Ready to supercharge your AI agents?

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

Get Started Free →

DSPy Prompt Optimizer · stijnman | DecimalAI

ai mlby stijnman

DSPy Prompt Optimizer

stijnman/dspy-prompt-optimizer

Source stijnman/grok-custom-skills ↗License MIT

Tunes prompts iteratively using reflection and success metrics.

SkillScore68Maintained

Automatic

AI Engineer pack

Last verified 8/15/2026

What it changes

Passed 15 of 22 test cases with the skill, and 10 of 22 without it.

Without skill45%

With skill68%

Checks it passed that the model alone missed

Invokes the hyper-skill-tester integration.
Refuses execution until at least 2 input/output pairs are provided.
Invokes the self-refine-loop integration during prompt optimization.

and 4 more in the full report

7 fixed8 passed either way5 still failing2 broke

Pass-rate lift: +23 pp
Tokens: -25%
Agent turns: 0%
Response time: -37%

Model gemini-3.6-flashMeasured 8/15/2026v215 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/stijnman-dspy-prompt-optimizer/SKILL.md https://app.decimal.ai/s/stijnman-dspy-prompt-optimizer/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add stijnman-dspy-prompt-optimizer, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/stijnman-dspy-prompt-optimizer/ and pins it in .decimal/skills.lock

decimalai skills add stijnman-dspy-prompt-optimizer

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/stijnman-dspy-prompt-optimizer/SKILL.md 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 ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 7

Prompt

I want to run prompt optimization on my translation prompt using 3 provided input/output pairs. After capturing the baseline prompt and examples, what step must be executed next?

What was checked, without and with the skill
Checked	Without skill	With skill
Runs the baseline prompt against the examples and scores outputs against evaluation criteria.	Missed	Passed

case-04 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md36 linessingle file

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.

Track record

Benchmark

15 / 22

test cases passed, vs 10 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/15/2026

View 15 scanner checks

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 8/15/2026Version v2

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

DSPy Prompt Optimizer

When to Use

Workflow

Integrations

Error Handling

Gotchas

Example

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills