Agent skill · Testing & QA

documentary-montage-production

Provider-independent workflow for AI agents producing documentary-style montages, archive-driven timelines, interview-supported sequences, nonprofit or advocacy shorts, historical explainers, and hybrid generated/archive edits. Use for editorial thesis development, research/source logs, fact-checking, archive rights, synthetic reenactment disclosure, chronology, interview selects, lower thirds, generated b-roll direction, music restraint, captions, sensitive subjects, review escalation, delivery variants, and documentary QA.

Calesthio43,316★ · +2,384/wk · 2 repos on radarProfile →
claude-codecodexcopilotcursorMIT
Install
npx skills add calesthio/generative-media-skills --skill documentary-montage-production --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 27 KB
Bundled scripts: none
Path: skills/production/content-formats/documentary-montage-production/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 112 · +8 this week
Language: Python
Read our review of the source →

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Use this skill when the deliverable asks the viewer to believe, understand, or feel the significance of real people, real events, real institutions, or real-world claims. The central rule is: do not let the audience become more certain than the evidence allows.

How it works

  • Establish a five-part documentary posture in every decision: Documented fact, Corroborated interpretation, Participant testimony, Illustration or reenactment, Editorial thesis.
  • Start with an evidence-first brief, including thesis, audience/context, core claims, human stakes, evidence map, rights/disclosure map, and sensitivity level.
  • Maintain a source and research log with fields like source_id, title, creator, URL or path, dates, source type, rights status, provenance notes, relevant claims, and confidence.
  • Log a minimum claim log per claim with claim_id, exact wording, evidence (source_id references), support level, on-screen treatment, and fact-check status.
  • Apply a strict fact-checking discipline, prioritizing original records and verified sources, and clearly distinguish event date, source date, publication date, and edit date for timelines.
  • Build chronology using a structured approach (timeline spine, argument ladder, witness braid, etc.) and ensure transitions do not imply unsupported causality.
  • Handle interviews with complete transcripts and source audio/video, documenting speaker details, timecodes, transcripts, context, purpose, and cleanup.
  • Manage archive and reference rights with a clear rights status (owned/licensed/CC/public domain/etc.) and a rights log tied to the source log.
  • Preserve provenance metadata (filenames, checksums, metadata, C2PA) and avoid assuming authenticity from appearance.
  • Use synthetic media disclosures when applicable, labeling generated content and providing three disclosure points on-screen, in credits, and platform controls; monitor platform rules today and adjust as needed.
  • Generate b-roll prompts carefully, requiring factual anchors, forbidden details, and a clear disclosure label; follow the provided prompt pattern and example.
  • Create lower thirds and source cards with precise formatting rules, and avoid implying evidentiary authority before evidence supports it.
  • Apply archival texture ethics to ensure any age treatment, restoration, or processing is properly justified and labeled.
  • Adhere to music and sound restraint to keep narration intelligible and avoid cueing unintended beliefs.

When to use it

Use when producing documentary-style content that relies on real-world claims, archival material, or sensitive subjects, and when you need to maintain an evidence-first approach, rights awareness, and a clear separation between fact, interpretation, testimony, illustration, and thesis.

What it can touch

Tools declared: claude-code, codex, copilot, cursor. The skill directs the agent to employ these tools as needed to gather sources, draft logs, structure claims, and generate prompts, while keeping all outputs traceable to logged sources and clearly labeled as appropriate (e.g., generated media disclosures).

Caveats

Documentary posture requires strict separation of five categories; rights and disclosure decisions escalate to humans for sensitive items; synthetic media must be disclosed in three places and platform rules can change. The policy also notes escalation triggers for rights, privacy, and vulnerable-subject issues.

From the SKILL.md

# Documentary Montage Production Use this skill when the deliverable asks the viewer to believe, understand, or feel the significance of real people, real events, real institutions, or real-world claims. The central rule is: do not let the audience become more certain than the evidence allows. This is not legal advice. Treat rights, defamation, privacy, platform-policy, election, medical, financia

More from generative-media-skills
All skills →
About this skill
What does the documentary-montage-production skill do?

Provider-independent workflow for AI agents producing documentary-style montages, archive-driven timelines, interview-supported sequences, nonprofit or advocacy shorts, historical explainers, and hybrid generated/archive edits. Use for editorial thesis development, research/source logs, fact-checking, archive rights, synthetic reenactment disclosure, chronology, interview selects, lower thirds, generated b-roll direction, music restraint, captions, sensitive subjects, review escalation, delivery variants, and documentary QA.

How do I install it?

Run `npx skills add calesthio/generative-media-skills --skill documentary-montage-production --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going