CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

bexio

Bexio integration. Manage Organizations, Users. Use when the user wants to interact with Bexio data.

Quality

73%

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/bexio/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 highly actionable, with copy-paste-ready CLI commands covering the full install/auth/connect/discover/run/proxy workflow and a useful connection-state decision tree. Weaknesses are the dangling 'Step 2' cross-references, absent validation guidance for data-write operations, and some redundancy between the overview bullet list and the Popular actions table.

Suggestions

Fix the dangling cross-references: both 'skip to **Step 2**' mentions point to a step that is never labeled — either number the sections consistently (1. Connect, 2. Search/Run actions) or replace 'Step 2' with the actual section name.

Add validation checkpoints for write operations, e.g. re-fetch a record with the get-* action after create/update to confirm the result, and check the `output`/error fields before reporting success.

Trim the redundant 'Bexio Overview' bullet list (it duplicates the Popular actions table) and remove the filler line 'Use action names and parameters as needed' to tighten token efficiency.

DimensionReasoningScore

Conciseness

The body is mostly tight command examples and tables, but includes unnecessary content: the 'Bexio Overview' bullet list largely duplicates the Popular actions table, 'Use action names and parameters as needed' is filler, and the two-sentence intro about what Bexio is could be trimmed. This matches the 'mostly efficient but some unnecessary explanation' anchor rather than the 'minor instances of over-explanation' level above.

3 / 5

Actionability

Every section gives copy-paste-ready commands with real examples: 'npm install -g @membranehq/cli@latest', 'membrane connection ensure "https://www.bexio.com" --json', 'membrane action run <actionId> --connectionId=CONNECTION_ID --input \'{"key": "value"}\'', plus a concrete proxy flag table. The common cases (install, auth, connect, discover, run, proxy) are each covered by an executable example.

5 / 5

Workflow Clarity

A rough sequence exists (install → auth → connect → poll → search → run) with a good polling feedback loop for connection states, but both 'skip to **Step 2**' references point to a step that is never defined, and there are no validation or verification checkpoints for write operations (create/update contact, invoice, order). This fits 'steps listed but validation gaps; checkpoints missing or implicit' rather than the checkpoint-complete level above.

3 / 5

Progressive Disclosure

The single-file body is organized into clearly labeled sections (Install, Authentication, Connecting, Searching, Popular actions, Running, Proxy, Best practices) with a curated 'Popular actions' subset rather than the full API catalog — appropriate disclosure since discovery is delegated to 'membrane action list'. Minor gap: the ~22-row action table and proxy flag table are content that could live in a reference file, so it does not reach the well-signaled one-level-references level.

4 / 5

Total

15

/

20

Passed

Description

66%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 has an explicit 'Use when' trigger, a distinct niche (Bexio), and correct third-person voice, so routing will work well. It under-sells the skill's actual capabilities — only 'Organizations, Users' are mentioned while contacts, invoices, orders, quotes, projects, and timesheets dominate the body — which limits both specificity and natural trigger-term coverage.

Suggestions

List the real capabilities instead of just 'Organizations, Users', e.g. 'Manage Bexio contacts, invoices, orders, quotes, projects, and timesheets' — the body's own action table provides the vocabulary.

Add concrete trigger phrases to the 'when' clause, such as 'Use when the user mentions Bexio, or wants to create, find, or update contacts, invoices, orders, or projects in Bexio'.

DimensionReasoningScore

Specificity

The description names the domain ('Bexio integration') and two concrete object types ('Manage Organizations, Users'), but the verb 'manage' is generic and the coverage is far from comprehensive — the body shows contacts, invoices, orders, quotes, articles, projects, and timesheets are the core capabilities. This matches 'names domain and 1-2 concrete actions, but not comprehensive' rather than the 'several specific actions' level above.

3 / 5

Completeness

It explicitly answers both parts: what ('Bexio integration. Manage Organizations, Users.') and when ('Use when the user wants to interact with Bexio data.'), written in third person with no voice violation. The 'when' clause is explicit but generic — it lacks concrete trigger phrases like 'contacts, invoices, orders' — which is exactly the anchor-4 pattern ('when' could be more explicit or specific), not the concrete-trigger-phrases level above.

4 / 5

Trigger Term Quality

'Bexio' and 'Bexio data' are the natural core terms and are present, but common variations a user would actually say — 'Bexio contacts', 'invoice', 'quote', 'timesheet', 'project' — are absent, so keyword coverage misses most natural phrasings. This fits 'some relevant keywords but missing common variations or synonyms' rather than the 'good keyword coverage, a few natural terms missing' level.

3 / 5

Distinctiveness Conflict Risk

Bexio is a specific named SaaS product and the description repeats it in both the what and the when clause, so a user mentioning Bexio would route here with minimal conflict risk against any other skill. This clearly matches the 'clear niche with distinct triggers' anchor.

5 / 5

Total

15

/

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.

Validation — 15 / 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

Path

skills/bexio/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.