Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add flamexnreal/davinci-resolve-ai-bridge-mcp --skill resolve-ai-editinggit clone --depth 1 https://github.com/flamexnreal/davinci-resolve-ai-bridge-mcpWrote 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.
[](https://agentmods.dev/skills/flamexnreal/davinci-resolve-ai-bridge-mcp/resolve-ai-editing)<a href="https://agentmods.dev/skills/flamexnreal/davinci-resolve-ai-bridge-mcp/resolve-ai-editing"><img src="https://agentmods.dev/badge/skills/flamexnreal/davinci-resolve-ai-bridge-mcp/resolve-ai-editing/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.
<a href="https://agentmods.dev/skills/flamexnreal/davinci-resolve-ai-bridge-mcp/resolve-ai-editing"><img src="https://agentmods.dev/badge/skills/flamexnreal/davinci-resolve-ai-bridge-mcp/resolve-ai-editing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00028 | $0.02347 |
| Opus 5.5 | $0.00011 | $0.00939 |
| Sonnet 5.5 | $0.00006 | $0.00469 |
| Haiku 4.5 | $0.00003 | $0.00235 |
Grade A, and why
resolve-ai-editing 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resolve AI Editing
Use this skill whenever a request involves the open DaVinci Resolve project.
Mandatory Live Timeline Audit Protocol
CRITICAL RULE FOR AI AGENTS: Before analyzing audio, generating subtitles/captions, rendering motion graphics, or proposing any edit:
- Always Call
timeline_overviewFirst: Never assume previous timeline state, cached clip names, or raw files on disk. The user frequently records new microphone audio, cuts clips, trims in-points (GetLeftOffset), moves the playhead, or switches projects/timelines in DaVinci Resolve between prompts. - Use Source Mapping Metadata: Use timeline_audio's returned source_start_sec, timeline_start_frame and frame_rate. Do not assume source frames equal timeline frames on mixed-rate or retimed clips. Source analysis excludes Fairlight processing.
- Audio Formats: Let timeline_audio normalize decoded media to 16-bit PCM. Do not infer timing errors solely from source bit depth.
- Timing Review: Activity clusters are energy-based, not transcripts. Any anticipatory caption lead is an optional creative choice; audition the result rather than promising universal perceptual sync.
- GPU Cache Invalidation: When placing newly rendered transparent subtitle or motion graphic videos onto the timeline, always use a unique timestamped filename or disable old overlapping clips on lower tracks so DaVinci Resolve's GPU video memory immediately displays the fresh render.
Required Workflow
- Call
resolve_statusbefore every editing session. It reports which transport is live. If offline, choose Workspace > Scripts > Resolve AI Bridge > Start AI Bridge once per Resolve session. On the tested macOS Free build it starts directly; use the portable Py3 Console line only if automatic startup fails. - Call
timeline_overviewbefore proposing an edit. - Summarize what is open and identify ambiguities.
- State a short plan before changing the timeline.
- Prefer the stable
idfrom the latest overview. Positionallabelvalues such asV1.2can change after edits. Duplicates and rebuilt clips have new IDs. Do not target a repeated name. - Before a batch of changes, use
preview_timeline, inspect its new IDs, and keep the original. Usecompare_timelinesplus visual/audio review afterward. - Make one logical change per tool call.
- Call
timeline_overviewagain to verify the result. - Ask for explicit approval before deletion, ripple deletion, or starting a render.
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.
- 11d ago Changed · +8 lines 21a4ffb33e50
- 1mo ago Changed 02a807ed265d
- 1mo ago Changed · +11 lines f90a766b133b
- 1mo ago Changed · +2 lines c14e2e7f8b01
- 1mo ago First seen · 90 lines · 28 tokens per session scan A d471668ebd0f
resolve-ai-editing is a skill published in the GitHub repository flamexnreal/davinci-resolve-ai-bridge-mcp (38 stars, last pushed 11d ago), licensed MIT. It adds 28 tokens to every session and 2,347 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
documentation-and-adrs
Records decisions and documentation. Use when you need to document an architecture decision (ADR) or the reasoning behind a design choice, when changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.
idea-refine
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or…
peon-ping-log
Log exercise reps for the Peon Trainer. Use when user says they did pushups, squats, or wants to log reps. Examples - "/peon-ping-log 25 pushups", "/peon-ping-log 30 squats", "log 50 pushups".
ai-output-validation
Validates, parses, and sanitizes AI-generated outputs before they reach end users or downstream systems. Structured output enforcement, schema validation, and fallback handling.
idea-to-spec
Converts vague ideas into concrete, testable specifications with acceptance criteria. No implementation begins without a spec.
ponytail-lazy-senior-dev
Applies the "lazy senior developer" mindset. Use this skill whenever generating, modifying, reviewing code, or fixing bugs to prioritize code reuse, minimalism, YAGNI principles, and root-cause fixes. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni"…