CtrlK
BlogDocsLog inGet started
Tessl Logo

heavy-file-ingestion-claude-desktop

Use in Claude Desktop when a user asks to read, analyze, summarize, or extract from a heavyweight file such as PDF, DOCX, PPTX, XLSX, CSV, or TSV. Avoid raw ingestion of bulky files. Ask for a converted markdown or CSV artifact first, or give the user exact conversion commands to run outside Claude Desktop.

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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.

A well-structured, concise instruction skill with a clear gated workflow and concrete per-type guidance. Its main weakness is the reliance on a non-bundled conversion script, which slightly undercuts executability.

Suggestions

Either bundle scripts/convert_heavy_file.py or replace the named-script commands with self-contained, dependency-free conversion commands so the flagship guidance is directly executable.

Add an explicit extraction-quality validation loop (e.g., 'if conversion is incomplete or garbled, re-request a different format') to lift workflow clarity above 4.

Tighten the 'Problem' section and remove the restated tradeoff in Client Rules to reach a leaner conciseness score.

DimensionReasoningScore

Conciseness

Mostly lean with no padding about basic file concepts, but the 'Problem' framing and the restated tradeoff in Client Rules ('converting first is cheaper and usually better') are minor over-explanation that could be trimmed.

4 / 5

Actionability

Provides concrete per-type artifact mapping (PDF/DOCX→markdown, PPTX→slide outline, XLSX→CSV per sheet) and named commands, but the flagship 'python convert_heavy_file.py' commands depend on a script that is not bundled, a minor executability gap partly mitigated by the documented fallback.

4 / 5

Workflow Clarity

Clear numbered sequence from request to index to analysis, with an explicit gate ('Only then analyze') and a quality checkpoint ('any obvious extraction-quality problems') before proceeding; lacks a full validate-fix-retry loop so it stops short of 5.

4 / 5

Progressive Disclosure

A single ~50-line file with well-organized sections (Problem, Trigger Conditions, Process, Commands, Client Rules) and no need for external references, matching the simple-skill exception for a top score.

5 / 5

Total

17

/

20

Passed

Description

91%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 description that clearly conveys both capability and trigger conditions with comprehensive file-type coverage. Minor specificity gap from generic verbs keeps it just below a perfect score.

DimensionReasoningScore

Specificity

Names concrete actions ('read, analyze, summarize, or extract') plus a distinctive conversion-first behavior and exact-command offering, but the verbs are somewhat generic relative to the comprehensive multi-action anchor at 5.

4 / 5

Completeness

Explicitly states both what the skill does (avoid raw ingestion, request converted artifact, provide conversion commands) and when to use it ('Use in Claude Desktop when a user asks to...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Covers natural user verbs (read, analyze, summarize, extract) and the full set of file extensions (PDF, DOCX, PPTX, XLSX, CSV, TSV), matching the comprehensive coverage-with-extensions anchor.

5 / 5

Distinctiveness Conflict Risk

The Claude Desktop framing plus heavyweight-file conversion-first niche is mostly distinct, though it overlaps with general PDF/document extraction skills on the listed file types.

4 / 5

Total

18

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
NateBJones-Projects/OB1
Reviewed

Table of Contents

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.