CtrlK
BlogDocsLog inGet started
Tessl Logo

docparser

Docparser integration. Manage Organizations. Use when the user wants to interact with Docparser data.

56

Quality

65%

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/docparser/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 well-structured, mostly concise, and highly actionable with concrete CLI commands and an actions table. Its main weakness is the absence of validation/verification steps for the batch document operations it exposes.

Suggestions

Add a verification step after running batch operations (e.g., poll get-document-status or inspect the output field) so re-parse/re-integrate workflows include a validation checkpoint.

Replace placeholder paths in the proxy example with a concrete Docparser endpoint to close the actionability gap.

Consider splitting the popular-actions table and detailed connection state machine into a reference file so SKILL.md reads as a tighter overview.

DimensionReasoningScore

Conciseness

The body is mostly efficient commands, tables, and state-machine bullets with only minor padding (e.g., 'so you can focus on the integration logic rather than auth plumbing' and the agent-types aside). Efficient but not perfectly lean, so below the 5 anchor.

4 / 5

Actionability

Provides many copy-paste-ready membrane commands and a concrete popular-actions table, but examples lean on placeholders (CONNECTION_ID, <actionId>, /path/to/endpoint) and include one vague line ('Use action names and parameters as needed'). Mostly executable with minor gaps.

4 / 5

Workflow Clarity

The connection setup is well-sequenced with explicit state checks and a poll-after-user-action feedback loop, but batch operations (re-parse-documents, reintegrate-documents) have no validation/verification steps. The batch-ops-without-validation cap holds this at 3.

3 / 5

Progressive Disclosure

Single-file skill with no bundle references, but it is well-organized under clear section headers with no nested-reference problem and appropriately placed content. Missing the one-level-deep reference structure of the 5 anchor, leaving minor organization gaps.

4 / 5

Total

15

/

20

Passed

Description

62%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 covers both what and when and leverages a distinct product name, but it is thin on concrete actions and natural trigger synonyms. It is functional but could be sharpened with more specific verbs and user-facing terms.

Suggestions

Replace the generic 'Manage Organizations' with the concrete data actions the skill supports (e.g., parse documents, list/get parsed data, fetch documents by URL) to lift specificity.

Add natural trigger terms users actually say — 'documents', 'PDFs', 'parsing', 'data extraction' — alongside the product name to improve trigger_term_quality.

Expand the 'Use when...' clause with concrete triggers (e.g., 'Use when the user wants to parse PDFs or retrieve parsed data from Docparser') to reach explicit-trigger completeness.

DimensionReasoningScore

Specificity

Names the domain ("Docparser integration") and one concrete action ("Manage Organizations"), but coverage is not comprehensive and the action is fairly generic. Fits the 'names domain and 1-2 concrete actions' anchor better than the minimal/generic anchor at 2.

3 / 5

Completeness

Both a what ("Docparser integration. Manage Organizations.") and an explicit when ("Use when the user wants to interact with Docparser data.") are present, but the when clause is generic rather than listing concrete trigger phrases. Below the explicit-trigger 5 anchor.

4 / 5

Trigger Term Quality

The product name "Docparser" is a natural keyword a user would say, but the description lacks common variations or synonyms (parsing, documents, PDFs, data extraction). Matches 'some relevant keywords but missing common variations'.

3 / 5

Distinctiveness Conflict Risk

The unique named product "Docparser" gives a clear niche with minimal conflict risk, but the thin trigger phrasing ("interact with Docparser data") leaves minor overlap risk with other document skills. Not the comprehensive-trigger 5 anchor.

4 / 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
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.