CtrlK
BlogDocsLog inGet started
Tessl Logo

visual-mode

Guidance for working on Remotion Studio Visual Mode, sequence identity, node paths, symbolicated stacks, override IDs, and hot reload behavior. Use when implementing or debugging visual editing of Sequences.

55

Quality

61%

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 ./.agents/skills/visual-mode/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

55%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 a lean set of engineering observations that successfully captures non-obvious domain knowledge, but it reads as stream-of-consciousness notes rather than guidance. Turning the identity rules into a decision procedure and fixing typos would substantially improve it.

Suggestions

Convert the Fields observations into a decision procedure (e.g. numbered rules: which identity to key on in which situation, and what to do when a stack is already in use), so a reader knows the sequence of decisions rather than just the facts.

Fix typos and garbled sentences ('needs to be calculated asyn', 'overrideId works change', 'does never change') and reconcile the contradictory nodePath stability claims.

State the actionable consequence of each field property — e.g. what 'fetch the nodepath for every stack once' implies for implementation — instead of leaving observations implicit.

DimensionReasoningScore

Conciseness

Terse field-level notes with zero padding or explanation of concepts Claude already knows ('We should only fetch the nodepath for every stack once'), but overlapping stack/nodePath statements and typos ('calculated asyn', 'overrideId works change') keep it below anchor 5's every-token-earns-its-place bar.

4 / 5

Actionability

The route-tracking rule is concrete and executable ('add it to the Browser Studio parity checklist in issue #9807... place it in either the required Browser Studio operations or the explicitly unsupported routes'), but the core Fields section is observations, not instructions — no code, commands, or steps for mapping nodePath to overrideId — matching anchor 3's 'some concrete guidance but incomplete'.

3 / 5

Workflow Clarity

The body opens with 'I've made the following observations' and presents a knowledge dump; there is no sequence for the identity/hot-reload work and no validation checkpoints, matching anchor 2's rough-or-absent sequence with poorly defined steps rather than anchor 3's listed-steps-with-gaps.

2 / 5

Progressive Disclosure

Well under 50 lines with no bundle files, two clear section headers ('## Fields', '## Browser Studio route tracking') and a well-signaled external link to the GitHub issue; the simple-skill exception could justify a 5, but the Fields section's unsorted, partially contradictory bullet prose ('nodePath -> same identity... changes on hot reload' vs 'nodePath could theoretically change on every file change') keeps it at 4.

4 / 5

Total

13

/

20

Passed

Description

68%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 names a highly specific niche with a genuine 'Use when...' trigger clause and near-zero conflict risk, but it lists topics rather than capabilities. Replacing 'Guidance for working on' with concrete verbs would lift specificity and completeness.

Suggestions

Replace the generic opener 'Guidance for working on' with concrete capability verbs, e.g. 'Reason about sequence identity, map node paths to symbolicated stacks, and debug hot-reload state drift.'

State what the skill does with the listed concepts (decide, track, debug) so the 'what' half is as strong as the 'when' half.

Add one or two trigger synonyms users might say, such as 'expanded state' or 'sequence tree', to round out keyword coverage.

DimensionReasoningScore

Specificity

The only action phrase is the generic 'Guidance for working on'; the remainder is a topic inventory ('sequence identity, node paths, symbolicated stacks, override IDs') with no concrete capabilities stated, matching the anchor 'names the domain but actions are minimal or generic' rather than anchor 3's 1-2 concrete actions.

2 / 5

Completeness

Both halves are present: an explicit trigger clause ('Use when implementing or debugging visual editing of Sequences') and a stated what, but the 'what' is a topic list rather than concrete capabilities, so it does not clearly match anchor 5's fully explicit both-parts example.

4 / 5

Trigger Term Quality

'Remotion Studio Visual Mode', 'visual editing of Sequences', 'implementing or debugging', and 'hot reload behavior' are natural terms a Remotion contributor would actually say, giving good coverage; it falls short of anchor 5 because no synonyms or variations of the trigger phrases are included.

4 / 5

Distinctiveness Conflict Risk

'Remotion Studio Visual Mode' and 'override IDs' define a narrow niche no other skill would plausibly claim; distinct triggers make conflict risk minimal, matching anchor 5 exactly.

5 / 5

Total

15

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
remotion-dev/remotion
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.