Agent skill

Premiere Captions

by ayushozha in ayushozha/AdobePremiereProMCP

Import, verify, structurally validate, and export timed captions or subtitles in Adobe Premiere Pro.

MITAuto-check passedMedia & Creative

Install Premiere Captions

skills CLI
$ npx skills add ayushozha/AdobePremiereProMCP --skill premiere-captions -a claude-code

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

GitHub CLI
$ gh skill install ayushozha/AdobePremiereProMCP premiere-captions --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/ayushozha/AdobePremiereProMCP.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/premiere-captions .claude/skills/premiere-captions && 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
premiere-captions
GitHub stars
120
Token cost
~724 tokens
SKILL.md length
349 words
Files
2
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Import, verify, structurally validate, and export timed captions or subtitles in Adobe Premiere Pro.

  • Works in 7 steps: Verify the host and target sequence with… → Obtain a valid SRT file with segment… → Fix line wrapping in the SRT before… → …
  • Supplied timed transcripts
  • SKILL.md covers Required server profile, Workflow and Guardrails
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Premiere Captions is an agent skill from ayushozha/AdobePremiereProMCP. Import, verify, structurally validate, and export timed captions or subtitles in Adobe Premiere Pro. Use for SRT workflows, supplied timed transcripts, caption QA, accessibility checks, or sidecar subtitle delivery through the Premiere Pro MCP server.

Its SKILL.md is about 720 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Media & Creative, covering Transcription. It works with Model Context Protocol. The repository describes itself as: An open-source bridge between AI assistants and Adobe Premiere Pro, for supported editing workflows. Go, Rust, Python, and TypeScript. The licence is MIT.

When your agent uses it

  • Supplied timed transcripts
  • Accessibility checks
  • Sidecar subtitle delivery through the Premiere Pro MCP server

Example prompts

  • “/premiere-captions”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Verify the host and target sequence with premiere_ping, premiere_get_project, and premiere_get_timeline.
  2. Obtain a valid SRT file with segment timestamps. If only audio exists, request or generate a timestamped transcript with a separate…
  3. Fix line wrapping in the SRT before import: keep at most two lines, avoid single-word orphan lines, and reject overlaps or non-positive…
  4. Resolve the active sequence index with premiere_get_sequence_list, duplicate it with premiere_duplicate_sequence, identify exactly one new…
  5. Call premiere_add_subtitles_from_srt on the duplicate. Require verified: true and an exact caption-count match.
  6. Call premiere_get_captions and compare every readable segment's text, start, and end against the source. Stop on a mismatch.
  7. Run premiere_validate_closed_captions for structural QA. Reconfirm the duplicate's active ID, export sidecar captions with…

What it can do on your machine

Read from SKILL.md and the folder at commit 36574e4. 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

Premiere Captions loads about 724 tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 349 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~67
When it runs · the whole SKILL.md, loaded when a task matches
~724

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 ayushozha/AdobePremiereProMCP at commit 36574e4, republished under its MIT licence (© ayushozha). 349 words, ~724 tokens.

Download SKILL.mdSave it as .claude/skills/premiere-captions/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
premiere-captions
description
Import, verify, structurally validate, and export timed captions or subtitles in Adobe Premiere Pro. Use for SRT workflows, supplied timed transcripts, caption QA, accessibility checks, or sidecar subtitle delivery through the Premiere Pro MCP server.

Premiere Captions

Use supplied timed text as the source of truth. The current server does not provide trustworthy speech transcription by itself.

Required server profile

Start or restart the MCP server with MCP_TOOL_PROFILE=captions. The default standard profile also contains this workflow, but captions is the smaller dedicated surface.

