seedance-pipeline

This skill should be used when the user asks about Seedance 2.0 workflow operations, API planning, BytePlus ModelArk, Dreamina/Jimeng surfaces, provider/router APIs, China-facing surfaces, ComfyUI, post-production, stitching, batch workflow, or integration planning.

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

50%

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

A well-structured orchestration skill with clear workflow taxonomy and an output contract, but it leans on motivational prose and defers all actionable detail to reference files that do not exist.

Suggestions

Add the missing reference files under references/ (api-status, api-workflow, model-name-map, pro-filmmaking-standards, delivery-qc) so the [ref:...] markers resolve to real, navigable content.

Replace the motivational "Intent" prose with a one-line operational purpose statement to improve token efficiency.

Add explicit validation checkpoints (e.g., a verify-before-deliver step tying [ref:delivery-qc] to the output contract) for batch and delivery workflows.

Dimension	Reasoning	Score
Conciseness	The body is largely lean routing guidance, but the "Intent" section is motivational prose ("Behind every API question is a person with a deadline...") that does not earn its tokens against the operational content.	2 / 3
Actionability	It gives concrete routing (which [ref:] to load per trigger, ten workflow types, an output contract) but no executable commands, exact field names, auth, or API-call specifics — the actionable detail is deferred to references.	2 / 3
Workflow Clarity	Ten sequenced workflow paths and an explicit output contract give clear structure, but validation checkpoints are mostly implicit (only "Load [ref:delivery-qc] before saying an asset is delivery-ready" and "rechecked before code or pricing guidance"), which caps clarity for batch/delivery work.	2 / 3
Progressive Disclosure	The [ref:api-status], [ref:api-workflow], [ref:pro-filmmaking-standards], [ref:delivery-qc], and [ref:model-name-map] markers signal one-level-deep deferral, but no references/ directory exists, so those references are dangling rather than navigable.	2 / 3
	Total	8 / 12 Passed

Description

72%

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 specific, well-triggered description tied to a clear niche, but it answers "when to use" far better than "what it does" — it lists domains instead of concrete actions.

Suggestions

Open with one or two concrete actions the skill performs (e.g., 'Plans and sequences Seedance 2.0 video-generation workflows across API and web surfaces') before the trigger list.

Replace the topic-only enumeration with at least one explicit capability statement so the "what" is as clear as the "when".

Keep the existing trigger list but trim redundant near-synonyms (e.g., "batch workflow" vs "integration planning") to tighten the trigger surface.

Dimension	Reasoning	Score
Specificity	The description enumerates concrete surfaces ("Seedance 2.0", "BytePlus ModelArk", "Dreamina/Jimeng surfaces", "ComfyUI") but lists domains/topics rather than concrete actions the skill performs, so it sits between vague and comprehensive.	2 / 3
Completeness	It provides an explicit "when" ("This skill should be used when the user asks about...") but the "what" is only implied through topic enumeration — no action verb states what the skill does.	2 / 3
Trigger Term Quality	It packs in natural terms a user would say ("Seedance 2.0", "API planning", "ComfyUI", "post-production", "stitching", "China-facing surfaces"), giving good coverage of likely phrasings.	3 / 3
Distinctiveness Conflict Risk	The Seedance/BytePlus/Dreamina niche is sharply scoped with distinct triggers, making it unlikely to fire for an unrelated skill.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 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

	Total	14 / 16 Passed

Repository: Emily2040/seedance-2.0
Path: skills/seedance-pipeline/SKILL.md
Commit: 6c51262

Reviewed: 1 day 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.