Ready to supercharge your AI agents?

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

Safe Image Editor — measured AI agent skill | DecimalAI

stijnman/safe-image-editor

SkillScore68Maintained

Edits images with policy and quality guardrails. Use when modifying images o ruser says edit image, safe edit, adjust photo. Triggers: edit image, safe e dit, adjust photo, modify image.

by stijnman

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

Automatic

Design & UX Review pack

decimalai skills pull stijnman-safe-image-editor

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/stijnman-safe-image-editor/SKILL.md

Raw file: /s/stijnman-safe-image-editor/SKILL.md ↗ · machine-readable summary at /s/stijnman-safe-image-editor.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 — +36% lift-51% tokens0% turns68% of whole cases pass with skill (15/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	109%	0%
case-03	✗→✓	▲ Improved	41%	0%
case-05	✗→✓	▲ Improved	-56%	0%
case-09	✗→✓	▲ Improved	-47%	0%
case-10	✗→✓	▲ Improved	-38%	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/safe-image-editor/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

Safe Image Editor

When to Use

User says edit image or task matches this capability
User says safe edit or task matches this capability
User says adjust photo or task matches this capability
User says modify image or task matches this capability

Workflow

Load source image; confirm edit intent.
Run compliance-image-guard on edit plan.
Apply edit via image_edit or equivalent.
Show before/after; preserve original backup.

Integrations

imagine
compliance-image-guard
imagine-asset-generator

Error Handling

| Failure | Response | |---------|----------| | Edit failed | Retry with simpler edit scope. |

Gotchas

Never edit ID documents without HITL.

Example

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

Want to see if stijnman/safe-image-editor 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.