imagera-photo-dump
Someone wants a set of casual, phone-style photos of one person (often an AI influencer) to post together. Use when: "Make a photo dump of my AI influencer", "Four casual Instagram photos of this person", "Candid phone photos of my character for a carousel", "photo dump", "photodump", "casual photos", "instagram dump". Runs the Imagera "Photo dump" template (four photos, about a minute).
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 1.6k
- Forks
- 491
01 前言 Front Matter
- name
- imagera-photo-dump
- description
- Someone wants a set of casual, phone-style photos of one person (often an AI influencer) to post together. Use when: "Make a photo dump of my AI influencer", "Four casual Instagram photos of this person", "Candid phone photos of my character for a carousel", "photo dump", "photodump", "casual photos", "instagram dump". Runs the Imagera "Photo dump" template (four photos, about a minute).
03 SKILL.md 正文
Photo dump
Four casual, phone-shot photos of the person in your photo, the kind posted together as a photo dump: a café table, a golden-hour street, a mirror selfie and a beach walk. Same face and style in each, ordinary light, nothing posed.
When to use
Someone wants a set of casual, phone-style photos of one person (often an AI influencer) to post together.
How to run it
- Ask for one clear photo of the person; the vibe of the set is optional.
- Only for the user themself, someone who agreed, or an invented character: never a real public figure, and never revealing or intimate imagery.
- For an account that posts often, offer the Character ID skill (/character-id) first so every set keeps the same face.
- Check every photo for drift in the face before handing it over, and re-run only the one that drifted.
Inputs
photo(image) — a clear photo of the personvibe(text, optional) — the vibe of the week
Steps
- Photos ×4
Run it through Imagera
Connect the Imagera MCP server (https://mcp.imagera.ai/mcp, sign in with your Imagera account), then:
run_skillwithskill_id: "photo-dump"and the inputs above,confirm: false— this returns the price in credits and starts nothing.- Show the price. Only after the person agrees, call
run_skillagain withconfirm: true. - Poll
check_skill_runwith the returnedrun_iduntil it finishes; hand over the result URLs. - Pictures of a saved Character, Object, Location or Outfit ID:
list_identitiesreturns each ID's sheet URL to pass as a reference image.
In Imagera itself, type /photo-dump in Superagent, or open it from https://imagera.ai/skills.
04 同仓库更多 Skills
worktable-review-with-annotations
Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.
worktable-find-and-synthesize-context
Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.
worktable-create-or-update-docs
Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.
worktable-create-or-manage-records
Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.
worktable-create-or-manage-interactive-html
Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.
worktable-collaborate-threads
Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.