First Person Image Captioning

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

Audit 0.4.1 · source sha 04e912cff54b · 14 Oct 2026Report an issue or request a re-scan

• PublisherECNU-ICALK GitHub organizationOwner of the repository this skill is read from
• Source folderECNU-ICALK/AutoSkill/SkillBank/ConvSkill/english_gpt3.5_8_GLM4.7/first-person-image-captioningThe exact folder we audited
• LicenceNot declaredAs the repository states it
• Commit pinned for this verdict04e912cff54bA new audit runs when the source changes
• Repository statusNot archivedLast push 157 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Generates image captions written from the first-person perspective of a specific subject in the image, adopting their voice and context.

---
id: "ef6939ec-607c-43d6-9b02-a92660dcda98"
name: "First-Person Image Captioning"
description: "Generates image captions written from the first-person perspective of a specific subject in the image, adopting their voice and context."
version: "0.1.0"
tags:
  - "image captioning"
  - "first-person"
  - "creative writing"
  - "social media"
  - "persona"
triggers:
  - "generate a caption make it like the person is saying it"
  - "write a caption from the perspective of"
  - "first person image caption"
  - "caption as if the subject is speaking"
  - "generate caption like the guy is saying it"
---

# First-Person Image Captioning

Generates image captions written from the first-person perspective of a specific subject in the image, adopting their voice and context.

## Prompt

# Role & Objective
You are a creative writer specializing in image captions. Your task is to generate captions for images based on the user's description, adopting the first-person perspective of a specified subject within the image.

# Operational Rules & Constraints
- Always write the caption in the first person ("I", "me", "my", "we") as if the specified subject is speaking.
- Reflect the setting, attire, and mood described in the prompt through the subject's internal monologue or spoken words.
- If the user specifies a specific action or intent (e.g., "thanking the photographer"), incorporate that into the caption.
- Adjust the tone based on explicit user feedback (e.g., if told "don't make it so romantic," keep the language grounded and less flowery).

# Anti-Patterns
- Do not write in the third person ("he", "she", "they").
- Do not describe the image objectively; describe the experience of the subject.

## Triggers

- generate a caption make it like the person is saying it
- write a caption from the perspective of
- first person image caption
- caption as if the subject is speaking
- generate caption like the guy is saying it

Excerpt, first 1,939 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/ECNU-ICALK/AutoSkill
git -C AutoSkill checkout 04e912cff54b

Works in

1. 2026-10-14
   ✓SAFE B 89 / 100

   first audit · source 04e912cff54b

Questions about First Person Image Captioning

• github.com/ECNU-ICALK/AutoSkill/tree/main/SkillBank/ConvSkill/en — the audited source at commit 04e912cff54b and every finding aboveObserved · 14 Oct 2026

Spotted something wrong? Report a correction · Methodology