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.

68

Quality

85%

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 dense, highly actionable pipeline document with excellent sequencing and unusually strong validation gates. Its two real weaknesses are the missing examples/master-skeleton.html bundle file (breaks step 0 and the anti-patterns' prescribed fix) and repetitive emphasis on the same failure modes that could be consolidated.

Suggestions

Add the missing examples/master-skeleton.html to the bundle — step 0's cp command and the 'restart at the cp of the master-skeleton scaffold' recovery instruction both depend on it, and its absence breaks the first step of the pipeline.

Consolidate the scaffold-off-brand warning and the captions-are-non-optional warning into their single authoritative spots (step 0 and step 5 respectively), leaving one-line reminders elsewhere instead of full re-explanations in steps 4, 6, and two anti-pattern rows.

Remove the instance-specific postmortem reference ('This is exactly what went wrong on the Jul 13-20 v4 build') or move dated build history into a dedicated old-patterns/incidents section, per time-sensitive-content guidance.

DimensionReasoningScore

Conciseness

Assumes Claude's competence throughout (no explanations of ffmpeg, whisper, or TTS) and every section instructs, but the scaffold warning and caption non-optionality are each repeated 3-4 times across steps 0, 4, 5, 6, and the anti-patterns table, and the dated postmortem reference ('This is exactly what went wrong on the Jul 13-20 v4 build') is trimmable. Anchor 4's 'minor instances of over-explanation' fits; not 5 given that redundancy.

4 / 5

Actionability

Copy-paste-ready bash with exact flags (ffmpeg filter chain, voice ID, full caption-zone check command) plus the whisper fallback — but the pivotal step-0 command 'cp <SKILL_DIR>/examples/master-skeleton.html project/index.html' targets a file that does not exist in the bundle, so following the instructions as written fails at the first step. Anchor 4's 'concrete code or commands with minor gaps' fits; not 5 because a core instruction cannot execute as written.

4 / 5

Workflow Clarity

Steps 0-6 are explicitly sequenced with five validation gates ('all green before presenting'), MISMATCH resolution before building, a hard word-timings gate with a whisper forced-alignment fallback, and a caption-presence hard-fail with a re-do path — a clear anchor-5 match with feedback loops for this batch/render operation.

5 / 5

Progressive Disclosure

The body acts as a router: brand tokens to references/build-spec.md, visualization routing to references/visualization-registry.md, voice to references/script-voice.md and lexicon.json — all one level deep, clearly signaled, and all present in the bundle. However, the referenced path examples/master-skeleton.html does not exist in the bundle (no examples/ directory), a broken reference to the file the whole pipeline is built on. Good structure with a real defect — anchor 4, not 5.

4 / 5

Total

17

/

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.

A strong description: concrete output spec, explicit 'Use when...' triggers including an exact quoted phrase, and a clearly distinct niche. The only gaps are minor — no multi-action enumeration and a missing 'release notes' synonym.

DimensionReasoningScore

Specificity

Names the domain and concrete output specifications — 'square 1080, ~45-60s, Annie VO, animated brand background, mock-UI visualizations, lowkey captions' — but describes a single transform action rather than multiple distinct actions. Anchor 5 requires several concrete actions; anchor 3 ('1-2 concrete actions') understates the parameter-rich spec.

4 / 5

Completeness

Explicitly answers both: what ('Turn a weekly changelog .md into a finished branded changelog video' with full output spec) and when ('Use when the user provides a changelog/digest markdown and wants the weekly video, or says "changelog video"') with concrete trigger phrases — a clear anchor-5 match.

5 / 5

Trigger Term Quality

Good natural-keyword coverage: 'changelog', 'digest markdown', '.md', 'weekly video', and the exact quoted trigger 'changelog video'. Missing common synonyms like 'release notes video', so short of anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

Clear niche ('branded changelog video', Annie VO, square 1080) with distinct trigger phrases; minimal overlap risk with generic video or document skills. Uses imperative voice consistent with the good examples; no first/second-person penalty.

5 / 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: 1 missing

Warning

Total

13

/

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.