agentsope/SkillAlchemy / skills/LEAP
LEAP
VerifiedLEAP builds skills through two pipelines: Branch A distills a skill from raw data, while Branch B combines multiple skills into one. It is called by the main SkillAlchemy workflow. Use when SkillAlchemy requires distillation or fusion.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 30.5 KB |
| domains/cybersecurity/domain.md | markdown | 2.1 KB |
| domains/energy/domain.md | markdown | 2.1 KB |
| domains/finance/domain.md | markdown | 1.9 KB |
| domains/healthcare/domain.md | markdown | 2.1 KB |
| domains/manufacturing/domain.md | markdown | 2.1 KB |
| domains/mathematics/domain.md | markdown | 2.1 KB |
| domains/media-content-production/domain.md | markdown | 2.4 KB |
| domains/natural-science/domain.md | markdown | 2.0 KB |
| domains/office-white-collar/domain.md | markdown | 2.1 KB |
| domains/persona-os/domain.md | markdown | 5.3 KB |
| domains/robotics/domain.md | markdown | 1.9 KB |
| domains/software-engineering/domain.md | markdown | 2.0 KB |
| references/skill-grammar.md | markdown | 17.3 KB |
| scripts/build_component_index.py | script | 23.7 KB |
| scripts/build_corpus.py | script | 11.0 KB |
| scripts/download_subtitles.sh | script | 2.1 KB |
| scripts/score_skill.py | script | 6.8 KB |
| scripts/srt_to_transcript.py | script | 3.3 KB |
| skill.json | config | 132 B |
scripts/srt_to_transcript.py
View on GitHub#!/usr/bin/env python3
"""
Convert SRT/VTT subtitle files into clean plain-text transcripts.
Remove timestamps, sequence numbers, duplicate lines, and HTML tags to produce
directly readable text.
Usage:
python3 srt_to_transcript.py input.srt [output.txt]
python3 srt_to_transcript.py input.vtt [output.txt]
If no output file is specified, the default is input_transcript.txt.
"""
import sys
import re
from pathlib import Path
def clean_srt(content: str) -> str:
"""Clean subtitles in SRT format."""
lines = content.strip().split('\n')
texts = []
for line in lines:
line = line.strip()
# Skip sequence-number lines containing only digits.
if re.match(r'^\d+$', line):
continue
# Skip timestamp lines.
if re.match(r'\d{2}:\d{2}:\d{2}', line):
continue
# Skip blank lines.
if not line:
continue
# Remove HTML tags.
line = re.sub(r'<[^>]+>', '', line)
# Remove VTT positioning markers.
line = re.sub(r'align:.*$|position:.*$', '', line).strip()
if line:
texts.append(line)
# Deduplicate consecutive lines, which are common in automatic captions.
deduped = []
for text in texts:
if not deduped or text != deduped[-1]:
deduped.append(text)
# Merge short consecutive sentences into paragraphs. Start a new paragraph
# after terminal punctuation or a sufficiently long accumulated passage.
result = []
current = []
for text in deduped:
current.append(text)
# Form a paragraph when the accumulated text is long enough or the
# current subtitle ends with terminal punctuation.
joined = ' '.join(current)
if len(joined) > 200 or re.search(r'[.!?]$', text):
result.append(joined)
current = []
if current:
result.append(' '.join(current))
return '\n\n'.join(result)
def clean_vtt(content: str) -> str:
"""Clean VTT subtitles by removing VTT metadata, then applying SRT logic."""
# Remove the WEBVTT header.
content = re.sub(r'^WEBVTT.*?\n\n', '', content, flags=re.DOTALL)
# Remove NOTE blocks.
content = re.sub(r'NOTE.*?\n\n', '', content, flags=re.DOTALL)
return clean_srt(content)
def main():
if len(sys.argv) < 2:
print("Usage: python3 srt_to_transcript.py <input.srt|input.vtt> [output.txt]")
sys.exit(1)
input_path = Path(sys.argv[1])
if not input_path.exists():
print(f"❌ File not found: {input_path}")
sys.exit(1)
# Select the default output filename.
if len(sys.argv) >= 3:
output_path = Path(sys.argv[2])
else:
output_path = input_path.parent / f"{input_path.stem}_transcript.txt"
# Read the source and detect its format.
content = input_path.read_text(encoding='utf-8')
if input_path.suffix.lower() == '.vtt' or content.startswith('WEBVTT'):
transcript = clean_vtt(content)
else:
transcript = clean_srt(content)
output_path.write_text(transcript, encoding='utf-8')
# Report output statistics.
word_count = len(transcript)
line_count = transcript.count('\n') + 1
print(f"✅ Conversion complete: {output_path}")
print(f" Characters: {word_count} Paragraphs: {line_count}")
if __name__ == '__main__':
main()
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |