heavy-file-ingestion-codex

Use in Codex when a user asks to read, analyze, summarize, or extract from a heavyweight file such as PDF, DOCX, PPTX, XLSX, CSV, or TSV. Convert the file into markdown or CSV first with the bundled script, generate a lightweight index, and only spend model tokens on the compressed artifact.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%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.

Concise, well-structured body with concrete commands and a clear convert-then-index workflow including failure branches. The main defect is that the referenced bundle files (the converter script and the open-source-stack reference) are absent, breaking both actionability and navigation.

Suggestions

Bundle scripts/convert_heavy_file.py so the primary conversion command is actually executable, or remove the command and inline the conversion steps.

Bundle references/open-source-stack.md (or remove the dangling reference) so the signaled one-level-deep navigation resolves.

Add an explicit validation checkpoint after conversion (e.g., confirm index.md was generated and is non-empty) before reading it, to lift workflow_clarity toward 5.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence ("Convert first, index second, reason last"), with no padding or explanation of what PDF/DOCX/etc. are, matching the score-5 anchor; it is not a 4 because every section earns its place.	5 / 5
Actionability	Concrete, copy-paste-ready commands are provided ("python scripts/convert_heavy_file.py /absolute/path/to/file.ext" and the uv-run variant) plus explicit index branches, fitting score-4; it is not 5 because the referenced converter script is not present in the bundle, so the primary command is not actually runnable as-is.	4 / 5
Workflow Clarity	A clear sequenced process (do not open raw first, run converter, read index.md, follow recommendation, use expensive context only after compression) with failure feedback branches ("manual_review", "cheap_model_or_stronger_converter") fits score-4; it is not 5 because there is no explicit checkpoint verifying the conversion succeeded before consuming the index.	4 / 5
Progressive Disclosure	The body is well-sectioned and signals a one-level-deep reference ("references/open-source-stack.md explains the tool choices and fallback tiers"), but that referenced file and scripts/convert_heavy_file.py do not exist in the bundle, so navigation breaks, fitting score-3 rather than 4 per the guideline to score against the actual bundle structure.	3 / 5
	Total	16 / 20 Passed

Description

95%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.

A strong, specific description that answers both what and when with concrete trigger terms and file extensions. Minor weakness is that the leading verbs (read/analyze/summarize/extract) are generic relative to the more distinctive convert-and-index actions.

Dimension	Reasoning	Score
Specificity	"Convert the file into markdown or CSV first with the bundled script, generate a lightweight index, and only spend model tokens on the compressed artifact" lists several concrete actions (convert, index, compress) with only minor coverage gaps, fitting the score-4 anchor rather than 5 because "read, analyze, summarize, or extract" are somewhat generic verbs.	4 / 5
Completeness	It explicitly states both what (convert to markdown/CSV, generate a lightweight index, spend tokens only on the compressed artifact) and when ("Use in Codex when a user asks to read, analyze, summarize, or extract from a heavyweight file such as ..."), matching the score-5 anchor with concrete trigger phrases.	5 / 5
Trigger Term Quality	"read, analyze, summarize, or extract ... PDF, DOCX, PPTX, XLSX, CSV, or TSV" covers natural user verbs plus a comprehensive set of file extensions and synonyms, matching the score-5 anchor; it is not a 4 because common variations are not missing.	5 / 5
Distinctiveness Conflict Risk	The heavyweight-file niche with explicit extensions and a convert-first/index-second methodology, scoped to Codex, gives a clear distinct trigger with minimal overlap, matching the score-5 anchor rather than 4 because the conflict risk is low.	5 / 5
	Total	19 / 20 Passed

Validation

87%

Warnings & errors only

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

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: NateBJones-Projects/OB1
Path: skills/heavy-file-ingestion/variants/codex/SKILL.md
Commit: e79e9cb

Reviewed: 11 days ago

Table of Contents

Discovery Implementation Validation

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.