How do I install the Shotlist skill?

Run npx skillmds@latest add bendemartin97/shotlist in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Shotlist safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Shotlist?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Shotlist free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Shotlist?

bendemartin97 (@bendemartin97) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Shotlist by bendemartin97 — Agent Skill

Name: Shotlist
Author: bendemartin97

Shotlist

Builds a shoot plan from one or more scripts – a shotlist grouped by shoot economy, a props list, sequencing, and a time estimate. Use when a shoot day needs planning, a shotlist needs to be created, or several videos are being shot in one session.

File contents

Building the Shotlist

The most expensive mistake on a shoot day is resetting. So this plan sorts not by video, but by what can stay the same between two shots.

Approach

Collect all VISUAL fields from the provided scripts. If the scripts live in the connected task tool (e.g. Asana), pull them from there.
Tag each shot with four attributes: Location · Outfit · Setup · Light. Setup means camera position, height, lens, tripod or handheld.
Group by these attributes – biggest reset cost first: location beats outfit beats setup beats light.
Within a group, sort by sequence so continuity holds (food gets eaten, drinks run empty, hair falls out of place).
Check the order against daylight if shooting outdoors or by a window.

Output Format

# SHOTLIST · <Date>
VIDEOS: <n> · SHOTS: <n> · ESTIMATED: <h:mm>

## BLOCK 1 · <Location> · <Outfit> · <Setup>
Build: <what needs to be arranged> · <Minutes>

[ ] 1.1  <Video code> B2   <Shot>            <Minutes>
[ ] 1.2  <Video code> B4   <Shot>            <Minutes>
...
Reset to block 2: <what changes> · <Minutes>

Then two lists:

Props and material – everything that needs to be brought or prepared, grouped by block, flagging what needs to be sourced beforehand.

Do before the shoot – everything that must not happen on the shoot day itself: charging batteries, clearing memory cards, brewing coffee, ironing clothes, getting permits.

Make text cards – only if FORMATS.md describes them as a physical prop on set. If the cards only appear later as an overlay in the cut, they don't belong in the shotlist; don't list them at all in that case. If it's a real prop, list all texts verbatim and print-ready, grouped by video:

[ ] V1 Sign:  COLD BREW ≠ COLD COFFEE
[ ] V2 Sign:  What your grinder ruins first

Check the text length against the card surface as you go – anything that doesn't fit in two lines is too long for a sign and needs shortening before it's printed.

Time Estimate

Shot without spoken lines: 3 minutes
Shot with spoken lines: 6 minutes (two to three takes are the norm, not the exception)
Build per block: 10 minutes, 20 if the light changes
Reset between blocks: 5 minutes, estimate realistically for a location change
Add a 20 percent buffer to the total

State the sum without and with buffer separately. If the plan exceeds four hours of pure shooting time, say so clearly and suggest which videos should move to a second session – split along block boundaries, so no setup has to be built twice.

Continuity Check

Explicitly flag conflicts instead of silently planning around them:

Two videos in the same week with an identical outfit in the same setting – stands out in the timeline
A shot that assumes a state which an earlier shot destroys
Daylight shots that slip later in the schedule

---name: shotlistdescription: Builds a shoot plan from one or more scripts – a shotlist grouped by shoot economy, a props list, sequencing, and a time estimate. Use when a shoot day needs planning, a shotlist needs to be created, or several videos are being shot in one session.---# Building the ShotlistThe most expensive mistake on a shoot day is resetting. So this plan sorts **not by video**, but by what can stay the same between two shots.## Approach1. Collect all VISUAL fields from the provided scripts. If the scripts live in the connected task tool (e.g. Asana), pull them from there.2. Tag each shot with four attributes: **Location · Outfit · Setup · Light**. Setup means camera position, height, lens, tripod or handheld.3. Group by these attributes – biggest reset cost first: location beats outfit beats setup beats light.4. Within a group, sort by sequence so continuity holds (food gets eaten, drinks run empty, hair falls out of place).5. Check the order against daylight if shooting outdoors or by a window.## Output Format```# SHOTLIST · <Date>VIDEOS: <n> · SHOTS: <n> · ESTIMATED: <h:mm>## BLOCK 1 · <Location> · <Outfit> · <Setup>Build: <what needs to be arranged> · <Minutes>[ ] 1.1 <Video code> B2 <Shot> <Minutes>[ ] 1.2 <Video code> B4 <Shot> <Minutes>...Reset to block 2: <what changes> · <Minutes>```Then two lists:**Props and material** – everything that needs to be brought or prepared, grouped by block, flagging what needs to be **sourced beforehand**.**Do before the shoot** – everything that must not happen on the shoot day itself: charging batteries, clearing memory cards, brewing coffee, ironing clothes, getting permits.**Make text cards** – **only if `FORMATS.md` describes them as a physical prop on set.** If the cards only appear later as an overlay in the cut, they don't belong in the shotlist; don't list them at all in that case. If it's a real prop, list all texts verbatim and print-ready, grouped by video:```[ ] V1 Sign: COLD BREW ≠ COLD COFFEE[ ] V2 Sign: What your grinder ruins first```Check the text length against the card surface as you go – anything that doesn't fit in two lines is too long for a sign and needs shortening before it's printed.## Time Estimate- Shot without spoken lines: 3 minutes- Shot with spoken lines: 6 minutes (two to three takes are the norm, not the exception)- Build per block: 10 minutes, 20 if the light changes- Reset between blocks: 5 minutes, estimate realistically for a location change- Add a **20 percent buffer** to the totalState the sum without and with buffer separately. If the plan exceeds four hours of pure shooting time, say so clearly and suggest which videos should move to a second session – split along block boundaries, so no setup has to be built twice.## Continuity CheckExplicitly flag conflicts instead of silently planning around them:- Two videos in the same week with an identical outfit in the same setting – stands out in the timeline- A shot that assumes a state which an earlier shot destroys- Daylight shots that slip later in the schedule

Frequently asked questions