# AGENTS.md — Build guide for diclip ## Project scope Transcribe one long video, propose standalone clip ranges, let the editor refine boundaries and render vertical clips with reviewed captions. Catalogue verdict: kinda. The core loop is genuinely one-shottable: transcribe, rank the strongest moments, cut vertical clips with burned captions. The gaps are execution and infra. Face-aware reframing with seat tracking, a full in-browser timeline editor, and a container-scale render pipeline are not a one-session build. A competent agent can produce a usable personal clipper quickly, but matching diclip's reframe quality and editing depth is a multi-day project. Use the implementation prompt below to define the deliverable. Complete each phase's acceptance checks before extending the scope. ## Working agreement - Inspect the repository and its existing instructions before choosing paths, dependencies or commands. Keep one coherent stack and explain changes to the proposed architecture. - Plan a vertical slice that accepts a real input and produces the useful output described below. Persist only the state the prompt calls for; respect memory-only and upstream-managed workflows. Use fixtures only when they are clearly labelled. - After scaffolding, document the actual install, development, check and build commands in README and keep them synchronized with the package or project manifest. Do not report commands as successful unless they ran. - Work in small steps. At handoff, list implemented flows, checks actually performed, remaining blockers, and any credentials or provider setup the owner must supply. - Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization. ## Prerequisites - Runtime and tools: Python, FastAPI, SQLite, FFmpeg/ffprobe and a React review interface. - Before starting: Installed FFmpeg/ffprobe, writable media storage and a short recording whose use is authorized. ## Stack and architecture - Python, FastAPI, SQLite, FFmpeg/ffprobe and a React review interface - Data design: Store SourceVideo, TranscriptSegment, ClipCandidate, CropTrack and CaptionRevision; retain source timestamps and reject clips with overlapping or reversed boundaries. - Setup: Installed FFmpeg/ffprobe, writable media storage and a short recording whose use is authorized ## Security and data integrity - Keep source files immutable and store edit decisions separately. Run media tools with argument arrays, bounded file size/runtime and unique job directories; only rename a completed export into its final location. - Begin with manual center/subject positioning and one vertical preset. Highlight scores rank candidates only; no guaranteed virality, perfect face tracking or automatic factual context. - Keep secrets outside client bundles and exported projects; document what leaves the device and make retention/deletion controls visible. ## Agent implementation rules - Project rule — domain: Store SourceVideo, TranscriptSegment, ClipCandidate, CropTrack and CaptionRevision; retain source timestamps and reject clips with overlapping or reversed boundaries. - Project rule — scope and recovery: Begin with manual center/subject positioning and one vertical preset. Highlight scores rank candidates only; no guaranteed virality, perfect face tracking or automatic factual context. - Project rule — acceptance: Choose a highlight beginning mid-sentence, extend it to include context and render a two-speaker segment; preview exposes cropped faces and caption timing before export. - Project rule — delivery: document real setup commands and permissions; do not claim a build, accuracy level, performance result or security certification that has not been demonstrated. ## Optional agent skills and references - Recommended skill: [modern-python](https://github.com/trailofbits/skills/blob/main/plugins/modern-python/skills/modern-python/SKILL.md) — structure the Python worker or explicitly optional read-only utility with pinned dependencies, typed boundaries and clear failure handling. Follow the maintainer's installation instructions and match its requirements to the chosen runtime. - Recommended skill: [vercel-react-best-practices](https://github.com/vercel-labs/agent-skills/blob/main/skills/react-best-practices/SKILL.md) — keep the proposed React work/review views responsive and avoid unnecessary rendering or data-fetch waterfalls. Follow the maintainer's installation instructions and match its requirements to the chosen runtime. Read the linked SKILL.md and its dependencies before adding a skill. Select only the skills matching this project's runtime and task; their documentation does not supply API access, credentials or approval to perform external actions. Pin the reviewed revision where the tool supports it. Follow the chosen agent's documented project-level installation mechanism. ## Distribution ideas These are optional planning notes. Obtain the owner's approval before publishing or contacting anyone. - Demonstrate this working slice using synthetic or explicitly authorized non-sensitive examples: Transcribe one long video, propose standalone clip ranges, let the editor refine boundaries and render vertical clips with reviewed captions. - Share a synthetic example export and the acceptance walkthrough; keep real customer, health, financial and source data private: Choose a highlight beginning mid-sentence, extend it to include context and render a two-speaker segment; preview exposes cropped faces and caption timing before export. - State the limits before asking someone to replace their existing tool: Begin with manual center/subject positioning and one vertical preset. Highlight scores rank candidates only; no guaranteed virality, perfect face tracking or automatic factual context. ## Engineering roadmap 1. Phase 1 — Pin the working slice and create its example input: Transcribe one long video, propose standalone clip ranges, let the editor refine boundaries and render vertical clips with reviewed captions. Confirm setup: Installed FFmpeg/ffprobe, writable media storage and a short recording whose use is authorized. 