Agent skill

Resolve Delivery

by samuelgursky in samuelgursky/davinci-resolve-mcp

Delivery, rendering, and deliverable QC in the DaVinci Resolve MCP.

MITAuto-check passedAgent Workflows

Install Resolve Delivery

skills CLI
$ npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-delivery -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install samuelgursky/davinci-resolve-mcp resolve-delivery --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/samuelgursky/davinci-resolve-mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/resolve-delivery .claude/skills/resolve-delivery && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
resolve-delivery
GitHub stars
3.4k
Token cost
~2.1k tokens
SKILL.md length
937 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

Delivery, rendering, and deliverable QC in the DaVinci Resolve MCP.

  • Tasks that involve MCP servers
  • SKILL.md covers Two servers, Delivery targets (the short…, Live render essentials and Offline deliverable QC…, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Resolve Delivery is an agent skill from samuelgursky/davinci-resolve-mcp. Delivery, rendering, and deliverable QC in the DaVinci Resolve MCP. Apply when preparing render jobs, validating render settings, QCing a finished render against a spec (video/loudness/blanking/completeness), building or reconciling a render manifest, expanding texted/textless/stems/slate deliverables, verifying media ingest, or producing a provenance/episode report — live in a running Resolve OR offline against rendered files and the project DB. Routes to the live render tools, the offline…

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol. The repository describes itself as: MCP server integration for DaVinci Resolve Studio. The licence is MIT.

When your agent uses it

  • Tasks that involve MCP servers

Example prompts

  • “/resolve-delivery”

What it can do on your machine

Read from SKILL.md and the folder at commit 94c7a88. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Resolve Delivery loads about 2.1k tokens when it runs. Until then it costs about 146 tokens; SKILL.md has 937 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~146
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from samuelgursky/davinci-resolve-mcp at commit 94c7a88, republished under its MIT licence (© samuelgursky). 937 words, ~2,076 tokens.

Download SKILL.mdSave it as .claude/skills/resolve-delivery/SKILL.md (or your agent's skills folder).
name
resolve-delivery
description
Delivery, rendering, and deliverable QC in the DaVinci Resolve MCP. Apply when preparing render jobs, validating render settings, QCing a finished render against a spec (video/loudness/blanking/completeness), building or reconciling a render manifest, expanding texted/textless/stems/slate deliverables, verifying media ingest, or producing a provenance/episode report — live in a running Resolve OR offline against rendered files and the project DB. Routes to the live render tools, the offline deliverable/media/provenance tools, and the deliverables craft skills.

Resolve Delivery / Deliverable QC

Bridges delivery craft to this repo's tools.

  • Craft / specs — the global deliverables-knowledge, post-supervisor, and quality-control / qc-domain skills (distributor specs, mastering, QC discipline). Use for what the spec should be, not tool mechanics.
  • Live tool mechanics — docs/kernels/render-deliver-kernel.md (the render planning/validation boundary + Quick Export).
  • Offline deliverable QC — resolve-advanced/README.md → deliverable, media, provenance.

Two servers

JobServerTools
Plan / validate / run renders in a running Resolvedavinci-resolve (Python, live)render, render_presets
QC a finished render vs spec, verify ingest, build manifests/provenance with no Resolve opendavinci-resolve-advanced (Node)deliverable, media, provenance

Delivery targets (the short path)

Named render intents. list_delivery_targets → prepare_delivery_job(target, target_dir). Ask for prores422hq_master, dnxhr_hqx_master, h264_1080p_web, or an alias (youtube, tiktok, avid, stems). One definition emits BOTH the Resolve render settings and the deliverable_qc spec, so the returned qc_spec is what you QC the finished file against — do not hand-write a second spec.

  • Format/codec resolve against the live matrix. A target this machine or license cannot render fails with the available lists; it never silently substitutes. Use check_availability: true to see what this install supports.

  • Image-sequence targets return qc_spec: null — deliverable_qc probes one file, a sequence is many. That is expected, not a gap.

  • Bitrate is deliberately unset (Resolve has no bitrate key). Pin quality yourself via settings if a spec demands it.

  • Programme loudness is a separate projection. A target names a standard via overrides: {loudness_standard: "ebu_r128"}; resolve_delivery_target then returns a loudness_target alongside qc_spec. Hand loudness_target.target to advanced loudness_qc. render(action='list_loudness_standards') lists the five named contracts (web, podcast, ebu_r128, atsc_a85, ott_dialogue_gated) — cite one, never invent the numbers.

