CtrlK
BlogDocsLog inGet started
Tessl Logo

add-pdf-reader

Add PDF reading to NanoClaw agents. Extracts text from PDFs via pdftotext CLI. Handles WhatsApp attachments, URLs, and local files.

65

Quality

82%

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

93%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 an exemplary operational skill: fully executable commands, a phased workflow with pre-flight idempotency check, explicit validation, and strong error-recovery guidance including a troubleshooting section. The only weakness is a missing failure branch for the build/test validation step. No bundle files exist, and the content is appropriately self-contained.

DimensionReasoningScore

Conciseness

Every section is operational (commands, merge contents, validation, verify, troubleshooting) with no explanation of concepts Claude already knows; the scanned-PDF note is novel domain knowledge, so every token earns its place per anchor 5.

5 / 5

Actionability

Fully copy-paste ready throughout: git remote add/fetch/merge with a package-lock.json conflict fallback, npm run build, npx vitest run, ./container/build.sh, platform-specific restart commands, and a log-grep for verification, matching anchor 5.

5 / 5

Workflow Clarity

Clear phased sequence (pre-flight, apply, verify) with explicit validation commands, a merge-conflict feedback loop, and a troubleshooting section; the minor gap is the absence of a failure/retry branch after the npm run build / vitest validation step, fitting anchor 4's "minor validation gaps" rather than 5's full feedback loops.

4 / 5

Progressive Disclosure

No bundle files exist and none are needed; the ~100-line procedure is self-contained with well-organized, clearly navigable sections, and the contents of merged files are listed rather than inlined, so per the rubric's simple-skill guidance well-organized sections merit a 5.

5 / 5

Total

19

/

20

Passed

Description

61%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 states a clear, third-person "what" with a named tool and concrete input sources, but omits any explicit "Use when" trigger guidance, which caps completeness and limits its discoverability. Trigger term coverage is decent but misses common variations like ".pdf" or "document extraction". Adding an explicit usage-trigger clause would resolve the main weakness.

Suggestions

Append an explicit trigger clause, e.g. "Use when a PDF is received via WhatsApp, referenced by URL, or present in the local workspace and its text is needed."

Add natural keyword variations such as ".pdf", "read a PDF", or "document" to broaden trigger matching.

Mention one more concrete capability (e.g. fetching PDFs from URLs with pdf-reader fetch) to lift specificity beyond a single extraction action.

DimensionReasoningScore

Specificity

"Extracts text from PDFs via pdftotext CLI" names the tool and one concrete action, and "Handles WhatsApp attachments, URLs, and local files" describes input sources, but capability coverage stays at 1-2 actions rather than the several specific actions of level 4.

3 / 5

Completeness

The "what" is clear ("Extracts text from PDFs via pdftotext CLI") but there is no "Use when..." clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3; "Handles WhatsApp attachments, URLs, and local files" only weakly implies when to use it.

3 / 5

Trigger Term Quality

Good natural-keyword coverage ("PDFs", "extracts text", "WhatsApp attachments") matching anchor 4, though common variations like ".pdf", "document", or "read a PDF" are missing, keeping it below the comprehensive level 5.

4 / 5

Distinctiveness Conflict Risk

"Add PDF reading to NanoClaw agents" scopes the skill to a specific system and the PDF-plus-WhatsApp niche is mostly distinct, but it lacks distinguishing trigger phrases and has minor overlap risk with generic PDF-reading skills, matching anchor 4 rather than the minimal-conflict level 5.

4 / 5

Total

14

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
jbaruch/nanoclaw-telegram
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.