Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Dspy Prompt Optimizer — measured AI agent skill | DecimalAI

stijnman/dspy-prompt-optimizer

SkillScore82Maintained

Tunes prompts iteratively using reflection and success metrics. Use when the user says optimize this prompt, dspy tune, or improve prompt with reflectio n. Integrates self-refine-loop for critique cycles. Triggers: optimize this prompt, dspy tune, improve prompt with reflection.

by stijnman

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

AI Engineer pack

decimalai skills pull stijnman-dspy-prompt-optimizer

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/stijnman-dspy-prompt-optimizer/SKILL.md

Raw file: /s/stijnman-dspy-prompt-optimizer/SKILL.md ↗ · machine-readable summary at /s/stijnman-dspy-prompt-optimizer.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 7d ago

Yes — +23% lift-7% tokens0% turns82% of whole cases pass with skill (18/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-07	✗→✓	▲ Improved	-20%	0%
case-09	✗→✓	▲ Improved	-42%	0%
case-14	✗→✓	▲ Improved	1%	0%
case-15	✗→✓	▲ Improved	86%	0%
case-20	✗→✓	▲ Improved	-56%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

stijnman / grok-custom-skills

.grok/skills/dspy-prompt-optimizer/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

Dspy Prompt Optimizer

When to Use

User says optimize this prompt or task matches this capability
User says dspy tune or task matches this capability
User says improve prompt with reflection or task matches this capability

Workflow

Capture baseline prompt and 2-3 example inputs with desired outputs.
Run baseline; score outputs against criteria.
Generate 3 prompt variants addressing failures.
Test variants; pick best by score.
Return optimized prompt with before/after metrics.

Integrations

self-refine-loop
auto-tester
hyper-skill-tester

Error Handling

| Failure | Response | |---------|----------| | No examples | Ask for 2 input/output pairs minimum. | | Overfitting one example | Require 3+ diverse examples. |

Gotchas

Keep prompt under 2000 tokens unless user needs longer.

Example

Input: User request matching triggers above. Output: Structured result per workflow with integrations invoked as needed.

Want to see if stijnman/dspy-prompt-optimizer would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.