davinci-resolve-mcp: Skill for Claude Code

.agents/skills/house-style/SKILL.md

house-style is a skill for Claude Code from samuelgursky/davinci-resolve-mcp. It costs 55 tokens per session (665 once invoked), scanned A, original, MIT.

A project-specific guide to the editor's preferred choices for video cuts, including rhythm, shot selection, timing, and delivery conventions. It also records corrections so they can be applied consistently in later edits.

In plain words
What is it for?
Use it before assembling, restructuring, or refining a video cut, and update it when a correction represents a reusable preference rather than a one-off decision.
Why use it?
It prevents the same editorial preferences and corrections from having to be explained repeatedly. It turns subjective feedback into concrete rules that can be checked.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is samuelgursky/davinci-resolve-mcp's own configuration. It tells Claude Code how to work on davinci-resolve-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything davinci-resolve-mcp configures →

About the project

davinci-resolve-mcp is an MCP server that lets AI assistants control DaVinci Resolve Studio through its scripting API, including editing, media organization, rendering, grading, and other project tasks. It is for users who want agents to operate Resolve and inspect media through a local control panel. The catalogue entries support agent workflows for this Resolve integration.

samuelgursky/davinci-resolve-mcp · 2,701 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to samuelgursky/davinci-resolve-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/samuelgursky/davinci-resolve-mcp/main/.agents/skills/house-style/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/samuelgursky/davinci-resolve-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for house-style

README.md
[![agentmods](https://agentmods.dev/badge/skills/samuelgursky/davinci-resolve-mcp/house-style/github.svg)](https://agentmods.dev/skills/samuelgursky/davinci-resolve-mcp/house-style)
Your own site
<a href="https://agentmods.dev/skills/samuelgursky/davinci-resolve-mcp/house-style"><img src="https://agentmods.dev/badge/skills/samuelgursky/davinci-resolve-mcp/house-style/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for house-style

Your own site · 80×15
<a href="https://agentmods.dev/skills/samuelgursky/davinci-resolve-mcp/house-style"><img src="https://agentmods.dev/badge/skills/samuelgursky/davinci-resolve-mcp/house-style.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 665 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Prompt Injection · line 38
    Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
    Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
  • high Prompt Injection · line 50
    Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
    Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.00665
Opus 5 $0.00028 $0.00332
Sonnet 5 $0.00011 $0.00133
Haiku 4.5 $0.00006 $0.00067

Measured 13d ago against content hash 420e0e127350, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

house-style scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/house-style/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

House Style

The craft guides in docs/guides/ describe editing in general. This file describes how this editor wants it done — the accumulated, specific corrections that would otherwise have to be repeated every session.

Read it before any edit task. Append to it whenever a correction is given.

The capture protocol

This file is only worth what gets written into it. When the user corrects an editorial decision — rejects a cut, changes a shot choice, adjusts a duration, says "not like that" — do not just fix it. Fix it, then add the rule here.

A useful entry has three parts:

  • The rule, stated as an instruction, not an observation.
  • Why, in the user's terms — what it was in service of.
  • The trap, if there is one: what makes it easy to get wrong.

Write rules that are falsifiable. "Cut on motion" is a rule; "make it feel dynamic" is not. If a correction is one-off and situational, it does not belong here — this file is for what generalizes.

When an entry turns out to be wrong or too broad, edit it. A stale rule confidently followed is worse than no rule.


Pacing and rhythm

Not yet captured.

Shot selection

Not yet captured.

Cut points

Not yet captured.

Structure and openings

Not yet captured.

Rejected by default

Things not to add unless explicitly asked. Seeded from the rough-cut deliverable contract in the resolve-rough-cut skill, which exists because this work gets thrown away:

  • Titles, captions, and text cards
  • Transitions (an assembly is hard cuts)
  • Effects and speed ramps
  • Music beds
  • Grading on a cut that was asked for as an assembly

Delivery conventions

Read the full file on GitHub · 90 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 13d ago First seen · 90 lines · 55 tokens per session scan A 420e0e127350

Subscribe to this mod's changes

house-style is a skill published in the GitHub repository samuelgursky/davinci-resolve-mcp (2,701 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 665 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.