CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ketchup-video

Catch the user up like /ketchup, with a short subtitled video of slides for what happened and the waiting calls as text under it. Use for /ketchup-video.

Quality

84%

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

92%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 an exemplary terse, instruction-only skill: dense with concrete numeric rules, a clear section-ordered workflow, and an explicit validate-fix-rerender loop. The only meaningful gap is that the rendering step never names a tool or command, leaving the one fragile, tool-dependent step the least specified part of the process.

Suggestions

Name at least one concrete rendering path (e.g. an ffmpeg command template for assembling slide images plus burned-in subtitles into an mp4) so the most tool-dependent step is executable rather than inferred.

DimensionReasoningScore

Conciseness

The body is lean, imperative, and free of padding — e.g. "A slide is never a bullet list, a status list, a table, or boxes with nothing connecting them" and "Drop each slide that does not change what the user knows". It explains nothing Claude already knows and every sentence instructs, matching anchor 5.

5 / 5

Actionability

Guidance is highly concrete with specific numeric rules ("Use at most 10 slides", "about ten words", "at least one second for each three words", "burn each subtitle into its slide's frames") and a concrete check method ("Look at one frame from each slide at chat size"). It falls short of anchor 5 because no render tool or command is ever named — "Render one silent landscape video, such as an mp4, with motion between slides" leaves the rendering mechanism entirely to inference.

4 / 5

Workflow Clarity

The workflow is clearly sequenced through ordered sections (plan slides → subtitle styling → render → check) with an explicit validation pass ("check the rendered file", "Measure each hold", "Count the words each slide adds against its measured hold") and a feedback loop ("Fix any slide you cannot read in that time, render again, and check again"). This is not a destructive or batch operation, so no cap applies, and it matches anchor 5.

5 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external reference files, and is organized into clear sections (Slides, Subtitles, Render); its single reference to ../ketchup/SKILL.md is one level deep and clearly signaled. Per the simple-skill guideline this matches anchor 5.

5 / 5

Total

19

/

20

Passed

Description

71%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 specific, distinctive, and answers both what the skill does and when to use it, with an appropriate explicit tie to the /ketchup-video command. Its main weakness is narrow trigger coverage: no natural-language synonyms or variations beyond the command name itself, which leaves users who describe the need in their own words unserved by the trigger guidance.

Suggestions

Broaden the trigger clause beyond the bare command name, e.g. "Use for /ketchup-video, or when the user asks for a video recap, catch-up video, or subtitled summary of what happened."

State the core capability as discrete actions (e.g. "builds slides from the session's screenshots, diffs, and recordings; renders them as a silent subtitled video; lists waiting calls as text") to make the 'what' more comprehensive and concrete.

Clarify the relationship to /ketchup up front so the scope (video variant of the catch-up flow) is immediately unambiguous even to a reader who skips the link.

DimensionReasoningScore

Specificity

The description names several concrete outputs — "a short subtitled video of slides for what happened" and "the waiting calls as text under it" — which goes beyond naming the domain with 1-2 actions. It stops short of anchor 5 because it describes one composite deliverable rather than multiple comprehensive, separately enumerated actions.

4 / 5

Completeness

Both parts are present: a clear "what" (subtitled video of slides for what happened, waiting calls as text) and an explicit "when" ("Use for /ketchup-video"). It does not reach anchor 5 because the "when" is a single command mention without additional concrete trigger phrases, leaving it narrower than the anchor-5 pattern.

4 / 5

Trigger Term Quality

Relevant keywords like "Catch the user up", "video", "subtitled", and "slides" are present, but the only explicit trigger is the literal command "/ketchup-video", with no natural variations or synonyms a user might say (e.g. "recap video", "video summary", "catch-up video"). This matches anchor 3 (some relevant keywords, missing common variations) rather than 4, which requires broader natural-term coverage.

3 / 5

Distinctiveness Conflict Risk

The skill occupies a clear niche — a video catch-up tied to the specific /ketchup-video command — and explicitly differentiates itself from the related /ketchup skill ("instead of its summary and visuals"). Conflict risk with other skills is minimal, matching anchor 5.

5 / 5

Total

16

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

cursor/plugins

Path

harness/pstack/claude-code/skills/ketchup-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.