Skip to content

nexu-io/openmotion / skills/openmotion-production

openmotion-production

Verified

Execute local edits, asset or audio replacements, previews, technical troubleshooting, exports, and delivery on an existing OpenMotion project under established creative decisions. Use openmotion-director for narrative, motion, or audiovisual redesign; openmotion-template-to-video for existing templates; openmotion-recreate for recreating a reference video; and openmotion-video-to-template for reusable templates. Repository development and documentation maintenance do not trigger video production.

FileKindSize
SKILL.mdskill md6.0 KB
agents/openai.yamlconfig139 B
fonts/catalog.jsonconfig139.4 KB
references/context.mdmarkdown15.1 KB
references/decisions.mdmarkdown8.7 KB
references/edit.mdmarkdown5.9 KB
references/fonts.mdmarkdown8.6 KB
references/intake.mdmarkdown7.1 KB
references/materials.mdmarkdown19.4 KB
references/native.mdmarkdown21.4 KB
references/portable-project.mdmarkdown5.8 KB
references/production.mdmarkdown12.9 KB
references/reference-video.mdmarkdown15.5 KB
references/review.mdmarkdown11.2 KB
references/sound.mdmarkdown12.3 KB
references/templates.mdmarkdown9.9 KB
references/typography.mdmarkdown10.1 KB
references/verification.mdmarkdown12.5 KB

references/typography.md

View on GitHub
# Typography for motion

Read when selecting or replacing fonts, changing text hierarchy or reviewing a typography complaint. Preserve established brand, template and reference decisions; apply only to affected text on a local edit. A preview or export with unchanged typography does not trigger new font selection.

## Choose from the content

Identify the text's actual job and desired effect: what the audience must read, feel or recognize. A title may command, narrate, carry a character's voice or act as a visual performer; narration/subtitles, supporting explanation and data have different reading duties. Give each affected role a purpose in this film. One family may serve several jobs; additional families earn their place through a visible relationship.

Resolve identity before browsing fonts. Identify what the supplied brand material governs in this task: the whole film, one branded segment, or visual inspiration. An attachment's presence alone does not turn a personal showreel into that brand's advertisement. Preserve the user's specified identity, accepted template and agreed reference within their actual scope.

- **Original marks and packaging:** retain the supplied lettering or outlines as assets. Selecting a font for surrounding copy does not authorize rebuilding the wordmark.
- **Brand reading text:** use the prescribed family and role when available. If substitution is necessary, compare construction (rounded/angular, width, stroke contrast and weight), language coverage and the actual words against the reference. Record the affected role and visible compromise; pairing suggestions are not brand substitutes. An exact-font requirement that cannot be met remains an explicit dependency.
- **Open creative roles:** choose type character from this film's subject, voice and viewing conditions. One family can cover the whole role system. Add a contrasting family only for a useful role or an established expressive relationship.

Explain the consequential choice briefly in the existing creative record: which identity is binding, which role is open and why the selected face fits. A familiar face can be right; novelty alone is not a reason to replace it. A simple title may need one sentence, not a brand worksheet.

Use real copy when selecting. Check the actual languages, regional glyph forms, numerals, punctuation, available weights and italics. A Latin face does not establish the appearance of Chinese text. For mixed text, choose the CJK face deliberately and compare weight, scale and baseline in the actual frame.

Use the [curated font catalog](fonts.md) when existing brand/reference resources do not resolve the choice. Filter by language, role and real resource availability, then inspect only relevant candidates. Its mood and pairing tags are editorial starting points. A genre such as technology, luxury or anime leaves several plausible constructions open; resolve the actual tone and words before committing.

For an open choice whose appearance matters, compare a small shortlist with meaningfully different construction, including the current face when revising it:

1. **Set the question.** Use the role's actual phrase, script and numerals. State the visible distinction to resolve: for example, narrow urgency versus a broad command, or human narration versus an impersonal label. Select candidates whose construction could produce that difference; genre tags alone do not finish selection.
2. **Look at the words.** Prepare the candidate files and put the same copy side by side at equal role size, weight, width and spacing, scaled to the intended display. Inspect the actual glyph silhouette, counters, terminals, stroke contrast, density and rhythm that bear on the question. For mixed text compare the deliberate face stack, including the CJK face. The optional [offline specimen](fonts.md#compare-prepared-faces-with-actual-copy) creates this comparison from pinned resources; an existing project preview can serve the same purpose.
3. **Choose and compose.** Record the observed difference that matters to this role and select the treatment. Then tune that face's weight, tracking, breaks and hierarchy in the real frame. A promising specimen still needs the composition's background, neighboring roles and reading window. Keep a concise alternative or limitation when the evidence is ambiguous.