Workflow

  1. Verify the host and target sequence with premiere_ping, premiere_get_project, and premiere_get_timeline.
  2. Obtain a valid SRT file with segment timestamps. If only audio exists, request or generate a timestamped transcript with a separate transcription system; this server does not claim to transcribe speech.
  3. Fix line wrapping in the SRT before import: keep at most two lines, avoid single-word orphan lines, and reject overlaps or non-positive durations.
  4. Resolve the active sequence index with premiere_get_sequence_list, duplicate it with premiere_duplicate_sequence, identify exactly one new copy and its ID, and activate that copy with premiere_set_active_sequence. Require verified: true with that ID, then re-read the sequence list and stop unless activeSequenceID matches. Leave the source untouched as the recovery boundary. A timeline snapshot or saved sequence version is audit data only, not a whole-sequence restore point.
  5. Call premiere_add_subtitles_from_srt on the duplicate. Require verified: true and an exact caption-count match.
  6. Call premiere_get_captions and compare every readable segment's text, start, and end against the source. Stop on a mismatch.
  7. Run premiere_validate_closed_captions for structural QA. Reconfirm the duplicate's active ID, export sidecar captions with premiere_export_captions using that ID as sequence_id, then verify through the filesystem that the sidecar exists, is non-empty, and parses to the expected segment count. If filesystem verification is unavailable, report the export as unverified.

Guardrails

  • Preserve source language, names, numbers, and punctuation; flag uncertain words instead of inventing them.
  • Request a visual title-safe review; the CEP caption API cannot verify styling or on-screen placement.
  • CEP caption styling, speech alignment, and in-Premiere segment splitting are explicitly unsupported because they cannot be mutated and read back safely. Style manually or use a verified MOGRT-based burned-in workflow.
  • Structural validation is not FCC certification. Report caption count, overlaps, warnings, and errors; do not infer transcription accuracy, timeline coverage, reading speed, or placement.

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

Files

SKILL.md and 1 other file in skills/premiere-captions of ayushozha/AdobePremiereProMCP.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 36574e4

Compare with similar skills

Premiere Captions 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.

Premiere Captions compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Premiere Captions this skillayushozha/AdobePremiereProMCP120—~724Automated safety check: PassMIT
Horizon Speechpeters/horizon716—~1.8kAutomated safety check: PassMIT
Resolve Audiosamuelgursky/davinci-resolve-mcp3.5k—~1.3kAutomated safety check: PassMIT
Proofreadsonilo-ai/skills115—~4.4kAutomated safety check: NotesMIT
Transloadit Media Processinggithub/awesome-copilot40k1 repos~1.3kAutomated safety check: PassMIT
Scenario Caption Studioscenario-labs/skills946—~3.4kAutomated safety check: PassMIT

Similar skills

  • Horizon Speech

    peters/horizon

    Check that a microphone is usable for Horizon dictation and report which layer is at fault — no signal, bad level, or a genuine model/accent limit.

    716 GitHub stars~1.8k tokensUpdated today
    Media & CreativeAuto-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.

    3.5k GitHub stars~1.3k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Proofread

    sonilo-ai/skills

    Transcribe a video with Sonilo and translate the transcript into editable .srt files — one per target language, plus the detected source language — so the wording can be read and corrected before…

    115 GitHub stars~4.4k tokensUpdated 2 days ago
    Media & CreativeAuto-check: notes
  • Transloadit Media Processing

    github/awesome-copilot

    Official

    Process media files (video, audio, images, documents) using Transloadit.

    40k GitHub starsUsed in 1 repo~1.3k tokens
    Media & CreativeAuto-check passed
  • Scenario Caption Studio

    scenario-labs/skills

    A skill your agent uses when a video needs its spoken words on screen through Scenario via MCP: burned-in styled captions for a TikTok, Reels, or Shorts cut, ad captions for sound-off feeds, YouTube…

    946 GitHub stars~3.4k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Scenario Video Assembly

    scenario-labs/skills

    A skill your agent uses when generated clips must become a finished video on Scenario via MCP: cutting a shot list together, laying a timeline, concatenating with transitions, overlaying a logo or…

    946 GitHub stars~2.3k tokensUpdated yesterday
    Media & CreativeAuto-check passed

More from ayushozha/AdobePremiereProMCP

  • Premiere Batch Delivery

    ayushozha/AdobePremiereProMCP

    Validate, export, and inspect multiple Adobe Premiere Pro deliverables with explicit pending and unverified states.