2. Phase 2 — Implement persistence and write-time invariants before decorating the UI: Store SourceVideo, TranscriptSegment, ClipCandidate, CropTrack and CaptionRevision; retain source timestamps and reject clips with overlapping or reversed boundaries. 3. Phase 3 — Connect the working view to real saved state. Keep source files immutable and store edit decisions separately. Run media tools with argument arrays, bounded file size/runtime and unique job directories; only rename a completed export into its final location. 4. Phase 4 — Expose the app-specific limits and recovery path in context: Begin with manual center/subject positioning and one vertical preset. Highlight scores rank candidates only; no guaranteed virality, perfect face tracking or automatic factual context. 5. Phase 5 — Walk through this concrete acceptance case and preserve its exported evidence: Choose a highlight beginning mid-sentence, extend it to include context and render a two-speaker segment; preview exposes cropped faces and caption timing before export. Finish the README and backup/restore instructions; report unfinished capabilities explicitly. ## Paid-product capabilities outside this build - face-aware vertical reframing with seat tracking - full in-browser timeline editor with scenes, tracks, and effects - container-scale render pipeline and yt-dlp import - credit-based capacity model and priority processing - ready-to-post hooks and confidence scoring polished for clips ## Implementation prompt Build the following focused alternative to diclip. This is a deliberately limited personal or small-team substitute, not parity with the paid service. WORKING SLICE Transcribe one long video, propose standalone clip ranges, let the editor refine boundaries and render vertical clips with reviewed captions. SETUP AND ARCHITECTURE Use Python, FastAPI, SQLite, FFmpeg/ffprobe and a React review interface. Prerequisites: Installed FFmpeg/ffprobe, writable media storage and a short recording whose use is authorized. Before integrating anything, record actual versions and permissions, plus model files or provider limits only where used, in the README; make unavailable dependencies visible rather than simulating success. DOMAIN MODEL AND INVARIANTS Store SourceVideo, TranscriptSegment, ClipCandidate, CropTrack and CaptionRevision; retain source timestamps and reject clips with overlapping or reversed boundaries. IMPLEMENTATION CONTRACT Keep source files immutable and store edit decisions separately. Run media tools with argument arrays, bounded file size/runtime and unique job directories; only rename a completed export into its final location. Provide an input/setup view, the main work view, and a review/export view appropriate to this workflow. Preserve the last saved state if a job or save fails. Include empty, loading, permission-denied, partial and retryable-error states. Log identifiers and error categories without secret values or unnecessary private content. APP-SPECIFIC BOUNDARY AND RECOVERY Begin with manual center/subject positioning and one vertical preset. Highlight scores rank candidates only; no guaranteed virality, perfect face tracking or automatic factual context. ACCEPTANCE SCENARIO Choose a highlight beginning mid-sentence, extend it to include context and render a two-speaker segment; preview exposes cropped faces and caption timing before export. Also reopen the app after an interrupted operation, confirm the saved record/export remains inspectable, and document the recovery action. These are implementation acceptance requirements, not a claim that this guide has been tested. DELIVERY Deliver a runnable repository with migrations or project-format versioning, a non-sensitive example, environment/permission setup, the exact manual acceptance steps, and a backup/export-and-restore walkthrough. Implement the working slice before optional integrations; list any deferred paid-product capabilities honestly. Do not add capabilities outside the working slice just to resemble the original product. PROJECT RULES FOR AGENTS.md Keep the domain invariants above executable at the write boundary. Propose scope changes before adding providers or permissions. Never fabricate source evidence, publish results, identity matches or successful delivery. Preserve user originals and require an explicit confirmation for destructive changes or external publication. ## Completion evidence Demonstrate the prompt's acceptance scenarios against the scoped workflow. Include setup from a clean checkout and failure recovery. Check persistence across restart and export/restore only for the state the prompt says to store; for memory-only tools, confirm that temporary content is discarded as specified. Record actual results and remaining limitations. A detailed plan alone does not establish a working replacement.