SKILLEMALL.ai
GitHub ↗ RU Sign in

CD gpt-image

Generate or edit images with GPT Image 2 or 2.5 through the packaged CLI and Reference Gallery. Use for image requests including imprecise 'GPT 2.5' model names, posters, typography, reference edits, and inpainting; resolve the model choice before generation.

wuyoscar/gpt_image_2_skill Agent Skills author: wuyoscar MIT 44 files · 1 script body ≈ 2 397 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Generate or edit images with GPT Image 2 or 2.5 through the packaged CLI and Reference Gallery. Use for image requests including imprecise 'GPT 2.5' model…

As a process D 47/100 · Unfinished process — References files that are not bundled: references/gallery-*.md

GeneratorAI and agentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
87/100
safety, quality, tests
Safety 60%
88
Quality 40%
85
Run on models
none yet
Process rating
D
47/100
Unfinished process
References files that are not bundled: references/gallery-*.md
Tools and files w 18
0
Result and completion w 14
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Instruction override medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.

For the author

An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.

Obfuscation medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 4

✓ No critical or high findings

Medium and low: 4
  • medium Instruction override en-ignore-previous references/craft.md:161
    Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition)
    - If illustrating prompt injection, quote the payload visibly as a harmless example string such as `<!-- IGNORE previous instructions... -->`, then label it `injected instructions` / `payload`.
    detector
  • medium Obfuscation obf-html-comment-instruction references/craft.md:161
    Hidden instruction inside an HTML comment (detector / deny-list definition)
    - If illustrating prompt injection, quote the payload visibly as a harmless example string such as `<!-- IGNORE previous instructions... -->`, then label it `injected instructions` / `payload`.
    detector
  • low Instruction override en-ignore-previous references/gallery-research-paper-figures.md:400
    Instruction-override phrase ("ignore previous instructions") (security demo / example; quoted — discussed, not commanded)
    COLUMN 3 "Third-party content (attack surface)": stacked boxes "Public Slack message" (slate gray), "Web page" (slate gray), and "Attacker-controlled document" (soft-terracotta fill, dashed border) co
    demoquoted
  • low Obfuscation obf-html-comment-instruction references/gallery-research-paper-figures.md:400
    Hidden instruction inside an HTML comment (security demo / example; quoted — discussed, not commanded)
    COLUMN 3 "Third-party content (attack surface)": stacked boxes "Public Slack message" (slate gray), "Web page" (slate gray), and "Attacker-controlled document" (soft-terracotta fill, dashed border) co
    demoquoted

Files scanned: 44. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/gallery-*.md

Process rating: all ten parameters 47/100

Will not run. References files that are not bundled: references/gallery-*.md
  • 0Tools and files. 1 referenced file(s) missing: references/gallery-*.md
  • 0Result and completion. Does not say what the result is
  • 0Progress reporting. Says nothing while it works
  • 30Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 3 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 85Steps. 36 steps, 1 vague phrases
  • 100Failures and branches. 2 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2397 tokens

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 259: enough signal without eating the budget
  • +4Structure: 9 headings
  • +3Step-by-step instructions: 36 items
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (10 of 41)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.