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.

70

Quality

86%

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

72%

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

The body is well-structured, concise, and free of concept padding, but its actionability is undercut by conversion commands that reference an unbundled script, and the workflow lacks an explicit validation checkpoint. Tightening those two areas would lift the weaker dimensions.

Suggestions

Ship the referenced convert_heavy_file.py in a scripts/ bundle (or replace the command with self-contained, dependency-free conversion commands) so the primary guidance is actually runnable.

Add an explicit validation/quality-gate checkpoint in the process — e.g., after indexing, verify the artifact is complete and well-formed before analysis, with a 're-request the artifact if quality is poor' retry step.

If no script is bundled, make the fallback (markdown/CSV export or small excerpt) the primary instruction rather than leading with a command that depends on a file the user may not have.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — no generic explanations of what PDF/DOCX/XLSX are, and the 'Problem' line conveys a skill-specific client limitation rather than padding. Every section earns its tokens.

3 / 3

Actionability

Commands are concrete and specific ('python convert_heavy_file.py /absolute/path/to/file.pdf'), but the referenced script is not shipped in any scripts/ bundle, so the primary path is not actually copy-paste runnable — it lands at 'some concrete guidance but incomplete' rather than fully executable.

2 / 3

Workflow Clarity

There is a clear numbered sequence (ask for artifact → offer commands → index → analyze), but no explicit validate/fix/retry feedback loop; the indexing step's quality check is only an implicit checkpoint, so it sits above 'unclear' but below the explicit-checkpoint anchor of a 3.

2 / 3

Progressive Disclosure

A single short (~50-line), single-purpose file with clean sections (Problem, Triggers, Process, Commands, Client Rules) and no external references — the simple-skill scoring note allows a 3 for well-organized content without bundle files.

3 / 3

Total

10

/

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 precise, trigger-rich, and fully self-describing — it states concrete actions, natural trigger terms, explicit when/what guidance, and a distinct Claude-Desktop-specific niche. Voice is correctly third person. No changes needed.

DimensionReasoningScore

Specificity

Names multiple concrete actions ('read, analyze, summarize, or extract') and concrete artifacts ('converted markdown or CSV artifact'), matching the anchor for listing multiple specific concrete actions rather than the partial coverage of a 2.

3 / 3

Completeness

Explicitly answers both what ('Avoid raw ingestion... Ask for a converted markdown or CSV artifact first, or give... conversion commands') and when ('Use in Claude Desktop when a user asks to read...'), satisfying the explicit-trigger requirement for a 3.

3 / 3

Trigger Term Quality

Includes natural user phrasing ('asks to read, analyze, summarize, or extract') plus a full enumeration of common file types ('PDF, DOCX, PPTX, XLSX, CSV, or TSV'), giving good coverage of terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

Tied to a specific client ('Claude Desktop') and a narrow niche (heavyweight files, avoiding raw ingestion) with distinct file-type triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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.