CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

78%

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 ./.claude/skills/faceswap/SKILL.md

The canonical home for this skill is faceswap in calesthio/OpenMontage

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 well-structured, highly actionable single-endpoint API skill with copy-paste-ready examples in three languages and a clear default workflow. Its main weaknesses are redundant repetition of the same request/response examples and minor completeness gaps in the code (missing imports, no HTTP status checks).

Suggestions

Remove the duplicated curl request in 'Usage Examples > Basic Face Swap' (identical to the one under 'Execute Face Swap') and the repeated response format under 'Authentication' to tighten the document.

Make code examples fully standalone: add the missing 'requests' and 'os' imports to the avatar-chain example and check HTTP status (e.g., response.raise_for_status() / response.ok) before parsing JSON in the submit calls.

Add brief error-recovery guidance for a 'failed' execution status (e.g., inspect data.error.message, verify image has a single clear face, then resubmit) to close the feedback loop in the default workflow.

DimensionReasoningScore

Conciseness

Mostly dense and useful (field tables, code, best practices) with no concept-explaining padding, but the identical POST curl request appears three times (Authentication, Execute Face Swap, Usage Examples) and the response format is repeated, so it could be noticeably tightened.

3 / 5

Actionability

Executable curl, TypeScript, and Python examples plus a complete polling loop with failed/not_found handling cover the common cases. Minor gaps keep it below 5: the avatar-chain example omits the 'requests' and 'os' imports, and submit calls never check HTTP status before parsing JSON.

4 / 5

Workflow Clarity

The 'Default Workflow' gives a clear 4-step sequence (submit, capture execution_id, poll every 10s until completed, use video_url) and the polling code detects failure states. However, there is no recovery guidance for a failed execution beyond throwing, so it falls short of the explicit feedback-loop anchor.

4 / 5

Progressive Disclosure

Well-organized single-level sections (Authentication, Execute, Check Status, Polling, Examples, Best Practices) with no buried or nested references, and the content is appropriately inline for a single-endpoint API skill. The multi-language duplication and avatar-chain example inflate the file and could be split out, which keeps it from a 5.

4 / 5

Total

15

/

20

Passed

Description

82%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 strong description: it clearly states what the skill does and gives explicit, concrete 'Use when' triggers with good synonym coverage. Its only weaknesses are that the trigger list restates a single action rather than enumerating multiple distinct capabilities, and a few natural terms (file formats, adjacent phrasings) are missing.

DimensionReasoningScore

Specificity

Names the domain (face swapping via HeyGen API) and the core action ('Swap faces in a video'), but the four 'Use when' clauses largely restate one action rather than listing several distinct concrete capabilities, so coverage is not comprehensive.

3 / 5

Completeness

Explicitly answers 'what' ('Swap faces in a video using AI via the HeyGen API') and 'when' with four concrete trigger phrases in a 'Use when:' clause, matching the anchor-5 example structure.

5 / 5

Trigger Term Quality

Good keyword coverage with natural synonyms users would say ('swap faces', 'face swapping', 'replacing a face', 'personalized videos', 'HeyGen'), but it misses file-format terms (.mp4, .jpg) and adjacent natural phrasings like 'deepfake' that anchor 5 expects.

4 / 5

Distinctiveness Conflict Risk

A clear niche (HeyGen API face swapping) with distinct triggers ('face swap', 'HeyGen', '/v1/workflows/executions'); minimal risk of firing for unrelated video or image skills.

5 / 5

Total

17

/

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

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

.claude/skills/faceswap/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.