[skills] Fix heavy file ingestion markdown lint

Author: justfinethanku

resources/heavy-file-ingestion-claude-code.zip

@@ -24,10 +24,10 @@ Heavy File Ingestion stops agents from wasting expensive context on raw PDFs, sl
 ## Installation
 
 1. Copy the entire [`heavy-file-ingestion`](./) folder into a place your AI client can access, not just `SKILL.md`. The skill expects the bundled `scripts/` and `references/` folders to stay next to it.
-2. For Claude Code, place the folder at `~/.claude/skills/heavy-file-ingestion/`.
-3. For Codex or Cursor, keep the folder in your workspace or copy the contents into that client's skills or rules location.
-4. Restart or reload the client so it picks up [`SKILL.md`](./SKILL.md).
-5. When you want the deterministic converters available, run the skill script with either:
+1. For Claude Code, place the folder at `~/.claude/skills/heavy-file-ingestion/`.
+1. For Codex or Cursor, keep the folder in your workspace or copy the contents into that client's skills or rules location.
+1. Restart or reload the client so it picks up [`SKILL.md`](./SKILL.md).
+1. When you want the deterministic converters available, run the skill script with either:
 
 ```bash
 uv run \
@@ -38,7 +38,7 @@ uv run \
   python skills/heavy-file-ingestion/scripts/convert_heavy_file.py /absolute/path/to/file.pdf
 ```
 
-6. If you already have `markitdown` installed and want to prefer it for rich document conversion, add `--prefer markitdown`.
+1. If you already have `markitdown` installed and want to prefer it for rich document conversion, add `--prefer markitdown`.
 
 ## Downloadable Variants
 

resources/heavy-file-ingestion-claude-desktop.skill

@@ -21,20 +21,20 @@ Agents waste money and context when they read heavyweight files raw. This skill
 ## Core Policy
 
 1. **Convert before reading.** Do not dump raw heavyweight files into model context if a deterministic converter can create a cheaper artifact.
-2. **Index before reasoning.** Read the generated `index.md` or `index.json` first. It should tell you what is in the file, how clean the extraction was, and whether escalation is justified.
-3. **Match the converter to the file type.**
+1. **Index before reasoning.** Read the generated `index.md` or `index.json` first. It should tell you what is in the file, how clean the extraction was, and whether escalation is justified.
+1. **Match the converter to the file type.**
    - PDFs and documents: markdown artifact
    - Presentations: markdown slide outline
    - Spreadsheets: CSV per sheet plus a markdown manifest
-4. **Escalate by cost tier, not instinct.**
+1. **Escalate by cost tier, not instinct.**
    - Tier 1: deterministic converter plus index
    - Tier 2: cheap model on the extracted artifact only if quality flags say the deterministic pass lost structure
    - Tier 3: expensive model only after the file has already been compressed into markdown, CSV, or a sampled subset
 
 ## Process
 
 1. Identify the file path, extension, and rough size.
-2. Run the converter script instead of reading the original file directly:
+1. Run the converter script instead of reading the original file directly:
 
 ```bash
 uv run \
@@ -45,15 +45,15 @@ uv run \
   python skills/heavy-file-ingestion/scripts/convert_heavy_file.py /absolute/path/to/file.ext
 ```
 
-3. If you already have `markitdown` installed and want to prefer it for PDF or DOCX conversion, rerun with:
+1. If you already have `markitdown` installed and want to prefer it for PDF or DOCX conversion, rerun with:
 
 ```bash
 python skills/heavy-file-ingestion/scripts/convert_heavy_file.py /absolute/path/to/file.ext --prefer markitdown
 ```
 
-4. Read the generated `index.md` first.
-5. Only read the extracted markdown or CSV outputs that the index says are worth reading.
-6. If the index flags weak extraction, use a cheap fallback:
+1. Read the generated `index.md` first.
+2. Only read the extracted markdown or CSV outputs that the index says are worth reading.
+3. If the index flags weak extraction, use a cheap fallback:
    - Try an alternate deterministic converter
    - Use a small model to rebuild only the structure or outline from the extracted artifact
    - Escalate to a stronger model only when the cheaper passes still leave critical ambiguity

resources/heavy-file-ingestion-codex.zip

@@ -20,14 +20,14 @@ Claude Code has the tools to convert files locally, so it should not waste conte
 ## Process
 