Stop when the role choice has visible support; an established satisfactory face needs no browsing exercise. The comparison record describes what was seen, rather than claiming that catalog membership or an HTML file proves a better design.

**Done:** the applicable brand boundary, purposeful text roles, chosen faces/weights and important mixed-language relationship are resolved for the affected scope. Consequential open choices have an actual-copy observation supporting them. Reuse the existing record; no new approval step.

## Compose with the real words

Establish hierarchy through size, weight, spacing and placement together. Tune tracking and line height to the face, script and scale. Choose line breaks from meaning and the actual frame. Build a stable readable state when the audience must read; intentional moving type is judged by whether the required message can still be followed.

Labels, numbering, capitals and mono text can carry information, atmosphere or rhythm. Keep them when that contribution is visible. If they repeat the heading, compete with the subject or merely fill a template slot, simplify their content or treatment and compare the affected frame. Style membership alone is neither a defect nor a reason to add decoration.

Check the intended viewing size with actual copy. For a phone-led film without a specified viewing size, start with the complete composition displayed at 360 CSS px wide, preserving its aspect ratio. Treat this as a reproducible review condition, not a required export width. The displayed size is approximately authored size × displayed video width / source width, including any text transforms. Source pixels alone do not establish readability.

Review the required message, not only the largest title: the core claim, longest feature label or subtitle, and final CTA/URL where present. At that displayed width, roughly 24–40 px for a main title and 14–18 px for essential supporting copy are useful initial editing ranges, not pass/fail thresholds or a fixed scale. Script, stroke contrast, wording, background and movement determine the result. A deliberate oversized title or a readable exception is valid. Separate optional texture/credits from information the audience must read.

Read each required phrase in its actual stable window at normal speed. Capture the corresponding phone-size frame to inspect glyphs and spacing; a full-resolution crop or a larger editor preview does not replace it. If a required line is weak, improve contrast/weight or enlarge it, reflow or simplify surrounding decoration, then adjust time or split the message while preserving locked wording. Establish hierarchy by emphasis and layout while keeping necessary secondary information readable. A smaller treatment needs a reading benefit or real space constraint, not merely a wish for a refined-looking end card.

For a local edit, compare the affected reading states with the previous version. For new work, compare them with the applicable brand/reference hierarchy. Record target display size, representative time/role, observed problem and correction in the existing review; successful technical checks do not settle reading quality.

**Done:** all required text roles in the affected scope have a checked readable state and reading window at the intended display size, including the end card when present. Missing playback or viewing evidence stays unverified; no numeric font-size check alone declares a pass.

## Use the face that was chosen

Follow the pinned engine guide and the supported project asset path. Resolve the real family, weight and style from the font resource, not its filename. Keep required resources reproducible through project-relative files and declared dependencies, with the applicable license/source record for distribution.

Check actual glyph coverage, requested weights and fallback. A loaded font or a successful FontFaceSet check alone does not prove which face rendered every glyph. Use available font metadata and rendered-font evidence for representative text; report any known substitution. A static Regular resource does not provide all weights. An intentional system stack or mixed-font run is valid when it is part of the agreed design and delivery conditions.

For managed projects, use the available version-protected tools. If a required font cannot be imported through the supported path, choose a suitable available alternative or report the dependency; never write around project revision protection. A catalog entry is not evidence that its font file has been installed or imported.

**Done:** the relevant resource and substitution checks support the declared text treatment. Unverified rendering remains unverified rather than a design pass.

## Diagnose a typography complaint

Use the current affected frame and its neighboring playback window. Separate:

1. **Resource:** unexpected fallback, missing glyph, wrong regional form, synthetic weight/style.
2. **Hierarchy and reading:** role ambiguity, weak contrast, cramped spacing, unintended wrap, insufficient readable time.
3. **Content and fit:** text density or treatment that weakens the subject, voice or intended atmosphere.

Fix the earliest applicable cause and review the result. A complaint about font character or fit reopens the affected role's choice even when surrounding visuals are locked: use the actual-copy shortlist above while preserving the locked content and composition. When both font and typesetting are plausible causes, compare a face-only change and a treatment-only change before combining them. Record wrapping and width changes caused by new font metrics; this is the direct replacement effect, not a perfectly isolated glyph-shape experiment.

Use the existing review record: location/version, observation, impact, change and evidence. Actual rendering proves layout and face behavior; normal-speed viewing proves the relevant reading window. Technical success alone does not establish content fit.
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 198kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 198kUpdated Claude CodeCodexVerifiedInstall