faceswap

Swap faces in a video using AI via the HeyGen API. Use when: (1) Replacing a face in a video with another face, (2) Face swapping from a source image onto a target video, (3) Creating personalized videos by swapping in a person's face, (4) Working with HeyGen's /v1/workflows/executions endpoint for face swap processing.

Quality

82%

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

Quality

Content

77%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.

The body is highly actionable with clear workflow sequencing and status-check feedback loops. Its main weaknesses are repeated curl examples that waste tokens and a monolithic single-file structure that could split API reference and examples into bundled reference files.

Suggestions

Remove the duplicate POST curl example — keep one canonical example in 'Execute Face Swap' and reference it from Authentication and Usage Examples instead of repeating it.

Move the multi-language code samples and the 'Chain with Avatar Video' example into a references/ file (e.g. EXAMPLES.md) linked from the body to reduce inline length and improve progressive disclosure.

Add a brief input-validation note before submission (e.g. confirm the source image contains exactly one front-facing face) to strengthen workflow checkpoints.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code, but the same POST curl example is repeated nearly verbatim in Authentication, Execute Face Swap, and the Basic Usage Example, adding redundant tokens; not severely padded so above 2 but below 4.	3 / 5
Actionability	Fully executable, copy-paste ready guidance in curl, TypeScript, and Python covering the common submit-and-poll cases, matching the 5 anchor.	5 / 5
Workflow Clarity	The Default Workflow gives a clear 4-step sequence and the polling code has explicit status checkpoints (completed/failed/not_found) with a timeout, providing a clear feedback loop; this is not a destructive/batch operation so no cap applies.	5 / 5
Progressive Disclosure	Well-organized with section headers, but ~250 lines of API reference, multi-language examples, and chaining examples are all inlined in a single file with no external references, matching the 3 anchor where content that could live in separate files is inline.	3 / 5
	Total	16 / 20 Passed

Description

87%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.

The description is strong: it states a concrete capability, gives an explicit multi-part 'Use when' trigger list, and is tightly scoped to HeyGen face swapping. Minor improvements could add a synonym like 'deepfake' for broader trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('Swap faces in a video', 'Replacing a face in a video', 'Face swapping from a source image onto a target video') with minor gaps in coverage, fitting the 4 anchor rather than the comprehensive 5.	4 / 5
Completeness	Clearly states what it does ('Swap faces in a video using AI via the HeyGen API') and provides an explicit 'Use when:' clause with four concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('face swap', 'faces in a video', 'face swapping', 'personalized videos') that users would plausibly say, with a few synonyms (e.g. 'deepfake') missing, placing it at 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	A clear niche tied to HeyGen's face swap endpoint with distinct triggers, minimal overlap with other skills, matching the 5 anchor.	5 / 5
	Total	18 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	13 / 16 Passed

Repository: calesthio/OpenMontage
Path: .agents/skills/faceswap/SKILL.md
Commit: 08e2151

Reviewed: 2 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.