 1. Do not read the original heavyweight file directly into context if conversion is possible.
-2. Resolve the bundled converter relative to this skill directory: `scripts/convert_heavy_file.py`
-3. Run the converter first. Default command:
+1. Resolve the bundled converter relative to this skill directory: `scripts/convert_heavy_file.py`
+1. Run the converter first. Default command:
 
 ```bash
 python scripts/convert_heavy_file.py /absolute/path/to/file.ext
 ```
 
-4. If dependencies are missing, prefer:
+1. If dependencies are missing, prefer:
 
 ```bash
 uv run \
@@ -38,12 +38,12 @@ uv run \
   python scripts/convert_heavy_file.py /absolute/path/to/file.ext
 ```
 
-5. Read the generated `index.md` before reading any converted artifact.
-6. Use the index to decide the cheapest next step:
+1. Read the generated `index.md` before reading any converted artifact.
+2. Use the index to decide the cheapest next step:
    - `read_extracted_artifact`: read the markdown or CSV and continue
    - `install_dependency_and_retry`: install the missing deterministic dependency and rerun
    - `cheap_model_or_stronger_converter`: retry with a better converter or use a cheaper model only on the extracted artifact
-7. Only escalate to a stronger model after the file has already been compressed into markdown, CSV, or a short sampled subset.
+3. Only escalate to a stronger model after the file has already been compressed into markdown, CSV, or a short sampled subset.
 
 ## Client Rules
 
@@ -55,4 +55,3 @@ uv run \
 ## Bundled References
 
 - `references/open-source-stack.md` explains the tool choices and fallback strategy.
-

skills/heavy-file-ingestion/README.md

@@ -20,11 +20,11 @@ Claude Desktop does not have the same local shell workflow as coding agents, so
 ## Process
 
 1. Do not ingest the raw heavyweight file by default.
-2. First ask for the cheapest workable artifact:
+1. First ask for the cheapest workable artifact:
    - PDF or DOCX: markdown
    - PPTX: markdown slide outline
    - XLSX: CSV per sheet or a small sample plus sheet names
-3. If the user has not converted it yet, offer exact commands they can run outside Claude Desktop.
+1. If the user has not converted it yet, offer exact commands they can run outside Claude Desktop.
 
 ### Suggested Conversion Commands
 
@@ -41,16 +41,15 @@ If the script is not available, say so and ask the user for:
 - a CSV export
 - or a small representative excerpt
 
-4. Once the user provides the converted artifact, create a quick index:
+1. Once the user provides the converted artifact, create a quick index:
    - file type
    - sections, slides, or sheet names
    - row counts or page counts if available
    - any obvious extraction-quality problems
-5. Only then analyze the content.
+2. Only then analyze the content.
 
 ## Client Rules
 
 - Be explicit about the tradeoff: converting first is cheaper and usually better.
 - If the user insists on staying inside Claude Desktop, ask for a smaller excerpt rather than taking the whole file raw.
 - Use raw ingestion only for genuinely small files where conversion would cost more effort than it saves.
-

skills/heavy-file-ingestion/SKILL.md

@@ -20,13 +20,13 @@ Codex can run local commands and inspect files, so direct ingestion of bulky doc
 ## Process
 
 1. Do not open the raw heavyweight file as your first move if a deterministic conversion path exists.
-2. Run the bundled converter from this skill directory:
+1. Run the bundled converter from this skill directory:
 
 ```bash
 python scripts/convert_heavy_file.py /absolute/path/to/file.ext
 ```
 
-3. If the environment is clean and needs packages, prefer:
+1. If the environment is clean and needs packages, prefer:
 
 ```bash
 uv run \
@@ -37,12 +37,12 @@ uv run \
   python scripts/convert_heavy_file.py /absolute/path/to/file.ext
 ```
 
-4. Read `index.md` first, not the original file.
-5. Follow the index recommendation:
+1. Read `index.md` first, not the original file.
+2. Follow the index recommendation:
    - `read_extracted_artifact`: inspect the generated markdown or CSV
    - `cheap_model_or_stronger_converter`: retry with a better deterministic tool or use a cheaper model on the extracted artifact only
    - `manual_review`: tell the user the deterministic route failed and propose the next cheapest fallback
-6. Use expensive model context only after the file has already been compressed into a smaller artifact.
+3. Use expensive model context only after the file has already been compressed into a smaller artifact.
 
 ## Client Rules
 
@@ -54,4 +54,3 @@ uv run \
 ## Bundled References
 
 - `references/open-source-stack.md` explains the tool choices and fallback tiers.
-