intertwine/dspy-agent-skills/dspy-advanced-workflow

Claude Code and agent skill by intertwine/dspy-agent-skills

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Build DSPy 3.2.x programs through spec, program, metric and baseline; extend to optimization and export when requested and justified by task budget. Orchestrates the other four DSPy skills (dspy-fundamentals, dspy-evaluation-harness, dspy-gepa-optimizer, dspy-rlm-module) in the correct order. Use for greenfield DSPy builds; prototypes may stop at a validated baseline.

Install

npx vskill@latest install intertwine/dspy-agent-skills/dspy-advanced-workflow

SKILL.md

DSPy Advanced Workflow (2026)

This skill runs the seven-step loop that turns a natural-language task description into an optimized, saved, deployable DSPy program. Use the relevant steps in order. Stop at a validated baseline for a prototype; optimizer runs require an appropriate authorized budget and evidence of need. Exporting a local artifact does not authorize deployment.

The seven steps

1. Spec

Rephrase the user's task in one sentence. Identify inputs, outputs, the quality axis that matters, and any constraints (latency, cost, tool access, context size). Pick predictor shape:

Task shapePredictor
Single-step structured I/Odspy.Predict / dspy.ChainOfThought
Tool use / multi-stepdspy.ReAct
Code executiondspy.ProgramOfThought
Long context / codebasedspy.RLM → dspy-rlm-module
2. Program

Write the typed dspy.Signature + dspy.Module subclass per dspy-fundamentals. No hard-coded prompts. Keep predictors named so GEPA can target them.

3. Data

Build trainset and separate valset as dspy.Example(...).with_inputs(...). For GEPA, maximize trainset size and keep validation just large enough to represent downstream behavior; held-out testset is reported on at the end only. See dspy-evaluation-harness.

4. Rich metric

Write rich_metric(gold, pred, trace=None, pred_name=None, pred_trace=None) returning dspy.Prediction(score=0..1, feedback="natural-language critique"). The feedback is load-bearing — it's what GEPA's reflection LM learns from. A dict with the same fields crashes dspy.Evaluate; only dspy.Prediction aggregates correctly. See dspy-evaluation-harness.

5. Baseline
python
evaluator = dspy.Evaluate(devset=valset, metric=rich_metric,
                          num_threads=8, display_progress=True,
                          provide_traceback=True,
                          save_as_json="runs/baseline.json")
baseline = evaluator(program)
print("Baseline:", baseline.score)
6. GEPA optimize
python
reflection_lm = dspy.LM("openai/gpt-5", temperature=1.0, max_tokens=32000)
optimizer = dspy.GEPA(
    metric=rich_metric,
    auto="medium",
    reflection_lm=reflection_lm,
    candidate_selection_strategy="pareto",
    track_stats=True,
    track_best_outputs=True,
    log_dir="./gepa_logs",
    num_threads=8,
    seed=0,
)
optimized = optimizer.compile(student=program, trainset=trainset, valset=valset)
print("Optimized:", evaluator(optimized).score)

Run auto="light" first as a sanity check; move to auto="medium"/"heavy" for the final run. See dspy-gepa-optimizer.

If you need a deliberate multi-stage compile loop, DSPy 3.2.x also exposes dspy.BetterTogether(metric=..., bootstrap=..., gepa=...) for chaining named optimizers after you have a clean baseline GEPA setup.

7. Export & deploy
python
optimized.save("artifacts/program.json", save_program=False)     # state, portable
# or for full deployment artifact:
optimized.save("artifacts/program_dir/", save_program=True)

Deploy:

  • Load with dspy.load("artifacts/program_dir/") or reconstruct + .load("program.json").
  • Wrap in FastAPI/CLI.
  • Enable track_usage=True for cost/latency observability.
  • Log with MLflow (mlflow.dspy.autolog()) or W&B in CI.
  • Keep an offline regression test that runs the evaluator against the saved program and fails CI below a threshold.

Full orchestration template

python
"""DSPy end-to-end pipeline — spec → optimize → deploy."""
import dspy
from pathlib import Path
# ----- 1–2. Spec & program (dspy-fundamentals) -----
class MyTask(dspy.Signature):
    """<one-line instruction from the spec>."""
    input_field: str = dspy.InputField()
    output_field: str = dspy.OutputField()
class MyProgram(dspy.Module):
    def __init__(self):
        super().__init__()
        self.step = dspy.ChainOfThought(MyTask)
    def forward(self, **kw):
        return self.step(**kw)
# ----- 3. Data (dspy-evaluation-harness) -----
trainset = [...]   # list[dspy.Example(...).with_inputs(...)]
valset   = [...]
# ----- 4. Rich metric (dspy-evaluation-harness) -----
def rich_metric(gold, pred, trace=None, pred_name=None, pred_trace=None):
    score = ...          # compute 0..1
    feedback = ...       # detailed critique
    return dspy.Prediction(score=score, feedback=feedback)  # NOT a dict
# ----- 5. Baseline -----
dspy.configure(lm=dspy.LM("openai/gpt-4o"), track_usage=True)
evaluator = dspy.Evaluate(devset=valset, metric=rich_metric, num_threads=8,
                          display_progress=True, provide_traceback=True,
                          save_as_json="runs/baseline.json")
program = MyProgram()
print("Baseline:", evaluator(program).score)
# ----- 6. GEPA optimize (dspy-gepa-optimizer) -----
optimizer = dspy.GEPA(
    metric=rich_metric,
    auto="medium",
    reflection_lm=dspy.LM("openai/gpt-5", temperature=1.0, max_tokens=32000),
    candidate_selection_strategy="pareto",
    track_stats=True, track_best_outputs=True,
    log_dir="./gepa_logs", num_threads=8, seed=0,
)
optimized = optimizer.compile(student=program, trainset=trainset, valset=valset)
print("Optimized:", evaluator(optimized).score)
# ----- 7. Export (dspy-fundamentals) -----
Path("artifacts").mkdir(exist_ok=True)
optimized.save("artifacts/program.json", save_program=False)

Guardrails

  • Define the metric in step 4 before optimization; use informative feedback appropriate to the task.
  • Always baseline before optimizing — no baseline, no claim.
  • Save both pre- and post-optimization metrics to JSON for auditability.
  • If held-out test score drops, preserve that result and diagnose using training/validation evidence rather than assuming a cause. After test-informed changes, use a new untouched final holdout or label subsequent results exploratory; do not repeatedly tune against the original test set.
  • Freeze optimized program with module._compiled = True before multi-stage re-compilation.

Runnable scaffold → example_pipeline.py

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

Repository stars
239
Repository forks
22
7-day trend score
27

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 23 May 2026, 5 months ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/intertwine/dspy-agent-skills/dspy-advanced-workflow/badge)](https://verified-skill.com/skills/intertwine/dspy-agent-skills/dspy-advanced-workflow)

Something wrong with this skill or its page? Tell us.