  • No shipped target names a loudness standard by default: a ProRes master has no inherent programme loudness and a broadcast handoff depends on territory. A loudness_note tells you when none is pinned.

  • Dialogue-gated standards emit no gradeable integrated. loudness_qc measures full-programme; grading a dialogue-gated figure against that means nothing. The number rides in meta for a properly gated meter and only true peak is asserted. This is deliberate, not a missing field.

Use the lower-level path below when you need something no target covers.

Live render essentials

  • Discover then validate then apply: probe_render_matrix (formats/codecs/res) → validate_render_settings → safe_set_render_settings (dry-run capable) → prepare_render_job (adds a job, does not start it).
  • Format AND codec accept display names or ids; both normalize against the live maps. A rejected pair is a hard error with the available codecs — it never queues a job in the previously set codec.
  • Render lifecycle helpers require temp output dirs by default; real delivery paths need explicit lower-level actions.
  • GetRenderSettings readback is version/page dependent — the kernel validates and applies through SetRenderSettings regardless.
  • safe_quick_export forces EnableUpload=False and needs allow_render=True before it actually renders.
  • Pin the base render state with prepare_render_job(from_preset=...). SetRenderSettings applies your keys on top of whatever the Deliver page is holding rather than replacing it, and a loaded preset carries more state than the keys you pass. An Audio Only preset plus an explicit ExportVideo: true has been measured to queue a job that reads back IsExportVideo: true and renders an mp4 with no video stream (issue #123). There is no way to detect this: the API documents neither GetRenderSettings nor GetCurrentRenderPresetName, so the inherited state cannot be read — only pinned. Verify the OUTPUT, not the job: ffprobe for a codec_type=video stream. A long timeline that "renders" in seconds is the tell.
  • Three render keys are 21.0.4+: UseFullExtents, AddFrameHandles, DataBurnIn (issue #131). SetRenderSettings ignores unknown keys silently, so on an older build these are dropped with no signal rather than refused — which is exactly the failure mode that produces a deliverable missing handles nobody notices until the conform. Check resolve_control check_version_support before offering them, and note AddFrameHandles is also ignored when full extents is enabled, so it can do nothing for two different reasons.
Show full SKILL.md (317 more words)Show less

Offline deliverable QC (deliverable actions)

Report-only, gate: review — never auto-pass-clear. Run these on the finished file, not the timeline:

  • deliverable_qc — ffprobe a render vs its spec → pass/fail per field.
  • loudness_qc — ebur128 LUFS / true-peak / LRA.
  • reframe_blanking_check — pillar/letterbox/blanking vs expected framing.
  • conform_completeness — every intended shot present in the delivered cut.
  • re_delivery_diff — what changed between two delivery versions.
  • render_manifest — build / reconcile the manifest of what was delivered.
  • expand_deliverable — derive texted / textless / stems / slate / leader entities from a master.
  • spec_from_authored — turn the authored deliverable vocabulary (codec display names, "1920x1080", "-16 LUFS", <SHOW>_<EP>_<YYYYMMDD>.mov naming) into a deliverable_qc spec plus a loudness_qc target. Anything it cannot map is listed in unmapped[] rather than dropped, so an unrecognized codec surfaces instead of quietly producing a spec with no codec check in it.

Two things that bite when hand-writing specs, both handled by the projections:

  • container is "mov" for both .mov and .mp4 — ffprobe reports format_name=mov,mp4,m4a,... for each and only the first token is kept. Use video.codec to tell them apart; a spec asserting container: "mp4" always fails.
  • Loudness is not a deliverable_qc field. It comes back as a separate loudnessTarget for loudness_qc.

Media front-end + provenance

  • media (front-end / AE): ingest_verify (hash seal / verify / dupes), media_inventory (fps/codec/colorspace/TC + card gaps), sync (picture↔sound TC + drift/MOS), relink_manifest, rename_plan (refuses camera originals) / reel_normalize, turnover_package, project_hygiene.
  • provenance (audit): grade_provenance ("why is this graded this way"), gallery_lineage, cdl_export / cdl_diff (round-trip asserted), revision_tracking, episode_report.

Gotchas

  • QC tools refuse rather than fabricate — a "refused" result means missing file, wrong spec, or a metric it cannot honestly compute; read it, don't retry blind. deliverable/media QC needs ffmpeg + ffprobe on PATH (GPL, not bundled) — call the advanced capabilities tool for live status + install hints.
  • Deliverable gates never auto-clear; surface the per-field verdict to a human.

