CtrlK
BlogDocsLog inGet started
Tessl Logo

doc-reader

Read any common document/data file — PDF, Word (.docx), Excel (.xlsx/.xls), PowerPoint (.pptx), images (OCR), CSV/TSV, plain text, JSON/YAML/TOML, HTML/XML, and most source-code files. Use the `read_document` tool.

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./a_全网优秀资源/10_大模型/07_skill包/vibe_trading_skills/doc-reader/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 lean, highly actionable reference for a unified document reader, with concrete tool calls, a clear return envelope, and useful operational notes. Its only weaknesses are minor illustrative padding in the Workflows section and a fully inline structure that leaves progressive disclosure at good rather than excellent.

DimensionReasoningScore

Conciseness

The body is efficient and avoids explaining concepts Claude already knows (no 'what is a PDF' padding), with each table and notes block earning its place; it is not a 5 because the Workflows section contains somewhat illustrative scenario walkthroughs (paper summary, contract review) that could be trimmed.

4 / 5

Actionability

It provides copy-paste-ready read_document(...) calls across the common formats plus a concrete JSON return envelope and per-format extra-key table, fully covering the common cases per the top anchor.

5 / 5

Workflow Clarity

This is a simple single-action read-only skill where the action is unambiguous ('Always call the tool directly — do not run Python from bash'), and it includes an explicit OCR-empty checkpoint ('If OCR returns empty, tell the user; don't fabricate'), satisfying the simple-skill exception and the feedback-loop note.

5 / 5

Progressive Disclosure

Content is well-organized into clear sections (Purpose, Supported formats, Usage, Return envelope, Workflows, Notes) with no nested references and nothing that obviously belongs in a separate file; it is not a 5 because everything is inline with no one-level-deep reference split, and the body exceeds the <50-line simple-skill threshold.

4 / 5

Total

18

/

20

Passed

Description

65%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 strong on natural trigger terms and format coverage but is held back by a missing explicit 'Use when…' clause and by relying on a single action verb across a very broad file range. It is clear and well-written but stops just short of the top anchors on completeness and distinctiveness.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to read, extract text from, or inspect the contents of a document or data file' to lift completeness above 3.

Broaden the action vocabulary beyond 'Read' (e.g., 'extract text, OCR images, preview spreadsheet sheets') to raise specificity toward 4-5.

Narrow distinctiveness by signaling this is the unified fallback reader (e.g. 'single unified reader for any supported format') to reduce overlap with format-specific skills.

DimensionReasoningScore

Specificity

The description names the domain comprehensively ('any common document/data file') and lists many formats, but offers only a single concrete action verb ('Read') rather than several specific actions, matching the 'names domain and 1-2 concrete actions' anchor; it is not a 4 because there are not multiple distinct actions like extract/fill/merge.

3 / 5

Completeness

It clearly states what the skill does ('Read any common document/data file …') but lacks any 'Use when…' or equivalent explicit trigger guidance, so per the judging guideline completeness is capped at 3; it is not a 4 because the 'when' is entirely absent rather than merely weak.

3 / 5

Trigger Term Quality

It covers natural terms users say (PDF, Word, Excel, PowerPoint, images, CSV/TSV, plain text, JSON/YAML/TOML, HTML/XML, source-code) together with file extensions (.docx, .xlsx/.xls, .pptx), giving comprehensive coverage including synonyms and extensions per the top anchor.

5 / 5

Distinctiveness Conflict Risk

The phrase 'any common document/data file' is broad and overlaps with format-specific skills (PDF, Excel, presentation skills), fitting 'somewhat specific but could still overlap with similar skills'; it is not a 4 because the breadth keeps overlap risk moderate rather than minor.

3 / 5

Total

14

/

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
charliedream1/ai_quant_trade
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.