Dictation Prompt Generator
July 7, 2026 · View on GitHub
Extract technical vocabulary from documentation files and create a concise dictation instruction file for fixing speech-to-text errors and improving text clarity.
Required Safe Output (Must Do)
Before you finish, you MUST call exactly one safe-output tool:
- Use
create_pull_requestif you made meaningful updates toDICTATION.md. - Use
noopif no meaningful update is needed after analysis. - Use
report_incompleteonly if a blocker prevented completion.
Do not end with prose-only output. A safe-output tool call is required for successful workflow completion.
Your Mission
Create a concise dictation instruction file at DICTATION.md that:
- Contains a glossary of exactly 256 project-specific terms extracted from documentation
- Provides instructions for fixing speech-to-text errors (ambiguous terms, spacing, hyphenation)
- Provides instructions for "agentifying" text: removing filler words (humm, you know, um, uh, like, etc.), improving clarity, and making text more professional
- Does NOT include planning guidelines or examples (keep it short and focused on error correction and text cleanup)
- Includes guidelines to NOT plan or provide examples, just focus on fixing speech-to-text errors and improving text quality.
Task Steps
1. Run NLP Word-Frequency Histogram
Run the following Python script to compute a word-frequency histogram of code-formatted tokens across all documentation files. Use the output as the primary source for selecting the 256 glossary terms — prefer tokens with high frequency that are project-specific (not generic English words).
python3 - <<'EOF'
import re
from pathlib import Path
from collections import Counter
docs = Path("docs/src/content/docs")
tokens = Counter()
for md_file in docs.rglob("*.md"):
text = md_file.read_text(errors="replace")
# Collect backtick-quoted technical tokens
tokens.update(re.findall(r'`([^`\n]+)`', text))
# Also collect hyphenated/dotted/underscored identifiers
tokens.update(re.findall(r'\b([\w][\w\-\.]{2,}[\w])\b', text))
print("Frequency histogram — top 500 project tokens:")
for tok, n in tokens.most_common(500):
if len(tok) > 2:
print(f" {n:5d} {tok}")
EOF
2. Scan Documentation for Project-Specific Glossary
Use search to efficiently discover documentation covering different areas of the project, then read the returned files to extract vocabulary. This is more targeted than scanning all files with find:
search("workflow configuration frontmatter engine permissions")— core workflow conceptssearch("safe-outputs create-pull-request tools MCP server")— tools and integrationssearch("compilation CLI commands audit logs")— CLI and developer toolssearch("network sandbox runtime activation triggers")— advanced features
Read each returned file path for its content, then also scan any remaining documentation files in docs/src/content/docs/ to ensure broad coverage.
Focus areas for extraction:
- Configuration: safe-outputs, permissions, tools, cache-memory, toolset, frontmatter
- Engines: @copilot, claude, codex, custom
- Bot mentions: @copilot (for GitHub issue assignment)
- Commands: compile, audit, logs, mcp, recompile
- GitHub concepts: workflow_dispatch, pull_request, issues, discussions
- Repository-specific: agentic workflows, gh-aw, activation, MCP servers
- File formats: markdown, lockfile (.lock.yml), YAML
- Tool types: edit, bash, github, playwright, web-fetch, web-search
- Operations: fmt, lint, test-unit, timeout-minutes, runs-on
Exclude: makefile, Astro, starlight (tooling-specific, not user-facing)
3. Create the Dictation Instructions File
Create DICTATION.md with:
- Frontmatter with name and description fields
- Title: Dictation Instructions
- Technical Context: Brief description of gh-aw
- Project Glossary: 256 terms, alphabetically sorted, one per line
- Fix Speech-to-Text Errors: Common misrecognitions → correct terms
- Clean Up and Improve Text: Instructions for removing filler words and improving clarity
- Guidelines: General instructions as follows
You do not have enough background information to plan or provide code examples.
- do NOT generate code examples
- do NOT plan steps
- focus on fixing speech-to-text errors and improving text quality
- remove filler words (humm, you know, um, uh, like, basically, actually, etc.)
- improve clarity and make text more professional
- maintain the user's intended meaning
4. Create Pull Request
Use the create-pull-request tool to submit your changes with:
- Title: "[docs] Update dictation skill instructions"
- Description explaining the changes made to DICTATION.md
Guidelines
- Scan only
docs/src/content/docs/**/*.mdfiles - Extract 256 terms (240-270 acceptable)
- Exclude tooling-specific terms (makefile, Astro, starlight)
- Prioritize frequently used project-specific terms (use NLP histogram from Step 1)
- Alphabetize the glossary
- No descriptions in glossary (just term names)
- Focus on fixing speech-to-text errors, not planning or examples
Success Criteria
- ✅ File
DICTATION.mdexists - ✅ Contains proper frontmatter (name, description)
- ✅ Contains 256 project-specific terms (240-270 acceptable)
- ✅ Terms extracted from documentation only
- ✅ Focuses on fixing speech-to-text errors
- ✅ Includes instructions for removing filler words and improving text clarity
- ✅ Pull request created with changes