    120 GitHub stars~776 tokensUpdated 5 days ago
    Auto-check passed
  • Premiere Dialogue Cut

    ayushozha/AdobePremiereProMCP

    Tighten interviews, podcasts, tutorials, and talking-head edits in Adobe Premiere Pro by detecting silence, preserving natural speech margins, keeping an untouched recovery sequence, and verifying…

    120 GitHub stars~897 tokensUpdated 5 days ago
    Auto-check passed
  • Premiere Look Effects

    ayushozha/AdobePremiereProMCP

    Build consistent, reversible visual effect recipes in Adobe Premiere Pro from effects confirmed as installed.

    120 GitHub stars~648 tokensUpdated 5 days ago
    Auto-check passed
  • Premiere Proxy Conform

    ayushozha/AdobePremiereProMCP

    Speed Adobe Premiere Pro editing with proxy creation, attachment, media matching, and original-media readiness checks.

    120 GitHub stars~822 tokensUpdated 5 days ago
    Auto-check passed
  • Premiere Social Reframe

    ayushozha/AdobePremiereProMCP

    Produce vertical, square, and platform-specific versions of an Adobe Premiere Pro sequence while preserving the master edit.

    120 GitHub stars~994 tokensUpdated 5 days ago
    Auto-check passed
  • Premiere Transition Pack

    ayushozha/AdobePremiereProMCP

    Select and apply restrained, installed video or audio transitions in Adobe Premiere Pro.

    120 GitHub stars~722 tokensUpdated 5 days ago
    Auto-check passed

Questions about Premiere Captions

What does Premiere Captions do?

Import, verify, structurally validate, and export timed captions or subtitles in Adobe Premiere Pro. Premiere Captions is an agent skill from ayushozha/AdobePremiereProMCP. Import, verify, structurally validate, and export timed captions or subtitles in Adobe Premiere Pro.

When should I use Premiere Captions?

Premiere Captions fits situations like: supplied timed transcripts; accessibility checks; sidecar subtitle delivery through the Premiere Pro MCP server.

How do I install Premiere Captions in Claude Code?

Run `npx skills add ayushozha/AdobePremiereProMCP --skill premiere-captions -a claude-code`. Or copy the skill folder (skills/premiere-captions in ayushozha/AdobePremiereProMCP) into .claude/skills/premiere-captions in your project. Claude Code loads it when a task matches its description.

How do I install Premiere Captions in Codex?

Run `npx skills add ayushozha/AdobePremiereProMCP --skill premiere-captions -a codex`. Or copy the skill folder (skills/premiere-captions in ayushozha/AdobePremiereProMCP) into .agents/skills/premiere-captions in your project. Codex loads it when a task matches its description.

Can I use Premiere Captions 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 ayushozha/AdobePremiereProMCP --skill premiere-captions -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/premiere-captions, .gemini/skills/premiere-captions, .github/skills/premiere-captions and .opencode/skills/premiere-captions in your project.

What does Premiere Captions need to run?

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

Does Premiere Captions 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 Premiere Captions 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 Premiere Captions use?

Premiere Captions 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 Premiere Captions use?

About 724 tokens (SKILL.md is roughly 2.9k 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 Premiere Captions?

Skills that share tags, products or a category with Premiere Captions: Horizon Speech (peters/horizon, 716 stars), Resolve Audio (samuelgursky/davinci-resolve-mcp, 3.5k stars), Proofread (sonilo-ai/skills, 115 stars) and Transloadit Media Processing (github/awesome-copilot, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Premiere Captions?

ayushozha (a GitHub user) maintains it in ayushozha/AdobePremiereProMCP, which has 120 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 5, 2026.

Source: ayushozha/AdobePremiereProMCP on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.