CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

74

Quality

92%

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

85%

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, actionable, and well-structured with executable commands and a single real reference, respecting token budget and Claude's intelligence. The main gap is that the workflow describes index-driven gating without making the validate-then-escalate feedback loop an explicit checkpoint.

Suggestions

Add an explicit validation checkpoint in the Process section, e.g. after running the converter: "Verify the index quality_flags; only proceed to read artifacts when no conversion_failed/dependency_missing flag is present."

Make the escalation feedback loop concrete with a retry step: "If quality flags indicate weak extraction, re-run with --prefer markitdown or an alternate converter before spending model tokens, then re-check the index."

State where converter output lands (e.g. the <source>.ob1/ directory containing index.md/index.json) so the read-index step is unambiguous about which files to open first.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it states policy and process without explaining what a PDF is or how libraries work, and every section (Problem, Trigger Conditions, Core Policy, Process, Output, Notes) earns its place with no padding.

3 / 3

Actionability

Provides a copy-paste-ready executable command (uv run --with pdfplumber ...) plus a concrete variant invocation with --prefer markitdown, and points to a real bundled script, matching the fully-executable score-3 anchor.

3 / 3

Workflow Clarity

The Process section gives a clear sequence (identify file, run converter, read index, then selective fallback) but lacks explicit validation checkpoints for the batch/conversion operation; the index-based quality-flag gating is implicit rather than a stated validate-then-proceed loop, so it sits at 2 rather than 3.

2 / 3

Progressive Disclosure

The body is a concise overview with a single clearly-signaled one-level reference to references/open-source-stack.md (a verified real file), and detailed conversion logic lives in the bundled script rather than inline, giving clean navigation.

3 / 3

Total

11

/

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 specific, triggers naturally, and clearly states both capability and usage conditions in third person. It is a strong, well-scoped trigger description with no padding.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "read, analyze, summarize, or extract" plus "Convert the file into markdown or CSV first, generate a lightweight index" — matching the score-3 anchor that lists several specific actions rather than vague verbs.

3 / 3

Completeness

Opens with an explicit "Use when..." trigger clause and then states both what it does (convert/index/compress) and when to fire, clearly answering what AND when as required for a 3.

3 / 3

Trigger Term Quality

Covers natural user phrasing like "read this PDF", "look through this spreadsheet", "summarize this deck" alongside concrete extensions (PDF, DOCX, PPTX, XLSX, CSV, TSV), giving broad coverage of terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

The heavyweight-file scope plus explicit cost-justification framing ("any time raw file ingestion would waste tokens") carves a clear niche unlikely to conflict with generic PDF or spreadsheet 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.