CtrlK
BlogDocsLog inGet started
Tessl Logo

unstructured

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

52

Quality

59%

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 ./skills/unstructured/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 content is action-oriented with solid executable CLI guidance and a well-handled connection state machine, but it carries some marketing padding, leaves a dangling step reference, and omits verification steps around destructive proxy operations. Tightening the prose and adding a worked Unstructured example would raise it.

Suggestions

Add a concrete worked example of a real Unstructured operation (e.g., partitioning a PDF) with actual command output instead of the generic '{"key": "value"}' placeholder.

Resolve the dangling 'skip to Step 2' reference by labeling steps consistently (Step 1a/1b/2) and merging the duplicated 'Searching for actions' and 'Popular actions' sections.

Add verification/error-handling guidance for proxy and action-run operations that can be destructive (POST/PUT/DELETE), such as checking the response status and error field before proceeding.

DimensionReasoningScore

Conciseness

The body is mostly efficient with concrete commands, but includes padding such as the marketing-style intro about data scientists, 'so you can focus on the integration logic rather than auth plumbing', and 'burn less tokens'.

3 / 5

Actionability

It provides concrete, executable CLI commands with flags throughout (login, connection ensure, action list/run, request) plus a flag table; the gap is that action examples use generic placeholders rather than a real Unstructured worked example.

4 / 5

Workflow Clarity

The connection-setup flow has good state-checkpoint polling and a retry feedback loop, but the destructive-capable proxy section (DELETE/PUT) lacks validation/verification guidance, and there is a dangling 'skip to Step 2' reference with duplicated action-listing sections.

3 / 5

Progressive Disclosure

Section structure is good and content is appropriately self-contained with no external references needed; minor gaps are the bare 'Unstructured Overview' bullet list and the duplicated 'Searching for actions' / 'Popular actions' sections.

4 / 5

Total

14

/

20

Passed

Description

57%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 answers both what and when with an explicit trigger clause, but the capability phrasing is generic and the trigger relies on the brand name with minor ambiguity. It is functional but could be sharpened with concrete document-processing verbs.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with concrete Unstructured operations such as 'partition documents, extract elements and layout, and download results'.

Strengthen the trigger with document-specific phrases: 'Use when the user wants to process PDFs, Word documents, or other files with Unstructured, or mentions partitioning, layout, or element extraction.'

Disambiguate the brand from the generic term 'unstructured data' by referencing the Unstructured.io platform or file types explicitly.

DimensionReasoningScore

Specificity

It names the domain ('Unstructured integration') but the actions 'Manage data, records, and automate workflows' are generic abstractions rather than concrete operations like partition or extract.

2 / 5

Completeness

It supplies both a 'what' ('Manage data, records, and automate workflows') and an explicit 'Use when the user wants to interact with Unstructured data' clause, but the 'when' is circular and could be more specific.

4 / 5

Trigger Term Quality

It includes the relevant keyword 'Unstructured data' but omits the natural document-processing phrases users would say (documents, PDFs, extraction, partition).

3 / 5

Distinctiveness Conflict Risk

It names a specific platform and gives a platform-specific trigger, making it mostly distinct; minor overlap risk comes from generic data/workflow phrasing and the ambiguity of 'unstructured data' as a common data-science term.

4 / 5

Total

13

/

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
membranedev/application-skills
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.