CtrlK
BlogDocsLog inGet started
Tessl Logo

heavy-file-ingestion-claude-code

Use in Claude Code 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.

72

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

80%

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

The body is lean and highly actionable with concrete commands and a routing decision tree, but it lacks an explicit conversion-validation checkpoint and references bundle files (scripts/convert_heavy_file.py, references/open-source-stack.md) that are not present in the skill bundle.

Suggestions

Add an explicit validation checkpoint after running the converter (e.g., verify index.md was produced and check for scan/low-density warnings before reading the artifact) to turn the implicit routing into a validate-then-proceed loop.

Ship the referenced bundle files or remove the references: create scripts/convert_heavy_file.py and references/open-source-stack.md, or drop the 'Bundled References' section so navigation is not broken.

Fix the Process list numbering so steps render as a clean 1–7 sequence, making the workflow order unambiguous.

DimensionReasoningScore

Conciseness

The body is lean: it assumes Claude's competence, never explains what a PDF or library is, and every section (Problem, Trigger Conditions, Process, Client Rules) earns its place; the only mild redundancy is the repeated converter command in the uv fallback block.

3 / 3

Actionability

Provides copy-paste-ready commands ('python scripts/convert_heavy_file.py /absolute/path/to/file.ext' and the full uv run block) plus a concrete decision tree (read_extracted_artifact, install_dependency_and_retry, cheap_model_or_stronger_converter).

3 / 3

Workflow Clarity

The process is sequenced and includes a retry route (install_dependency_and_retry), but there is no explicit validation/verify checkpoint confirming the conversion succeeded before consuming the artifact, and the numbered list is inconsistently authored (five '1.' items followed by 2 and 3), leaving checkpoints implicit.

2 / 3

Progressive Disclosure

The body is well-organized and signals one-level-deep references clearly ('references/open-source-stack.md explains the tool choices and fallback strategy'), but neither the referenced references/ directory nor the scripts/convert_heavy_file.py file actually exists in the bundle, so the signaled navigation is broken.

2 / 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 concise, concrete, and answers both what and when with an explicit trigger clause and natural file-type keywords. It is written in the appropriate imperative/third-person voice and occupies a distinct niche.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'read, analyze, summarize, or extract', 'Convert the file into markdown or CSV', 'generate a lightweight index' — matching the top anchor for specific concrete actions.

3 / 3

Completeness

Explicitly answers both what (convert to markdown/CSV, generate index, spend tokens only on the artifact) and when ('Use in Claude Code when a user asks to read, analyze, summarize, or extract from a heavyweight file'), with an explicit trigger clause.

3 / 3

Trigger Term Quality

Names the file types users would actually say ('PDF, DOCX, PPTX, XLSX, CSV, or TSV') alongside natural verbs ('read, analyze, summarize'), giving good coverage of natural trigger terms.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche — heavyweight-file ingestion via local conversion plus indexing — with distinct triggers unlikely to collide with other skills.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

14

/

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.