes parameters, and iterates until objective is met or timeout. Use when user says \"DSE\", \"design space exploration\", \"sweep parameters\", \"optimize\", \"find best config\", or wants iterative parameter tuning.

dsfa-erstellung

Klotzkette/claude-fuer-deutsches-recht

Datenschutz-Folgenabschätzung (DSFA) nach Art. 35 DSGVO erstellen: Schwellwertanalyse, BfDI-Blacklist-/Whitelist-Abgleich, strukturierte DSFA im eigenen Hausformat. Auslöser: Neues Verarbeitungsvorhaben, Systemeinführung, oder Ergebnis aus anwendungsfall-triage.

dsgvo-auskunft

Klotzkette/claude-fuer-deutsches-recht

Unterstützt bei der Bearbeitung von Auskunftsersuchen nach Art. 15 DSGVO – von der Identifizierung der betroffenen Person über Fristeinhaltung bis zur Formulierung der Auskunft und Prüfung von Ausnahmegründen. Lädt, wenn ein Mandant ein Auskunftsverlangen erhält oder stellen möchte.

dsgvo-auskunft-antwort

Klotzkette/claude-fuer-deutsches-recht

Bearbeitung von Betroffenenanfragen nach Art. 15–22 DSGVO: geführter Ablauf von Eingangsklassifikation über Identitätsprüfung und Systemabfrage bis zum Antwortentwurf. Fristen nach Art. 12 Abs. 3 DSGVO werden automatisch berechnet. Ausnahmen nach §§ 34 und 35 BDSG werden geprüft.

dsgvo-compliance-bausteine

Klotzkette/claude-fuer-deutsches-recht

Stellt datenschutzrechtliche Textbausteine für KI-Nutzungsrichtlinien bereit: Art. 2 Abs. 1, Art. 6, Art. 9, Art. 15, Art. 28 DSGVO; Auftragsverarbeitungsvertrag, Drittlandstransfer, Datenminimierung, Zweckbindung sowie Anonymisierung und Pseudonymisierung.

dsgvo-rechtswidriges-produkt

Klotzkette/claude-fuer-deutsches-recht

Prueft ob ein Produkt aus dem Ausland datenschutzrechtswidrig im Sinne der DSGVO ist: raeumlicher Anwendungsbereich Art. 3 DSGVO Erforderlichkeit Art. 5 Abs. 1 lit. c DSGVO Rechtsgrundlage Art. 6 DSGVO Einwilligung Art. 7 DSGVO Informationspflichten Art. 13 14 DSGVO Datenuebermittlung Drittlaender Art. 44 ff DSGVO automatisierte Entscheidung Art. 22 DSGVO biometrische Daten Art. 9 DSGVO. Relevant fuer Smartglasses Wearables IoT.

dspy

NousResearch/hermes-agent

DSPy: declarative LM programs, auto-optimize prompts, RAG.

dspy-adapters-multimodal

OmidZamani/dspy-skills

Use for DSPy adapter selection, JSONAdapter, XMLAdapter, ChatAdapter, native function calling, structured outputs, and multimodal inputs like dspy.Image or dspy.Audio.

dspy-advanced-module-composition

OmidZamani/dspy-skills

Use for composing DSPy modules with Ensemble, MultiChainComparison, ensemble voting, sequential pipelines, and multi-program workflows.

dspy-better-together

OmidZamani/dspy-skills

Use for BetterTogether, prompt plus weight optimization, fine-tuning sequences, and strategy chains like p -> w -> p.

dspy-bootstrap-fewshot

OmidZamani/dspy-skills

Use for BootstrapFewShot, bootstrapped demonstrations, teacher-model demos, and low-data DSPy prompt optimization.

dspy-custom-module-design

OmidZamani/dspy-skills

Use for creating custom DSPy modules, extending dspy.Module, reusable components, stateful modules, serialization, and module testing.

dspy-debugging-observability

OmidZamani/dspy-skills

Use for debugging DSPy programs, inspect_history, tracing LLM calls, custom callbacks, observability, monitoring, and cost tracking.

dspy-embedding-retrieval

OmidZamani/dspy-skills

Use for DSPy retrieval with dspy.Embedder, dspy.Embeddings, FAISS indexes, semantic search, and local or hosted embedding models.

dspy-evaluation-suite

OmidZamani/dspy-skills

Use for evaluating DSPy programs with Evaluate, answer_exact_match, SemanticF1, custom metrics, baselines, and program comparisons.

dspy-finetune-bootstrap

OmidZamani/dspy-skills

Use for BootstrapFinetune, fine-tuning DSPy models, teacher-student distillation, weight optimization, and lower-cost deployment.

dspy-gepa-reflective

OmidZamani/dspy-skills

Use for GEPA reflective optimization, ReAct agent optimization, feedback metrics, LLM reflection, and execution trajectories.

dspy-haystack-integration

OmidZamani/dspy-skills

Use for integrating DSPy with Haystack, optimizing Haystack prompts, improving retrieval pipelines, and extracting DSPy prompts.