CtrlK
BlogDocsLog inGet started
Tessl Logo

gatherup

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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/gatherup/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 content is actionable and well-structured with a strong connection workflow, but it loses points on workflow clarity for exposing destructive delete operations without any verification or confirmation guidance. Tightening the intro and adding a worked example would further improve it.

Suggestions

Add explicit confirmation/validation guidance for destructive actions (delete-customer, delete-business): verify the record exists first, confirm with the user before deletion, and check the result for success.

Trim the opening "GatherUp is a customer feedback..." paragraph and the auth-plumbing aside to reduce padding while keeping the essential setup steps.

Include one fully worked end-to-end example with concrete values (e.g., creating a connection, then running get-online-reviews with a real connection id and parsing the output) to close the placeholder gap.

DimensionReasoningScore

Conciseness

The body is mostly efficient command examples and tables, with only minor over-explanation (the opening "what GatherUp is" paragraph and the "so you can focus on the integration logic rather than auth plumbing" aside). It is not 5 because of that small amount of padding, and not 3 because the bulk is tight and executable.

4 / 5

Actionability

It provides concrete, copy-paste-ready membrane CLI commands (install, login, connection ensure/get, action list/run, request) plus a populated actions table and proxy-flag table. It is not 5 because examples rely on placeholders (CONNECTION_ID, actionId) with no fully worked end-to-end example using real values.

4 / 5

Workflow Clarity

The connection workflow is well-sequenced with state checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) and a re-poll feedback loop, but the skill lists destructive actions (delete-customer, delete-business) as popular actions with no validation/confirmation guidance. Per the rubric cap, missing validation for destructive operations caps this at 3 even though the connection flow is strong.

3 / 5

Progressive Disclosure

It is a single, well-organized file with clear section headers and inline tables appropriate for a CLI skill, and no bundle files exist to reference. It is not 5 because the popular-actions and proxy-flag tables could plausibly live in a reference file, and not 3 because structure and placement are good with no buried references.

4 / 5

Total

15

/

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 is brand-specific and includes an explicit Use-when clause, but it is thin on concrete capabilities and natural trigger synonyms. Expanding the action list and trigger phrases would raise specificity and completeness.

Suggestions

Replace the generic "Manage Organizations" with concrete capabilities the skill actually exposes (e.g., get online reviews, send feedback requests, manage customers and businesses).

Broaden the when-clause with natural trigger phrases users would say, such as "Use when the user wants to fetch GatherUp reviews, send feedback requests, or manage customers and business locations."

Add common synonyms/file-format-style cues (reviews, customer feedback, ratings, testimonials) so the description triggers on natural user language rather than only the brand name.

DimensionReasoningScore

Specificity

The description names the GatherUp domain but offers only one generic action ("Manage Organizations"), with no comprehensive list of concrete capabilities. It sits between anchor 2 and 3 but leans toward 2 because the single action is minimal and generic rather than truly concrete.

2 / 5

Completeness

It has both a "what" ("GatherUp integration. Manage Organizations.") and an explicit "when" ("Use when the user wants to interact with GatherUp data."), but the "when" trigger is generic rather than listing concrete trigger phrases. It is not 5 because the when-clause lacks concrete triggers, and not 3 because both what and when are explicitly present.

4 / 5

Trigger Term Quality

It includes the specific, relevant keyword "GatherUp" (repeated) and "interact with GatherUp data", but is missing natural variations or synonyms a user might say (reviews, customer feedback, ratings). This matches anchor 3 (some relevant keywords, missing common variations) better than 2 because the brand term is specific rather than generic.

3 / 5

Distinctiveness Conflict Risk

"GatherUp" is a specific named product, giving it a clear niche with distinct triggers and minimal risk of triggering for the wrong skill. It is not lower because the brand-specificity makes conflict risk negligible.

5 / 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.