MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
Conforming, relinking, and finishing prep in the DaVinci Resolve MCP.
$ npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-conform -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install samuelgursky/davinci-resolve-mcp resolve-conform --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ 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-conform .claude/skills/resolve-conform && rm -rf skills-srcUse ~/.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/
Install the "resolve-conform" agent skill from https://github.com/samuelgursky/davinci-resolve-mcp/tree/main/.agents/skills/resolve-conform into .claude/skills/resolve-conform/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve-conform", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/samuelgursky/davinci-resolve-mcp/tree/main/.agents/skills/resolve-conformType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-conform -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install samuelgursky/davinci-resolve-mcp resolve-conform --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/samuelgursky/davinci-resolve-mcp.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/resolve-conform .agents/skills/resolve-conform && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "resolve-conform" agent skill from https://github.com/samuelgursky/davinci-resolve-mcp/tree/main/.agents/skills/resolve-conform into .agents/skills/resolve-conform/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve-conform", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-conform -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install samuelgursky/davinci-resolve-mcp resolve-conform --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/samuelgursky/davinci-resolve-mcp.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/resolve-conform .cursor/skills/resolve-conform && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "resolve-conform" agent skill from https://github.com/samuelgursky/davinci-resolve-mcp/tree/main/.agents/skills/resolve-conform into .cursor/skills/resolve-conform/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve-conform", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/samuelgursky/davinci-resolve-mcp.git --path .agents/skills/resolve-conform--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-conform -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install samuelgursky/davinci-resolve-mcp resolve-conform --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/samuelgursky/davinci-resolve-mcp.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/resolve-conform .gemini/skills/resolve-conform && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "resolve-conform" agent skill from https://github.com/samuelgursky/davinci-resolve-mcp/tree/main/.agents/skills/resolve-conform into .gemini/skills/resolve-conform/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve-conform", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install samuelgursky/davinci-resolve-mcp resolve-conformInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-conform -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/samuelgursky/davinci-resolve-mcp.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/resolve-conform .github/skills/resolve-conform && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "resolve-conform" agent skill from https://github.com/samuelgursky/davinci-resolve-mcp/tree/main/.agents/skills/resolve-conform into .github/skills/resolve-conform/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve-conform", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-conform -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install samuelgursky/davinci-resolve-mcp resolve-conform --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/samuelgursky/davinci-resolve-mcp.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/resolve-conform .opencode/skills/resolve-conform && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "resolve-conform" agent skill from https://github.com/samuelgursky/davinci-resolve-mcp/tree/main/.agents/skills/resolve-conform into .opencode/skills/resolve-conform/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resolve-conform", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
resolve-conformConforming, relinking, and finishing prep in the DaVinci Resolve MCP.
Resolve Conform is an agent skill from samuelgursky/davinci-resolve-mcp. Conforming, relinking, and finishing prep in the DaVinci Resolve MCP. Apply when importing/relinking editorial, checking a conform against a reference, repairing reversed/retimed subclips, tracing grades across a re-conform, building relink plans, or QCing a conformed timeline frame-by-frame — live in a running Resolve OR offline against .drt/.drp files and the project DB. Routes to the live conform tools, the offline conform QC engine, and the online-editor craft skill.
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.
2 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 94c7a88. It shows what the files ask for, not the result of running them.
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.
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.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Resolve Conform loads about 2.1k tokens when it runs. Until then it costs about 123 tokens; SKILL.md has 987 words of instructions outside code blocks.
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.
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.
The full file from samuelgursky/davinci-resolve-mcp at commit 94c7a88, republished under its MIT licence (© samuelgursky). 987 words, ~2,127 tokens.
.claude/skills/resolve-conform/SKILL.md (or your agent's skills folder).Bridges online-editing / finishing craft to this repo's tools.
online-editor skill (conform, relink,
finishing philosophy in Resolve and Flame). Use for how a finishing editor
thinks, not tool mechanics.docs/kernels/timeline-conform-interchange-kernel.md
(the timeline conform/interchange boundary).resolve-advanced/README.md → conform,
color_trace, offline_ref, editorial, drt, project_db.timeline author_offline writes an importable timeline (drt / otio / edl) from a
file-path clip plan without any connection, and every not-connected error now carries an
offline_alternative block pointing at it.
