CtrlK
BlogDocsLog inGet started
Tessl Logo

meta-pdf-intelligence

Use this meta-skill instead of answering directly when the user needs PDF analysis, pasted PDF excerpt analysis, digesting, comparison, or question answering that benefits from multi-skill orchestration across PDF extraction, summarization, cross-document synthesis, traceable evidence indexing, and memory capture.

63

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./src/opensquilla/skills/exp/meta-pdf-intelligence/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 appropriately concise and cleanly structured but functions only as an overview — the actionable workflow detail resides in the YAML rather than the markdown, leaving the body's actionability and workflow clarity thin.

Suggestions

Add a concrete fallback recipe in the body (e.g., the specific pdf-toolkit script names/commands and the memory_save invocation syntax) so the fallback is executable without reading the YAML.

Surface the core pipeline as an explicit numbered sequence (intake → extract → digest → synthesize → index → memorize) with a one-line validation or failure-handling note per step.

Briefly cross-reference the underlying skills (pdf-toolkit, summarize) by name in the body so the orchestration boundary is explicit to a reader of the markdown alone.

DimensionReasoningScore

Conciseness

The body is lean — a three-sentence overview plus a one-line fallback — with no padding and no explanation of concepts Claude already knows; every token earns its place.

5 / 5

Actionability

The body offers only high-level hints ('LLM should manually run pdf-toolkit scripts then summarize and memory_save') with no concrete commands, arguments, or step-level guidance; the executable detail lives entirely in the YAML frontmatter rather than the body.

2 / 5

Workflow Clarity

A rough sequence is sketched ('classifies the request, preserves file/page evidence, synthesizes across documents when needed, and stores a structured memory index'), but checkpoints and validation steps are implicit and the fallback path is underspecified.

3 / 5

Progressive Disclosure

The short body is well-organized with a title, overview paragraph, and a Fallback heading; no bundle files exist so the structure is appropriate, though the fallback could more explicitly signal the referenced skills/tools.

4 / 5

Total

14

/

20

Passed

Description

88%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, trigger-rich description that clearly states both capability and activation conditions with third-person voice. Minor gains are possible by adding file extensions and tightening overlap with constituent skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across the orchestration domain — 'PDF analysis, pasted PDF excerpt analysis, digesting, comparison, or question answering' plus 'PDF extraction, summarization, cross-document synthesis, traceable evidence indexing, and memory capture' — giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both what (multi-skill orchestration across extraction/summarization/synthesis/indexing/memory capture) and when ('Use this meta-skill instead of answering directly when the user needs PDF analysis...'), with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural-term coverage including synonyms ('PDF analysis', 'pasted PDF excerpt', 'digesting', 'comparison', 'question answering', 'PDF extraction'), but file extensions like '.pdf' and the bare plural 'PDFs' are absent.

4 / 5

Distinctiveness Conflict Risk

The meta-skill orchestration framing and 'pasted PDF excerpt analysis' niche are distinctive, but broad triggers like 'PDF analysis' and 'comparison' create minor overlap risk with the underlying pdf-toolkit and summarize skills.

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
TokenRhythm/opensquilla
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.