CtrlK
BlogDocsLog inGet started
Tessl Logo

fal-lip-sync

Create talking head videos and lip sync audio to video via fal.ai. Useful for explainer avatars, multilingual dubbing previews, and social cuts.

56

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/fal-lip-sync/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

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

The body is well-organized and appropriately short for a catalogue entry, but it functions as a pointer to an external repo rather than providing concrete, executable guidance. The redundant description restatement and missing install command keep the actionability and workflow dimensions at 2.

Suggestions

Replace the vague "install the upstream bundle" instruction with a concrete, executable command (e.g. a git clone or tessl/open-design install command) so the How-to-use step is copy-paste ready.

Drop the verbatim restatement of the description in "What it does" and the meta sentence about advertising in Open Design to tighten conciseness.

If the skill is meant to delegate to the upstream bundle, add a one-line concrete usage example showing the expected invoke call (e.g. `fal-lip-sync --video input.mp4 --audio voice.wav`) so the workflow is unambiguous.

DimensionReasoningScore

Conciseness

The body is short, but it restates the frontmatter description verbatim in "What it does" and includes meta prose ("This catalogue entry advertises the skill in Open Design so the agent discovers it during planning") that could be trimmed, matching the level-2 anchor of mostly-efficient-but-tightenable rather than the lean level-3.

2 / 3

Actionability

It gives one concrete command (`open https://github.com/fal-ai-community/skills`) and an invoke instruction, but the core install step ("install the upstream bundle into your active agent's skills directory") has no executable command and says to "Inspect the upstream README for exact paths," so guidance is present but incomplete — the level-2 anchor.

2 / 3

Workflow Clarity

A loose two-step flow is present (install the upstream bundle, then invoke by name or trigger phrase), but the install step is underspecified with no concrete command or checkpoint, matching the level-2 anchor of steps-listed-with-gaps rather than a clean, sequenced, validated workflow.

2 / 3

Progressive Disclosure

At under 50 lines with no bundle files and no need for local references, the body is organized into clearly labeled sections (What it does, Source, How to use) with a single one-level external pointer to the upstream repo, which the simple-skills note allows to score 3.

3 / 3

Total

9

/

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.

The description is third-person, concise, and carves out a distinct niche with good natural trigger terms. Its main gap is the absence of an explicit "Use when..." trigger clause, which leaves the "when to use it" half only implied via use cases.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to lip sync audio to a video or make a talking-head avatar with fal.ai."

Expand the action list to be more comprehensive (e.g. mention choosing an avatar/model, providing audio + video inputs, and rendering the output) to lift specificity from 2 to 3.

DimensionReasoningScore

Specificity

It names the domain and two concrete actions — "Create talking head videos and lip sync audio to video via fal.ai" — mirroring the score-2 anchor ("Processes PDF files and extracts content") rather than listing many specific actions, so it does not reach level 3.

2 / 3

Completeness

It clearly answers "what" (create talking head videos / lip sync audio to video) but the "when" is only framed as use cases ("Useful for explainer avatars, multilingual dubbing previews, and social cuts") rather than an explicit "Use when..." trigger clause, which the guidelines say caps completeness at 2.

2 / 3

Trigger Term Quality

Natural user-facing terms are well covered: "talking head videos", "lip sync", "audio to video", "explainer avatars", "multilingual dubbing previews", and "social cuts" are phrases a user would plausibly say, matching the level-3 anchor.

3 / 3

Distinctiveness Conflict Risk

The fal.ai lip-sync / talking-head niche with distinctive terms ("fal.ai", "lip sync", "talking head") is unlikely to collide with unrelated skills, matching the level-3 clear-niche anchor.

3 / 3

Total

10

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
nexu-io/open-design
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.