Tessl • The management layer for AI agent skills

SkillPublic

askyourpdf

AskYourPDF integration. Manage data, records, and automate workflows. Use when the user wants to interact with AskYourPDF data.

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/askyourpdf/SKILL.md

Quality

Content

57%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 strong operational guide for the Membrane CLI workflow: executable install/auth/connect/run commands, a useful actions catalog, and solid connection error-handling. Its main weaknesses are generic filler sections, dangling step references ('skip to Step 2', '1b' with no '1a'), an actions table with an empty Description column, and everything being inlined with no reference files for the bulk API material.

Suggestions

Fix the broken sequence references: label the workflow steps explicitly (Step 1, Step 2...) so 'skip to Step 2' and '1b' resolve, or convert them to section-name links.

Populate the empty Description column of the Popular actions table (or remove it) and add one worked end-to-end example with realistic values (connect → find action → run with --input).

Trim the conceptual filler — the 'who uses AskYourPDF' intro, the unexplained entity tree, and 'Use action names and parameters as needed.' — and consider moving the action catalog and proxy flag reference into a separate reference file.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational commands, but it pads with content Claude doesn't need: the marketing-style app intro ('primarily used by students, researchers, and professionals'), an unexplained entity tree (PDF Document → Pages, Chat History, Annotations) that instructs nothing, and filler like 'Use action names and parameters as needed.' This matches anchor 3 ('mostly efficient but includes some unnecessary explanation'), not 4, because several such sections would need trimming.	3 / 5
Actionability	The skill gives concrete, executable commands throughout — 'npm install -g @membranehq/cli@latest', 'membrane connection ensure "https://askyourpdf.com/" --json', 'membrane action run <actionId> --connectionId=... --input ...', plus a full proxy flags table. It falls short of anchor 5 because the Popular actions table has an entirely empty Description column and there is no worked end-to-end example with realistic values.	4 / 5
Workflow Clarity	The implicit sequence (install → login → connect → poll/error-handle → search actions → run → proxy fallback) is present with genuinely good error-recovery for the connection flow (BUILDING polling, CLIENT_ACTION_REQUIRED handling, CONFIGURATION_ERROR guidance). However, 'skip to Step 2' references a step that is never labeled, and '#### 1b.' has no corresponding '1a'/Step 1 heading — dangling references that break navigation, matching anchor 3 rather than 4.	3 / 5
Progressive Disclosure	Section headers are clear and there are no nested references, but the ~175-line body inlines everything — including a 17-row API-style action table and a full proxy flag reference that would fit better in separate reference files. With no bundle files present and no external references, this matches anchor 3 ('some structure... content that should be separate is inline'), not 4.	3 / 5
	Total	13 / 20 Passed

Description

37%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 names the target app and includes an explicit 'Use when' clause, but its capability language is generic buzzword filler ('Manage data, records, and automate workflows') with no concrete AskYourPDF-specific actions or natural trigger terms like 'PDF' or 'document questions'. It is serviceable but reads like a template and would both under-trigger for real PDF-Q&A requests and over-trigger for generic data-management requests.

Suggestions

State the app's actual capabilities concretely, e.g. 'Upload PDFs, chat with documents, search and summarize content, and manage knowledge bases via AskYourPDF'.

Replace the circular trigger ('when the user wants to interact with AskYourPDF data') with natural user phrasing such as 'Use when the user wants to ask questions about a PDF, summarize a document, or search a document knowledge base'.

Cut the buzzword phrase 'Manage data, records, and automate workflows' — it adds no specific information and raises conflict risk with generic data skills.

Dimension	Reasoning	Score
Specificity	The description names the domain ('AskYourPDF integration') but the stated actions — 'Manage data, records, and automate workflows' — are generic buzzwords with no concrete capability (no 'chat with documents', 'summarize PDFs', or 'search knowledge bases'). This matches anchor 2 ('Names the domain but actions are minimal or generic'), not 3, since no specific concrete action is stated.	2 / 5
Completeness	An explicit 'Use when...' clause is present ('Use when the user wants to interact with AskYourPDF data'), ruling out anchor 2 (which requires no 'when'), but the 'what' is vague ('Manage data, records, and automate workflows') and the 'when' is circular — it restates the app name rather than giving concrete triggers. It sits between anchor 3 and anchor 4 (both present, 'when' could be more specific), landing at 3.	3 / 5
Trigger Term Quality	The only keywords are the product name 'AskYourPDF' and the generic 'data'; natural phrases users would say ('PDF', 'ask questions about my document', 'knowledge base') are absent. A user wanting PDF Q&A would not naturally utter these words, matching anchor 2 rather than 3's 'some relevant keywords'.	2 / 5
Distinctiveness Conflict Risk	Tying the description to the named app 'AskYourPDF' gives it some distinctiveness, but 'Manage data, records, and automate workflows' would plausibly trigger for almost any data-management or automation skill. This matches anchor 3 ('Somewhat specific but could still overlap with similar skills'), not 4, because the broad action phrasing creates real overlap risk.	3 / 5
	Total	10 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/askyourpdf/SKILL.md
Revision: f484c82

Reviewed: 16 days ago

Discovery Implementation Validation

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.

askyourpdf

Table of Contents

Is this your skill?