lebsral/dspy-programming-not-prompting-lms-skills

1

ai-stopping-hallucinations Stop your AI from making things up. Use when your AI hallucinates, fabricates facts, is not grounded in real data, do…

lebsral/dspy-programming-not-prompting-lms-skills

87

2

ai-switching-models Switch AI providers or models without breaking things. Use when you want to switch from OpenAI to Anthropic, try a ch…

lebsral/dspy-programming-not-prompting-lms-skills

61

3

ai-do Describe your AI problem and get routed to the right skill with a ready-to-use prompt. Use when you are not sure whic…

lebsral/dspy-programming-not-prompting-lms-skills

29

4

ai-reasoning Make AI solve hard problems that need planning and multi-step thinking. Use when your AI fails on complex questions, …

lebsral/dspy-programming-not-prompting-lms-skills

25

5

ai-building-chatbots Build a conversational AI assistant with memory and state. Use when you need a customer support chatbot, helpdesk bot…

lebsral/dspy-programming-not-prompting-lms-skills

24

6

ai-improving-accuracy Measure and improve how well your AI works. Use when AI gives wrong answers, accuracy is bad, responses are unreliabl…

lebsral/dspy-programming-not-prompting-lms-skills

24

7

ai-generating-data Generate synthetic training data when you do not have enough real examples. Use when you are starting from scratch wi…

lebsral/dspy-programming-not-prompting-lms-skills

22

8

ai-parsing-data Pull structured data from messy text using AI. Use when parsing invoices, extracting fields from emails, scraping ent…

lebsral/dspy-programming-not-prompting-lms-skills

22

9

ai-sorting Auto-sort, categorize, or label content using AI. Use when sorting tickets into categories, auto-tagging content, lab…

lebsral/dspy-programming-not-prompting-lms-skills

22

10

ai-fine-tuning Fine-tune models on your data to maximize quality and cut costs. Use when prompt optimization hit a ceiling, you need…

lebsral/dspy-programming-not-prompting-lms-skills

21

11

ai-scoring Score, grade, or evaluate things using AI against a rubric. Use when grading essays, scoring code reviews, rating can…

lebsral/dspy-programming-not-prompting-lms-skills

21

12

ai-taking-actions Build AI that takes actions, calls APIs, and does things autonomously. Use when you need AI to call APIs, use tools, …

lebsral/dspy-programming-not-prompting-lms-skills

21

13

ai-fixing-errors Fix broken AI features. Use when your AI is throwing errors, producing wrong outputs, crashing, returning garbage, no…

lebsral/dspy-programming-not-prompting-lms-skills

20

14

ai-following-rules Make your AI follow rules and policies. Use when your AI breaks format rules, violates content policies, ignores busi…

lebsral/dspy-programming-not-prompting-lms-skills

20

15

ai-monitoring Know when your AI breaks in production. Use when you need to monitor AI quality, track accuracy over time, detect mod…

lebsral/dspy-programming-not-prompting-lms-skills

20

16

ai-testing-safety Find every way users can break your AI before they do. Use when you need to red-team your AI, test for jailbreaks, fi…

lebsral/dspy-programming-not-prompting-lms-skills

20

17

ai-writing-content Generate articles, reports, blog posts, or marketing copy with AI. Use when writing blog posts, creating product desc…

lebsral/dspy-programming-not-prompting-lms-skills

20

18

ai-kickoff Scaffold a new AI feature powered by DSPy. Use when adding AI to your app, starting a new AI project, building an AI-…

lebsral/dspy-programming-not-prompting-lms-skills

19

19

ai-querying-databases Build AI that answers questions about your database. Use when you need text-to-SQL, natural language database queries…

lebsral/dspy-programming-not-prompting-lms-skills

19

20

ai-searching-docs Build AI that searches your documents and answers questions.

lebsral/dspy-programming-not-prompting-lms-skills

19

21

ai-serving-apis Put your AI behind an API. Use when you need to serve AI features as web endpoints, add AI to an existing backend, de…

lebsral/dspy-programming-not-prompting-lms-skills

19

22

ai-tracing-requests See exactly what your AI did on a specific request. Use when you need to debug a wrong answer, trace a specific AI re…

lebsral/dspy-programming-not-prompting-lms-skills

19

23

ai-tracking-experiments Track which optimization experiment was best. Use when you have run multiple optimization passes, need to compare exp…

lebsral/dspy-programming-not-prompting-lms-skills

19

24

ai-making-consistent Make your AI give the same answer every time. Use when AI gives different answers to the same question, outputs are u…

lebsral/dspy-programming-not-prompting-lms-skills

18

25

ai-moderating-content Auto-moderate what users post on your platform. Use when you need content moderation, flag harmful comments, detect s…

lebsral/dspy-programming-not-prompting-lms-skills

18

26

ai-summarizing Condense long content into short summaries using AI. Use when summarizing meeting notes, condensing articles, creatin…