Source-media safety (AGENTS.md)

Render probes may render derivatives of synthetic fixtures, never user source media. media.rename_plan refuses camera originals by design — do not override without explicit approval. Preserve the camera-original-to-delivery chain.

© samuelgursky, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/resolve-delivery of samuelgursky/davinci-resolve-mcp.

Open the folder on GitHubat commit 94c7a88

Compare with similar skills

Resolve Delivery next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Resolve Delivery compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Resolve Delivery this skillsamuelgursky/davinci-resolve-mcp3.4k—~2.1kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k4 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official38k11 repos~3.1kAutomated safety check: PassApache-2.0
Crush Configurationcharmbracelet/crush29k—~3.7kAutomated safety check: PassCustom licence
Context Mode Output Sandboxmksglu/context-mode26k—~4.1kAutomated safety check: PassCustom licence

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 4 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed
  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Context Mode Output Sandbox

    mksglu/context-mode

    Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.

    26k GitHub stars~4.1k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Migrates the compatible subset of settings and global file-based MCP servers from the Warp desktop app into Warp Agent CLI without exposing credentials or state.

    65k GitHub starsUsed in 1 repo~2.1k tokens
    Agent WorkflowsAuto-check passed

More from samuelgursky/davinci-resolve-mcp

All 14 skills in this repo
  • Resolve MCP

    samuelgursky/davinci-resolve-mcp

    Orientation and index for DaVinci Resolve MCP work — grading, editing, conforming, delivery, media analysis, and .drp/.drt/.drx file work, live in a running Resolve or offline with none open.

    3.4k GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed
  • Resolve Rough Cut

    samuelgursky/davinci-resolve-mcp

    Assembling a short-form social rough cut from raw behind-the-scenes or vlog footage in the DaVinci Resolve MCP.

    3.4k GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed
  • House Style

    samuelgursky/davinci-resolve-mcp

    The editorial and finishing preferences this project's work is judged against — cut rhythm, shot selection, delivery conventions, and the corrections that have already been given.

    3.4k GitHub stars~736 tokensUpdated yesterday
    Auto-check passed
  • Resolve Audio

    samuelgursky/davinci-resolve-mcp

    Audio and Fairlight work in the DaVinci Resolve MCP. An agent skill from samuelgursky/davinci-resolve-mcp.

    3.4k GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed
  • Resolve Color

    samuelgursky/davinci-resolve-mcp

    Color grading and look work in the DaVinci Resolve MCP. An agent skill from samuelgursky/davinci-resolve-mcp.

    3.4k GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed
  • Resolve Conform

    samuelgursky/davinci-resolve-mcp

    Conforming, relinking, and finishing prep in the DaVinci Resolve MCP.

    3.4k GitHub stars~2.1k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Resolve Delivery

What does Resolve Delivery do?

Delivery, rendering, and deliverable QC in the DaVinci Resolve MCP. Resolve Delivery is an agent skill from samuelgursky/davinci-resolve-mcp. Delivery, rendering, and deliverable QC in the DaVinci Resolve MCP.

When should I use Resolve Delivery?

Resolve Delivery fits situations like: tasks that involve MCP servers.

How do I install Resolve Delivery in Claude Code?

Run `npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-delivery -a claude-code`. Or copy the skill folder (.agents/skills/resolve-delivery in samuelgursky/davinci-resolve-mcp) into .claude/skills/resolve-delivery in your project. Claude Code loads it when a task matches its description.

How do I install Resolve Delivery in Codex?

Run `npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-delivery -a codex`. Or copy the skill folder (.agents/skills/resolve-delivery in samuelgursky/davinci-resolve-mcp) into .agents/skills/resolve-delivery in your project. Codex loads it when a task matches its description.

Can I use Resolve Delivery in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-delivery -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/resolve-delivery, .gemini/skills/resolve-delivery, .github/skills/resolve-delivery and .opencode/skills/resolve-delivery in your project.

What does Resolve Delivery need to run?

SKILL.md names no scripts, command-line tools or credentials: Resolve Delivery is instructions for the agent only.

Does Resolve Delivery access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Resolve Delivery safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Resolve Delivery use?

Resolve Delivery is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Resolve Delivery use?

About 2.1k tokens (SKILL.md is roughly 8.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Resolve Delivery?

Skills that share tags, products or a category with Resolve Delivery: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Crush Configuration (charmbracelet/crush, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Resolve Delivery?

samuelgursky (a GitHub user) maintains it in samuelgursky/davinci-resolve-mcp, which has 3,448 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 9, 2026.

Source: samuelgursky/davinci-resolve-mcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.