Say plainly what happened: the live operation failed and a file was written — the
timeline is not in a project until someone imports it. Read the warnings back too.
media_tc_origin_assumed is the one that matters: OTIO source frames are
timecode-absolute, and an event without media_start_tc_frame imports as an empty
timeline with no error at all.
Default to drt (Resolve-native, project version 17 / Resolve 21.0 — older builds need
drt downgrade). Pick otio when the plan carries retimes; a .drt flattens them.
| Job | Server | Tools |
|---|---|---|
| Import / relink / compare a running conform | davinci-resolve (Python, live) | timeline (conform actions), media_pool (safe_relink, safe_import_sequence) |
Conform QC math, reverse-clip repair, lineage, grade tracing, .drt/.drp/DB edits with no Resolve open | davinci-resolve-advanced (Node) | conform, color_trace, offline_ref, editorial, drt, project_db |
The scripting API changes per patch release, so "Resolve 21" is not a usable
label. Read resolve_control get_version → build.unavailable_on_this_build
before offering a gated surface; check_version_support asks about one named
symbol. Gated on the relink/media side this domain leans on:
| Surface | Needs | If absent |
|---|---|---|
MediaPoolItem.LinkProxyMedia | 17.0 | No script-side proxy attach |
MediaPoolItem.LinkFullResolutionMedia | 20.0 | Cannot swap proxies back to full-res from a script |
MediaPoolItem.ReplaceClipPreserveSubClip | 20.0 | Replacing a clip loses sub-clip boundaries; relink by path instead |
MediaPoolItem.MonitorGrowingFile | 20.0 | No growing-file support during ingest |
MediaPoolItem.GetTimeline | 21.0.4 | Cannot ask a clip which timelines use it; walk timelines and collect their items instead |
An empty unavailable_on_this_build means nothing recorded is missing, not
that everything exists — most of the API has never been version-bisected. A
symbol with no gate returns unknown, which means probe it. Probe with
name in dir(obj), never bare hasattr: on a Resolve object hasattr returns
True for every name, real or invented, so it can only say yes.
The offline conform / drt / project_db routes are not gated this way —
they operate on files, so a missing live surface is a reason to reach for them,
not a dead end.
probe_timeline_structure, detect_gaps_overlaps,
source_range_report, conform_boundary_report.export_timeline_checked / import_timeline_checked (temp-guarded).
drt is the only lossless project-native round-trip; EDL/FCPXML drop
Resolve-specific relationships.import_timeline_checked with media sanitize
(FCP7/FCPXML) so the API imports with links intact, then exact-path relink.
A running MCP server must be restarted to pick up the sanitize fix.detect_missing_media → build_relink_plan (read-only, bounded;
skips broad scans when the source volume is unmounted) → execute only via
media_pool.safe_relink with approved paths.conform actions)The offline engine QCs a conform with frame-oracle math, not filename matching — it catches a clip that relinked to the wrong-but-similarly-named source. It also does:
source_start =
masterFrames − 1 − endoffset (live-validated); DB-level repair.-1 edges resolved
to junctions and its absent pproTicksIn tolerated (<in> is the source frame).REF_OFFLINE verdict when a burn-in-free
reference exists.Native ColorTrace keys on timecode/name/order inside one project and gives up on renames, reorders, retimes and stringouts. The MCP path is two calls:
color_trace plan with
sourceProjectName/sourceTimeline (graded) and targetProjectName/targetTimeline
(the new cut), plus emitDir under the system temp dir. Projects in a Postgres /
network / cloud library have no Project.db to open: export each with
project_manager safe_project_export (allow_non_mcp_name: true, works without
loading the project) and pass sourceDrp / targetDrp instead. It matches on media
identity (pool id / file path / reel / file name + source-range overlap — a
stringout's graded sections resolve by overlap) and only falls back to names.
