Name: flanks
Rating: 56.00000000000001 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

flanks

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

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

76%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 highly actionable with executable commands and a clearly sequenced connection workflow that includes a polling/validation loop. It loses points on progressive disclosure (everything inlined, no reference files) and minor verbosity from a repeated discovery section.

Suggestions

Remove the redundant 'Popular actions' block that re-states `action list`/`action run` already covered in 'Searching for actions' and 'Running actions'.

Move the proxy request flag reference into a separate references file (or trim it) and link to it, so the SKILL.md stays a concise overview (improves progressive_disclosure).

Add an explicit recovery/checklist step for CONFIGURATION_ERROR and SETUP_FAILED states to push the connection workflow to a full feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean command-and-flag reference material that assumes competence, though the inline options table and a few restated discovery instructions (the Popular actions section repeats action list/run) are mild padding.	4 / 5
Actionability	It provides copy-paste-ready commands for login, connection ensure/get, action list/run, and proxy requests with concrete flags and JSON examples covering the common cases.	5 / 5
Workflow Clarity	The connection flow is clearly sequenced with state handling and a polling/feedback loop (BUILDING -> CLIENT_ACTION_REQUIRED -> poll again -> READY), which is a genuine validation checkpoint; minor gaps (no explicit error-recovery checklist for CONFIGURATION_ERROR/SETUP_FAILED) keep it just below 5.	4 / 5
Progressive Disclosure	Content is well sectioned but everything is inlined in a single file with no bundle references; there are no separate reference files and the proxy-options table could live elsewhere, so structure is adequate rather than clearly split.	3 / 5
	Total	16 / 20 Passed

Description

51%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 correctly states the domain and includes a Use-when clause, giving it a functional but shallow trigger. It lacks specific actions and richer natural-language trigger phrases that would make it comprehensive.

Suggestions

List the concrete Flanks operations users actually perform (e.g., manage campaigns, ad sets, and ads; pull account and reporting data) instead of the generic "Manage data, records, and automate workflows".

Expand the Use-when clause with concrete trigger phrases users would naturally say (e.g., "Use when the user wants to manage Flanks campaigns, ad sets, ads, accounts, or reports").

Keep third person and avoid the meta line that bled into the body; ensure the description reads purely as a capability + trigger statement.

Dimension	Reasoning	Score
Specificity	Names the domain and lists a few concrete actions ("Manage data, records, and automate workflows") but the actions are generic and lack the concrete operations that characterize Flanks data work; coverage is shallow.	3 / 5
Completeness	It states what the skill does and includes a "Use when..." clause, but the trigger guidance is shallow and not paired with concrete trigger phrases, so the "when" is only weakly specified relative to the 5-anchor.	3 / 5
Trigger Term Quality	The phrase "Use when the user wants to interact with Flanks data" provides one natural trigger ("interact with Flanks data") but misses common synonyms and concrete entity terms like campaigns, ad sets, ads, or reports that users would actually say.	3 / 5
Distinctiveness Conflict Risk	The "Flanks" brand name plus "Flanks data" trigger gives it a clear niche and low overlap risk with other skills; only minor risk that generic "manage data/records/workflows" wording could bleed into adjacent integrations.	4 / 5
	Total	13 / 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/flanks/SKILL.md
Commit: f484c82

Reviewed: 5 days ago

Table of Contents

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.