CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/seedance-camera/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 overview: concrete strong/avoid phrase pairs, intent-to-move mappings, and a clear output contract teach the skill's judgment without padding. The main weaknesses are an unnumbered workflow whose reference-file order is implicit, and reference links that point outside the skill bundle rather than to files that ship alongside it.

Suggestions

Reference the bundle files with paths inside the skill's own directory (e.g., references/quick-ref.md) and ship them with the skill, so the ../../references/ links resolve without an unstated parent-repo layout.

Number the core workflow (load Director's Read → classify → build the camera record → select the move → emit the output contract) so the order of loading quick-ref, directing-engine, and cinematography-shot-language is unambiguous.

Trim the Intent section's empathy-metaphor sentences to a single directive line and show one example of the final 'prompt-ready integrated sentence' the Output Contract asks for.

DimensionReasoningScore

Conciseness

The body is dense directive prose with almost no filler — tables, one-line rules, and terse anchors like '24mm wide lens for spatial energy'. Minor over-explanation appears in the Intent section ("Camera grammar is empathy mechanics: a push-in is leaning closer, a locked frame is holding your breath"), which teaches a concept Claude already knows and could be trimmed to one sentence.

4 / 5

Actionability

The Need/Strong-phrase/Avoid table gives copy-paste-ready camera phrases covering five common cases ("slow dolly-in from medium close-up to tight close-up as Character A lowers the envelope"), Move Selection maps intents to specific moves, Continuity Rules supply exact reference-tag phrasing ("@Video1 controls camera rhythm only; do not transfer performer, room, logo, or identity"), and the Output Contract enumerates deliverables. For an instruction-only skill this is fully actionable guidance.

5 / 5

Workflow Clarity

A sequence is stated up front ("Before producing prompt text... load the Director's Read, classify the brief, and complete its canonical narrative or non-narrative record") and the Output Contract defines the endpoint. It is not a 5 because the steps are not crisply ordered across the loaded reference files (quick-ref vs. directing-engine vs. cinematography-shot-language have no stated order), and validation is implicit rather than a checkpoint ("A prompt-ready camera phrase should be physically possible").

4 / 5

Progressive Disclosure

The ~50-line body stays a lean overview and signals one-level-deep references with a purpose per file ("Load quick-ref for prompt assembly", "directing-engine... to derive the move"). It is not a 5 because every referenced path points to "../../references/" — outside the skill directory — and no references/ directory exists in this bundle, so the navigation cannot be verified and the links resolve only inside an unstated parent layout.

4 / 5

Total

17

/

20

Passed

Description

68%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 an excellent explicit 'when' clause, weakened by a vague 'what': it never says what the skill actually does, only that it provides "guidance". Broad natural-language coverage of camera vocabulary makes triggering reliable.

Suggestions

State 1-2 concrete actions to lift specificity, e.g., 'Composes prompt-ready camera phrases specifying shot scale, movement, speed, and endpoint for Seedance 2.0 clips. Use when the user asks for...'

Add missing natural trigger synonyms users commonly say: tracking/tracking shot, crane, orbit, zoom, camera angle, and 'cinematography'.

Lead with the 'what' before the trigger list so the description answers both questions in the order a reader needs them.

DimensionReasoningScore

Specificity

The description richly names the domain ("camera movement, shot scale, lens feel, framing, one-take direction, dolly, pan, tilt...") but the only action offered is generic "camera-transfer guidance" — no concrete verbs like compose, select, or plan. This matches the anchor 'Names the domain but actions are minimal or generic'; it is not a 3 because no 1-2 concrete actions are actually listed.

2 / 5

Completeness

The 'when' is fully explicit ("This skill should be used when the user asks for camera movement... for Seedance 2.0"), but the 'what' is only implied — the skill's actual actions (e.g., composing prompt-ready camera phrases) are never stated, leaving "camera-transfer guidance" as a vague what. Better than a 3 (which lacks an explicit when); short of a 5's concrete what AND when.

4 / 5

Trigger Term Quality

Thirteen natural trigger terms ("dolly, pan, tilt, push-in, handheld, aerial, macro", "shot scale", "lens feel", "framing") that users would genuinely say when needing this skill. It falls short of comprehensive (5) because common variations are missing: "tracking", "crane", "orbit", "zoom", "camera angle", "cinematography", "shot composition".

4 / 5

Distinctiveness Conflict Risk

The "for Seedance 2.0" scope plus highly camera-specific triggers ("one-take direction", "push-in", "camera-transfer guidance") establish a clear niche with minimal conflict risk against generic cinematography or image-generation skills.

5 / 5

Total

15

/

20

Passed

Validation

81%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.