heavy-file-ingestion

Use 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, generate a lightweight index, and only spend model tokens on the compressed artifact. Trigger on requests like "read this PDF", "look through this spreadsheet", "summarize this deck", or any time raw file ingestion would waste tokens.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

86%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.

The body is a tight, executable overview with real bundle files correctly wired in and a clear convert-then-index-then-escalate workflow. Its only soft spot is mild editorializing in the Notes section and implicit rather than spelled-out validation of the generated artifact.

Suggestions

Tighten the Notes section: keep the deterministic-first policy but drop the comparative sub-agent commentary, which explains a tradeoff Claude can already infer.

Add an explicit validation checkpoint in the Process, e.g. 'Verify the generated index.md lists expected artifacts before reading outputs; if conversion produced nothing, retry with --prefer markitdown before escalating to a model.'

Make the index-quality feedback loop concrete by stating what a 'weak extraction' flag looks like (e.g. empty pages, low text density) so the fallback trigger is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence (no 'what is a PDF' padding), but the Notes section editorializes slightly about sub-agents and deterministic passes, a minor instance of over-explanation that could be trimmed.	4 / 5
Actionability	Provides two fully executable, copy-paste-ready bash blocks with exact uv-run invocations and dependency specs, plus a concrete tiered fallback procedure covering the common cases.	5 / 5
Workflow Clarity	The Process is clearly sequenced (identify path -> run converter -> read index -> read flagged outputs -> tiered fallback), and the index-first / quality-flags-then-escalate pattern acts as a checkpoint, but explicit validate-and-retry steps for the conversion artifact itself are only implicit.	4 / 5
Progressive Disclosure	A well-organized overview body points to a single one-level-deep, clearly signaled reference (references/open-source-stack.md) and keeps bulk logic in the bundled script rather than inlining it; the referenced file is real and appropriately scoped.	5 / 5
	Total	18 / 20 Passed

Description

100%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.

The description is exemplary: it pairs an explicit trigger with concrete actions, natural user phrases, file extensions, and a distinct convert-first niche, all in third person. No vague fluff or over-claims are present.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'read, analyze, summarize, or extract', 'Convert the file into markdown or CSV first', 'generate a lightweight index', 'only spend model tokens on the compressed artifact' — giving comprehensive coverage rather than minor gaps.	5 / 5
Completeness	Opens with an explicit 'Use when...' trigger and concrete trigger phrases, then states the what (convert, index, spend tokens on the compressed artifact), satisfying both what and when explicitly.	5 / 5
Trigger Term Quality	Combines natural user phrases ('read this PDF', 'look through this spreadsheet', 'summarize this deck') with explicit file extensions and synonyms (PDF, DOCX, PPTX, XLSX, CSV, TSV), matching the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (heavyweight-file ingestion with a convert-before-reading policy) with distinct, specific triggers and named file types, giving minimal overlap with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: NateBJones-Projects/OB1
Path: skills/heavy-file-ingestion/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.