CtrlK
BlogDocsLog inGet started
Tessl Logo

srt-from-script

Build an SRT subtitle file from a 3-shot short-drama script (ai-video-script OUTPUT FORMAT). Reads each SHOT_N block's DURATION_S + VOICEOVER, emits cumulative-timestamped SRT cues. Pure text-processing, no LLM, no network. Used by meta-short-drama between merge and the final subtitle-burn step.

68

Quality

83%

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

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 a lean, well-structured contract for an entrypoint-based skill: precise inputs, concrete parsing semantics, and clear failure modes. The only weakness is the lack of an inline executable example, since the real logic is delegated to the bundled script.

DimensionReasoningScore

Conciseness

Lean ~40-line body with well-organized sections and no padding or explanation of concepts Claude already knows; every line (inputs table, parsing rules, limits) earns its place. Not 4 because there is no noticeable over-explanation to trim.

5 / 5

Actionability

Provides a concrete input contract (exact keys, required flags, defaults, semantic notes) and precise parsing/output behavior; not 5 because the body contains no executable code example — the actual logic lives in scripts/build_srt.py, leaving a minor gap for a reader who wants to see the transform.

4 / 5

Workflow Clarity

Single-purpose transform (parse script stdin → write cumulative-timed SRT) with an unambiguous action; the simple-skill exception applies and the 'Drift away from that format → zero cues, exit 1' note surfaces the failure mode. Not 4 because the single action is fully unambiguous with no validation gaps for a non-destructive transform.

5 / 5

Progressive Disclosure

Under 50 lines with no need for external references; well-organized sections (Inputs, Parsing rules, Output, Limits) and the only bundle file (scripts/build_srt.py) is correctly referenced via the frontmatter entrypoint. Not 4 because structure is clean and appropriately self-contained.

5 / 5

Total

19

/

20

Passed

Description

75%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, concrete, and highly distinctive with strong third-person action verbs. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness at 3 despite the clear orchestration context.

Suggestions

Add an explicit trigger clause such as 'Use when converting an ai-video-script 3-shot script into a timed .srt subtitle file for the subtitle-burn step.'

Include natural synonyms and the file extension (e.g., 'captions', '.srt') to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Build an SRT subtitle file', 'Reads each SHOT_N block's DURATION_S + VOICEOVER', 'emits cumulative-timestamped SRT cues' — with comprehensive coverage of the task; not the 4 anchor because there are no real coverage gaps.

5 / 5

Completeness

Clearly answers 'what' (build SRT from shot blocks) but lacks an explicit 'Use when...' trigger clause; 'Used by meta-short-drama between merge and the final subtitle-burn step' describes orchestration context, not a user trigger, so the missing-trigger cap at 3 applies.

3 / 5

Trigger Term Quality

Includes natural terms 'SRT subtitle file', 'short-drama script', 'subtitle' that a user would say, but misses common synonyms/extensions like 'captions' or '.srt'; not 5 because synonym/extension coverage is incomplete.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (SRT generation from ai-video-script 3-shot short-drama scripts) with distinct triggers and minimal overlap risk; not 4 because it is sharply distinguishable rather than merely 'mostly distinct'.

5 / 5

Total

17

/

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.

Validation13 / 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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
TokenRhythm/opensquilla
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.