CtrlK
BlogDocsLog inGet started
Tessl Logo

changelog-video

Turn a weekly changelog .md into a finished branded changelog video (square 1080, ~45-60s, Annie VO, animated brand background, mock-UI visualizations, lowkey captions). Use when the user provides a changelog/digest markdown and wants the weekly video, or says "changelog video". Self-contained — fonts, background, lexicon, and scripts ship in this skill.

70

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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-architected, highly actionable skill with an exemplary gated render pipeline and clear reference structure. Its main weakness is a broken reference — the master-skeleton scaffold it tells Claude to copy is missing from the bundle — plus some repeated emphatic prose that could be tightened.

Suggestions

Ship `examples/master-skeleton.html` in the bundle (or correct the `cp` path) — step 0, build-spec.md, and the anti-patterns table all point to it, but the file is absent, breaking the primary executable instruction.

Tighten the bootstrap section: the 'don't start from a prior video' warning is conveyed in the prose, the STOP-and-restart paragraph, and the anti-patterns table — collapse to one authoritative statement and let the table carry the rest.

De-duplicate brand-token rules between SKILL.md step 5 and references/build-spec.md so the body points rather than restates, reducing token cost without losing the cross-reference.

DimensionReasoningScore

Conciseness

Dense and assumes Claude's competence with no elementary padding, but the bootstrap section restates the 'don't copy a prior video' warning across the prose, the STOP-and-restart paragraph, and the anti-patterns table, and re-emphasizes brand rules already in build-spec.md — minor trimmable repetition.

4 / 5

Actionability

Mostly executable copy-paste bash (cp, ffmpeg encode with full vf chain, node TTS with pinned voice id, align-captions flags, full check command with caption-zone args), but step 0's first `cp <SKILL_DIR>/examples/master-skeleton.html` targets a file absent from the bundle, a concrete execution gap keeping it just below fully ready.

4 / 5

Workflow Clarity

A clearly sequenced 0–6 pipeline with explicit validation checkpoints and feedback loops — the word-timings hard gate, whisper forced-alignment fallback, and the frame-sampling caption-presence hard-fail gate — exactly the validate→fix→retry pattern the rubric rewards for render/destructive work.

5 / 5

Progressive Disclosure

Good one-level-deep structure: references/ (build-spec, visualization-registry, script-voice, lexicon), scripts/align-captions.mjs, and assets/ are clearly signaled from the body, but `examples/master-skeleton.html` is referenced in both the body and build-spec.md yet does not exist in the bundle — a navigation dead-end.

4 / 5

Total

17

/

20

Passed

Description

92%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, specific, third-person description that concretely states what the skill produces and gives explicit natural-language triggers for when to use it. The only mild gap is slightly narrower keyword/extension variety than a maximally comprehensive trigger set.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and specs — 'Turn a weekly changelog .md into a finished branded changelog video (square 1080, ~45-60s, Annie VO, animated brand background, mock-UI visualizations, lowkey captions)' — comprehensive and concrete, matching the anchor-5 example.

5 / 5

Completeness

Explicitly answers both 'what' (the full video-build with specs) and 'when' ('Use when the user provides a changelog/digest markdown and wants the weekly video, or says "changelog video"') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural user phrases — 'changelog video', 'changelog/digest markdown', 'wants the weekly video' — and the .md extension, but the synonym/extension set is focused rather than exhaustive, so it sits at good-but-not-comprehensive.

4 / 5

Distinctiveness Conflict Risk

A clear niche — 'branded changelog video', 'Annie VO', 'mock-UI visualizations' — with distinct triggers and minimal overlap with other skills.

5 / 5

Total

19

/

20

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

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
heygen-com/hyperframes
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.