seedance-camera

This skill should be used when the user asks for camera movement, shot scale, lens feel, framing, one-take direction, dolly, pan, tilt, push-in, handheld, aerial, macro, or camera-transfer guidance for Seedance 2.0.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/seedance-camera/SKILL.md

Quality

Content

72%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable camera-direction skill body with strong concrete phrasing and good sectioning. Its main weaknesses are implicit workflow checkpoints and a broken bundle — six reference files are linked but none are present.

Suggestions

Ship the referenced bundle files (references/directors-read.md, quick-ref.md, cinematography-shot-language.md, directing-engine.md, vocab/zh.md, vocab/ru.md) or remove the links; dangling references make progressive disclosure non-functional.

Add an explicit numbered workflow with a validation/checkpoint step (e.g. '1. Load Director's Read; 2. Classify brief; 3. Draft camera phrase; 4. Check against Conflict Rule; 5. Return per Output Contract') to make the sequence and its gates explicit.

Trim the conceptual Intent paragraph ('Camera grammar is empathy mechanics...') to a one-line operational cue to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's intelligence — the Camera Contract table, Move Selection, and Continuity Rules are dense and high-value. Only minor over-explanation could be trimmed (the 'Camera grammar is empathy mechanics' philosophy in Intent and the dense opener), so it sits at 'Efficient; minor instances of over-explanation.' Not a 5 because the Intent section is conceptual padding rather than operational guidance.	4 / 5
Actionability	Highly actionable for an instruction-only skill: concrete strong/avoid phrase pairs in the contract table, specific lens mm anchors, explicit move-selection rules by use case, and exact reference-tag syntax ('@Video1 controls camera rhythm only; do not transfer performer, room, logo, or identity'). Specific examples cover the common cases.	5 / 5
Workflow Clarity	A conceptual flow is given up front ('load the Director's Read, classify the brief, complete its record, translate into carriers') and an Output Contract closes it, but there are no explicit validation checkpoints or feedback loops and the sequence is implicit rather than enumerated. This matches 'Steps listed but validation gaps; checkpoints missing or implicit.' Not a 4 because checkpoints are not present, and the destructive/batch cap is not triggered since this is a generation skill.	3 / 5
Progressive Disclosure	The SKILL.md is well-sectioned and clearly signals one-level-deep references (directors-read.md, quick-ref.md, cinematography-shot-language.md, directing-engine.md, vocab/zh.md, vocab/ru.md), which structurally suggests a 4-5; however none of these referenced files exist in the bundle (no references/ directory resolves), so navigation is broken. The missing backing files cap it at 'Some structure... references present but' not reliably navigable rather than a 4.	3 / 5
	Total	15 / 20 Passed

Description

67%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A trigger-rich, well-scoped description with excellent keyword coverage and low conflict risk, but it only communicates 'when' to use the skill and leaves 'what' it does vague. Adding a concrete capability clause would lift completeness and specificity.

Suggestions

Add an explicit 'what' clause, e.g. 'Generates and rewrites camera-direction prompts for Seedance 2.0 clips' before the trigger list, to convert the description from a pure trigger enumeration into a what+when statement.

State the concrete actions the skill performs (e.g. classifies the brief, assembles a prompt-ready camera phrase, resolves conflicting moves) rather than only listing trigger terms.

Dimension	Reasoning	Score
Specificity	The description names the domain richly ('camera movement, shot scale, lens feel, framing... for Seedance 2.0') but names no concrete actions the skill performs — it is a trigger enumeration, not a capability statement, matching 'Names the domain but actions are minimal or generic.' It is not a 3 because no concrete capability (e.g. 'generates camera direction prompts') is stated.	2 / 5
Completeness	The 'when' is explicit and strong ('This skill should be used when the user asks for...'), but the 'what' is only weakly implied through the trigger list ('camera-transfer guidance for Seedance 2.0'); there is no clear statement of what the skill produces, so it does not reach a 4 which requires both clearly present.	3 / 5
Trigger Term Quality	Comprehensive natural-term coverage with synonyms and specifics — 'camera movement, shot scale, lens feel, framing, one-take direction, dolly, pan, tilt, push-in, handheld, aerial, macro, camera-transfer' — exactly the kind of terms a user would say when they need this skill.	5 / 5
Distinctiveness Conflict Risk	Clear niche (Seedance 2.0 camera/cinematography direction) with distinct, specific triggers and the 'Seedance 2.0' scoping that minimizes overlap with general skills.	5 / 5
	Total	15 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 6 suspicious	Warning

	Total	13 / 16 Passed

Repository: Emily2040/seedance-2.0
Path: skills/seedance-camera/SKILL.md
Commit: 44b5149

Reviewed: 27 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.