CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

hunk-launch-video

Produces Hunk videos by driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg. Use for feature demos, workflow explainers, announcements, launch videos, and full-release roundups.

Quality

87%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

An exceptionally actionable and well-validated operational manual: executable commands for every stage, explicit checkpoints, and hard-won environment gotchas. Its main structural weakness is that all reference-grade detail lives inline in SKILL.md with no progressive-disclosure layer, and a few rules are stated twice.

Suggestions

Move the Chapter reference, Storyboard model, and Environment gotchas sections into one-level-deep reference files (e.g. references/storyboard-model.md, references/gotchas.md) and keep SKILL.md as a shorter overview with clearly signaled links.

Deduplicate the 50%-size legibility rule, which appears in both "Command and output legibility" and "Verification and delivery", by stating the gate once and referencing it from the verification checklist.

Trim the editorial framing in "Camera and callout composition" to the concrete rules (fit, blank-row edges, measured heights, cameraKey sharing) to reduce token load without losing guidance.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious operational fact (PTY resolution quirks, Playwright/Chromium matching, learned accuracy rules) and assumes Claude's competence throughout, but contains minor redundancy — the 50%-size legibility rule is restated across "Command and output legibility" and "Verification and delivery" — keeping it just below the every-token-earns-its-place anchor.

4 / 5

Actionability

Every stage ships copy-paste-ready commands: the bun capture invocation with SCENES overrides, the portable Playwright setup, exact ffmpeg/ffprobe encode and inspection commands, plus concrete fallback procedures (CHROMIUM_PATH resolution, install-deps retry, fontPath override) covering the common failure cases.

5 / 5

Workflow Clarity

Both recipes are explicitly numbered with validation checkpoints and feedback loops: "Stills first" review before full render, missing-keyframe preflight that fails fast, MP4-before-VP9 ordering, contributor aliasing reruns, and a dedicated Verification section with ffprobe duration cross-checks — matching the explicit-validation-with-recovery anchor.

5 / 5

Progressive Disclosure

The ~480-line body is well-sectioned but monolithic: reference-grade material like the Chapter reference, Storyboard model, and Environment gotchas is inlined in SKILL.md with no one-level-deep reference files, fitting the "content that should be separate is inline" anchor rather than the minor-organization-gaps anchor above it.

3 / 5

Total

17

/

20

Passed

Description

88%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: third-person voice, concrete pipeline actions, and an explicit "Use for" trigger clause covering the main use cases. The only weaknesses are a few missing natural synonyms (promo, product video, screencast) and the slightly over-broad "announcements" trigger.

DimensionReasoningScore

Specificity

"driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg" lists multiple specific concrete actions covering the entire pipeline with no gaps, matching the comprehensive-coverage anchor rather than the minor-gaps anchor below it.

5 / 5

Completeness

It explicitly answers both questions: the "what" is the three-stage produce-composite-encode pipeline, and an explicit "Use for..." clause names concrete trigger scenarios, matching the anchor requiring both with concrete trigger phrases; without the Use-for clause it would be a 3.

5 / 5

Trigger Term Quality

"feature demos, workflow explainers, announcements, launch videos, and full-release roundups" gives good natural keyword coverage, but common user phrasings like "promo", "product video", "demo video", or "screencast" are missing, so it falls just short of the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

"Hunk videos" anchors a clear niche with distinct triggers, but the unqualified term "announcements" could pull text-announcement requests toward this video skill, giving minor overlap risk with closely related content-creation skills rather than the minimal risk of the top anchor.

4 / 5

Total

18

/

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

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

referenced_paths_exist

Referenced path issues: 17 missing, 15 deeper-than-1-level

Warning

Total

13

/

16

Passed

Repository

modem-dev/hunk

Path

skills/hunk-launch-video/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.