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

82%

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

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and well-sectioned with concrete commands, but it is undermined by dangling bundle references (missing script and reference file) and a broken numbered list with no validation checkpoints. These gaps hold actionability, workflow clarity, and progressive disclosure at the mid-level.

Suggestions

Ship the referenced bundle files — create scripts/convert_heavy_file.py and references/open-source-stack.md — or remove the references so commands and links actually resolve.

Fix the Process numbering (the list restarts at '1.' three times) so the step sequence renders as a single ordered 1–7 workflow.

Add an explicit validation/checkpoint step (e.g. confirm index.md was generated and is non-empty before following its recommendation) with a fallback loop if conversion fails.

Dimension	Reasoning	Score
Conciseness	The body is lean — 'Convert first, index second, reason last' — and avoids explaining concepts Claude already knows; every section earns its place, with only minor restatement between Process and Client Rules.	3 / 3
Actionability	Concrete commands are provided ('python scripts/convert_heavy_file.py /absolute/path/to/file.ext' and the uv variant), but the referenced script does not exist in the bundle, so the commands are not truly executable, and the index.md recommendation labels are introduced without enough detail.	2 / 3
Workflow Clarity	A convert → index → read index → follow-recommendation sequence exists, but the numbered list restarts with repeated '1.' markers breaking the ordering, and there are no explicit validation or error-recovery checkpoints.	2 / 3
Progressive Disclosure	Sections are well organized and the one reference is clearly signaled ('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 to the deeper material is broken.	2 / 3
	Total	9 / 12 Passed

Description

100%

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 concise, specific, and answers both what the skill does and when to use it with explicit, natural trigger terms. It carves a clear niche around heavyweight-file ingestion in Codex.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'read, analyze, summarize, or extract', 'Convert the file into markdown or CSV first with the bundled script', 'generate a lightweight index' — rather than vague language.	3 / 3
Completeness	Explicitly states both what it does (convert → index → reason on compressed artifact) and when to use it via an explicit 'Use in Codex when a user asks...' trigger clause, so it is not capped at 2.	3 / 3
Trigger Term Quality	Covers natural user terms ('read, analyze, summarize, or extract from a heavyweight file such as PDF, DOCX, PPTX, XLSX, CSV, or TSV') that a user would plausibly say.	3 / 3
Distinctiveness Conflict Risk	Scoped to heavyweight file ingestion in Codex with a convert-first niche and distinct file-type triggers, making overlap with general file skills unlikely.	3 / 3
	Total	12 / 12 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: 6779106

Reviewed: about 18 hours 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.