Read summary.byMethod, ambiguous, and each match's confidence; it writes a
lossless .drx per graded match and returns planPath.timeline_item_color apply_trace_plan with plan_path and dry_run: true to
get the resolution table (every entry is apply or skip + reason). Re-call
without dry_run for a confirm_token, then with it to apply. version_name
adds a local version per clip first so the previous grade survives; the
timeline is archived to the Archive bin before anything is replaced.Say plainly what did not resolve: live_item_not_found, ambiguous_live_item
and below_min_confidence entries are reported, never guessed. For a single look,
the resolve-color skill's drx grade_transfer is the lighter tool. For "what
changed between cuts," use editorial.turnover_changelist (see resolve-edit).
Offline-ref clips have no scripting API but do live inside .drp/.drt as
<OfflineClip> entries — patch via offline_ref (plain-XML/DB path), not the
live server.
.drt version. For DaVinci Resolve 19.1.3, set DbPrjVer 17 → 16 when
authoring a .drt or the import can fail.project_db patches require the project CLOSED in Resolve plus
iConfirmProjectClosed:true; every write auto-backs-up and read-back verifies.
Resolve caches open projects in memory — after patching, fully QUIT and
relaunch Resolve or the change is invisible.editorial.parse_interchange, not a silent
empty result.better-sqlite3 for lineage/reverse/DB,
sharp/ffmpeg for frame compare) — call the advanced capabilities tool.Relink plans are read-only until you execute them; never relink, replace, or create derivatives of source media without explicit approval. Preserve the chain from camera original to final delivery.
© samuelgursky, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .agents/skills/resolve-conform of samuelgursky/davinci-resolve-mcp.
Open the folder on GitHubat commit 94c7a88
Resolve Conform 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Resolve Conform this skillsamuelgursky/davinci-resolve-mcp | 3.4k | — | ~2.1k | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server BuildershareAI-lab/learn-claude-code | 78k | 4 repos | ~1.2k | Automated safety check: Pass | MIT | |
| MCP Integration for Pluginsanthropics/claude-plugins-official | 38k | 11 repos | ~3.1k | Automated safety check: Pass | Apache-2.0 | |
| Crush Configurationcharmbracelet/crush | 29k | — | ~3.7k | Automated safety check: Pass | Custom licence | |
| Context Mode Output Sandboxmksglu/context-mode | 26k | — | ~4.1k | Automated safety check: Pass | Custom licence |
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
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.
anthropics/claude-plugins-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.
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.
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.
warpdotdev/warp
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.
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.
samuelgursky/davinci-resolve-mcp
Assembling a short-form social rough cut from raw behind-the-scenes or vlog footage in the DaVinci Resolve MCP.
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.
samuelgursky/davinci-resolve-mcp
Audio and Fairlight work in the DaVinci Resolve MCP. An agent skill from samuelgursky/davinci-resolve-mcp.
samuelgursky/davinci-resolve-mcp
Color grading and look work in the DaVinci Resolve MCP. An agent skill from samuelgursky/davinci-resolve-mcp.
samuelgursky/davinci-resolve-mcp
Delivery, rendering, and deliverable QC in the DaVinci Resolve MCP.
Works with
Categories
Conforming, relinking, and finishing prep in the DaVinci Resolve MCP. Resolve Conform is an agent skill from samuelgursky/davinci-resolve-mcp. Conforming, relinking, and finishing prep in the DaVinci Resolve MCP.
Resolve Conform fits situations like: tasks that involve MCP servers.
Run `npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-conform -a claude-code`. Or copy the skill folder (.agents/skills/resolve-conform in samuelgursky/davinci-resolve-mcp) into .claude/skills/resolve-conform in your project. Claude Code loads it when a task matches its description.
Run `npx skills add samuelgursky/davinci-resolve-mcp --skill resolve-conform -a codex`. Or copy the skill folder (.agents/skills/resolve-conform in samuelgursky/davinci-resolve-mcp) into .agents/skills/resolve-conform in your project. Codex loads it when a task matches its description.
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-conform -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-conform, .gemini/skills/resolve-conform, .github/skills/resolve-conform and .opencode/skills/resolve-conform in your project.
SKILL.md names no scripts, command-line tools or credentials: Resolve Conform is instructions for the agent only.
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.
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.
Resolve Conform is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.1k tokens (SKILL.md is roughly 8.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Resolve Conform: 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.
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.