lebsral/dspy-programming-not-prompting-lms-skills

18

27

ai-decomposing-tasks Break a failing complex AI task into reliable subtasks. Use when your AI works on simple inputs but fails on complex …

lebsral/dspy-programming-not-prompting-lms-skills

16

28

ai-building-pipelines Chain multiple AI steps into one reliable pipeline. Use when your AI task is too complex for one prompt, you need to …

lebsral/dspy-programming-not-prompting-lms-skills

15

29

ai-checking-outputs Verify and validate AI output before it reaches users. Use when you need guardrails, output validation, safety checks…

lebsral/dspy-programming-not-prompting-lms-skills

15

30

ai-coordinating-agents Build multiple AI agents that work together. Use when you need a supervisor agent that delegates to specialists, agen…

lebsral/dspy-programming-not-prompting-lms-skills

15

31

ai-request-skill Request or contribute a new AI skill that does not exist yet.

lebsral/dspy-programming-not-prompting-lms-skills

15

32

ai-cutting-costs Reduce your AI API bill. Use when AI costs are too high, API calls are too expensive, you want to use cheaper models,…

lebsral/dspy-programming-not-prompting-lms-skills

13

33

dspy-data Prepare training and dev data for DSPy - loading from CSV/JSON/HuggingFace, creating dspy.Example objects, setting in…

lebsral/dspy-programming-not-prompting-lms-skills

10

34

dspy-chain-of-thought Use when the task benefits from intermediate reasoning before producing an answer — multi-step logic, analysis, math,…

lebsral/dspy-programming-not-prompting-lms-skills

8

35

dspy-utils DSPy utility functions for caching control, debugging with inspect_history, saving/loading optimized programs, and ru…

lebsral/dspy-programming-not-prompting-lms-skills

8

36

dspy-adapters Use when you need to customize how DSPy formats prompts for a specific provider — switching from chat to completion f…

lebsral/dspy-programming-not-prompting-lms-skills

7

37

dspy-evaluate Run dspy.Evaluate to score DSPy programs against labeled examples using custom or built-in metrics. Use when you need…

lebsral/dspy-programming-not-prompting-lms-skills

7

38

dspy-gepa Optimize instructions in DSPy programs via reflective evolution using dspy.GEPA without adding few-shot examples. Use…

lebsral/dspy-programming-not-prompting-lms-skills

7

39

dspy-labeled-few-shot Attach hand-curated labeled examples as few-shot demonstrations using dspy.LabeledFewShot — no bootstrapping, no metr…

lebsral/dspy-programming-not-prompting-lms-skills

7

40

dspy-lm Use when you need to configure which language model DSPy uses — setting up providers, API keys, model parameters, or …

lebsral/dspy-programming-not-prompting-lms-skills

7

41

dspy-modules Build multi-step DSPy programs as composable, optimizable modules using dspy.Module and forward(). Use when composing…

lebsral/dspy-programming-not-prompting-lms-skills

7

42

dspy-multi-chain-comparison Use when you want higher accuracy by generating multiple reasoning chains and selecting the best answer — trading spe…

lebsral/dspy-programming-not-prompting-lms-skills

7

43

dspy-parallel Use when you have independent LM calls that can run concurrently — batch processing, fan-out patterns, or speeding up…

lebsral/dspy-programming-not-prompting-lms-skills

7

44

dspy-predict Build fast direct LM calls with dspy.Predict - the atomic DSPy module for simple input-to-output mapping with no reas…

lebsral/dspy-programming-not-prompting-lms-skills

7

45

dspy-primitives DSPy typed wrappers (dspy.Image, dspy.Audio, dspy.Code, dspy.History, dspy.File, dspy.Reasoning, dspy.Tool, dspy.Tool…

lebsral/dspy-programming-not-prompting-lms-skills

7

46

dspy-react Build tool-using agents with dspy.ReAct - the Reasoning-Action-Observation loop for interleaved thinking and action. …

lebsral/dspy-programming-not-prompting-lms-skills

6

47

dspy-rlm Recursive Language Model (dspy.RLM) that explores large contexts via a sandboxed Python REPL -- the LM writes code, q…

lebsral/dspy-programming-not-prompting-lms-skills

6

48

dspy-signatures Defines typed input/output contracts for LM calls using dspy.Signature, dspy.InputField, and dspy.OutputField. Use wh…

lebsral/dspy-programming-not-prompting-lms-skills

6

49

dspy-simba Optimize a DSPy program in small conservative steps using dspy.SIMBA (Stochastic Introspective Mini-Batch Ascent). Us…

lebsral/dspy-programming-not-prompting-lms-skills

6

50

dspy-tools Wraps Python functions as dspy.Tool objects and configures dspy.PythonInterpreter for sandboxed code execution in DSP…

lebsral/dspy-programming-not-prompting-lms-skills

6