CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

nex-kmo-portefeuille-flow

Loodst een Vlaamse kmo door de kmo-portefeuille: subsidiabiliteit, aanvraag, betaling via het portaal en de bewijsstukken. Use when: Bereken het juiste subsidiepercentage en plafond voor je onderneming; Genereer een stappenplan voor een foutloze subsidieaanvraag; Stel een bewijsstukkenlijst op voor een VLAIO controle.

Quality

70%

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/nex-kmo-portefeuille-flow/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

43%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 reads more like a product landing page than an operational skill: it is well-sectioned and brief, but it describes what the skill does without providing the concrete data, sequenced workflow, or verification steps needed to actually execute a kmo-portefeuille application. Internal inconsistencies in the deadline figures further undermine its reliability as guidance.

Suggestions

Replace the descriptive "Wat het doet" bullets with a sequenced applicant workflow (eligibility check → pijler choice advies/opleiding → aanvraag within 14 days → eigen aandeel deposit within 30 days → evidence collection) with explicit verification checkpoints such as confirming percentages and plafonds on vlaio.be before submission.

Inline the actual decision data the skill claims to use: steunpercentages and plafonds per company size (klein/middelgroot/groot) and the list of still-subsidiabel advice types, instead of only naming that they exist.

Reconcile the conflicting deadline numbers ("binnen 13 dagen" in the Example vs "uiterlijk 14 kalenderdagen" and "Na 15 dagen" in the FAQ) and move date-sensitive facts like "sinds februari 2026" into a clearly labeled changelog/deprecated section.

DimensionReasoningScore

Conciseness

The body is short and mostly efficient, but "Wat het doet" restates the frontmatter description almost verbatim, promotional links ("This file is the public guide from Agensi", "More skills, including the paid catalog") add tokens with no operational value, and time-sensitive specifics ("sinds februari 2026", "binnen 13 dagen") are not placed in a deprecation/old-patterns section. This is 'mostly efficient but could be tightened' (anchor 3), not 4, because the padding and uncontextualized date-sensitive facts are more than minor.

3 / 5

Actionability

The core sections describe capabilities rather than instruct ("Checkt of je onderneming en je dienstverlener in aanmerking komen", "Bouwt de aanvraag op") without the actual decision data — no steunpercentages or plafonds per company size, no eligibility rules, no portal steps. A few concrete facts appear only in the FAQ (45% for cybersecurity, 30 dagen) and the deadline numbers conflict across sections ("binnen 13 dagen" vs "uiterlijk 14 kalenderdagen" vs "Na 15 dagen"), leaving guidance minimal and high-level; it is not a 3 because the specific steps needed to execute are largely absent.

2 / 5

Workflow Clarity

The four "Wat het doet" bullets imply a rough order (eligibility → application → payment → evidence) but the process is never laid out as a sequenced workflow, steps are poorly defined, and validation is limited to one generic remark ("verifieer altijd op vlaio.be"). This matches anchor 2 (rough sequence, many gaps, validation absent); it is not 3 because there is no actual step list with an order to follow, only capability descriptions.

2 / 5

Progressive Disclosure

The body is a flat, well-organized set of sections ("Wat het doet", "Gebruikssituaties", "Bekende beperkingen", "Example", "Questions") of roughly 45 content lines with no nested or dangling references — I verified that no references/, scripts/, or assets/ bundle files exist. Per the rubric's simple-skill note, a short skill with no need for external references can score 5 with well-organized sections, which this has.

5 / 5

Total

12

/

20

Passed

Description

82%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 strong: it clearly separates what the skill does from when to use it, uses natural Flemish trigger terms, and occupies a highly distinct niche. Its main deductions are the second-person/imperative voice in the trigger clause and a few missing natural keyword variations.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ("Bereken het juiste subsidiepercentage en plafond", "Genereer een stappenplan", "Stel een bewijsstukkenlijst op", "betaling via het portaal"), which fits anchor 4 with minor coverage gaps. However, the trigger clause uses second-person/imperative voice ("voor je onderneming", "Bereken", "Genereer") instead of third person, so the mandated 1-point penalty applies, giving 3; it is not a 2 because the actions are specific rather than minimal or generic.

3 / 5

Completeness

Explicitly answers both: the first sentence states what it does ("subsidiabiliteit, aanvraag, betaling via het portaal en de bewijsstukken") and an explicit "Use when:" clause gives three concrete trigger phrases. This matches the anchor-5 example structure exactly; score 4 would require the 'when' to be less explicit, which it is not.

5 / 5

Trigger Term Quality

Contains natural terms a Flemish SME owner would actually say: "kmo-portefeuille", "subsidiepercentage", "plafond", "subsidieaanvraag", "VLAIO controle", "bewijsstukken". Coverage is good but misses common variations such as "steunpercentage", "kmo-portefeuille aanvragen", and "erkende dienstverlener", so it sits at anchor 4 rather than 5, and above 3 because the key terms are specific and natural rather than generic.

4 / 5

Distinctiveness Conflict Risk

"Loodst een Vlaamse kmo door de kmo-portefeuille" carves out a clear niche (Flemish KMO-portefeuille subsidy administration) with distinct triggers ("VLAIO controle", "subsidiepercentage"). Minimal conflict risk with any other plausible skill; nothing pushes it toward anchor 4's 'minor overlap risk'.

5 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

NexaiGuy/nex-ai-skills

Path

skills/nex-kmo-portefeuille-flow/SKILL.md

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.