CtrlK
BlogDocsLog inGet started
Tessl Logo

nyckel

Nyckel integration. Manage data, records, and automate workflows. Use when the user wants to interact with Nyckel 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/nyckel/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 a strongly actionable, well-structured CLI integration guide with clear auth and connection-state workflows and genuine feedback loops. Its main weaknesses are a wasted placeholder overview section, redundancy between the action-discovery sections, and a lack of concrete Nyckel-specific action examples that would make it fully copy-paste ready.

Suggestions

Delete or fill the empty 'Nyckel Overview' bullets so every section earns its tokens; if kept, populate 'Function / Input / Model / Label' with the concrete concepts instead of bare headers.

Replace the 'Popular actions' stub (which only re-issues the discovery command) with 3-5 concrete Nyckel actions (e.g. create/train a function, invoke a classification, manage labels) with sample --input JSON and the output field shape.

Promote the connection flow to an explicit numbered checklist ('1. Install -> 2. Login -> 3. connection ensure -> 4. Wait until READY -> 5. Search & run actions') so the validation/polling checkpoints read as a single coherent workflow.

DimensionReasoningScore

Conciseness

Most sections are lean command blocks with justified operational detail (auth, --wait polling, clientAction states) Claude would not know, but the placeholder 'Nyckel Overview' bullets ('Function / Input / Model / Label' with no content) and the redundant repetition of the action-list command under 'Popular actions' add waste, fitting 'mostly efficient but could be tightened'.

3 / 5

Actionability

It provides copy-paste-ready commands for install, login, connection ensure/get, action list, action run, and proxy with a full flags table, matching 'mostly executable guidance with minor gaps'; it falls short of 5 because 'Popular actions' only re-issues the discovery command and shows no concrete Nyckel action examples or sample inputs/outputs.

4 / 5

Workflow Clarity

The connection flow is clearly sequenced (install -> login -> connection ensure -> wait/poll -> handle clientAction -> search -> run) with state-based checkpoints (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR) and a poll-again feedback loop, matching 'clear sequence with most checkpoints'; it stops short of 5 because step numbering is loose ('1b' and implicit 'Step 2') rather than an explicit numbered checklist.

4 / 5

Progressive Disclosure

Content is well-organized into logical sections with clear headers and stays one level deep (no nested references, only an external docs link), matching 'good structure; most content appropriately placed'; it is not a 5 because the empty 'Nyckel Overview' section and inlined-but-redundant action-list blocks are minor organization gaps and the skill exceeds the under-50-line simple-skill threshold.

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 is distinct and correctly pairs a what-statement with an explicit 'Use when' trigger, but its action list is generic and it relies on a single brand keyword rather than varied natural triggers. Tightening the verbs and adding concrete Nyckel-specific use-case terms would lift the middle dimensions.

Suggestions

Replace generic verbs ('Manage data, records, and automate workflows') with concrete Nyckel capabilities, e.g. 'train and deploy custom ML models, classify and extract data, automate labeling workflows'.

Expand the 'Use when' clause with multiple natural trigger phrases and file/entity terms users actually say, e.g. 'Use when the user wants to train, classify, or extract data with Nyckel, or mentions Nyckel functions, models, or labels.'

Add synonyms/capability keywords (functions, models, labels, classification, training) so the trigger term coverage reaches the comprehensive anchor.

DimensionReasoningScore

Specificity

It names the Nyckel domain and lists actions ('Manage data, records, and automate workflows'), but those verbs are generic rather than concrete, fitting the 'names domain and 1-2 concrete actions but not comprehensive' anchor rather than the multi-specific-action anchor above.

3 / 5

Completeness

It states both what it does ('Nyckel integration. Manage data, records, and automate workflows.') and when to use it ('Use when the user wants to interact with Nyckel data.'), matching the 'has both what and when; when could be more explicit or specific' anchor; it falls short of a 5 because the triggers are not as concretely enumerated as the top anchor.

4 / 5

Trigger Term Quality

The natural trigger is essentially the brand name 'Nyckel' (repeated in 'Nyckel integration' and 'interact with Nyckel data') plus generic terms; this matches 'some relevant keywords but missing common variations or synonyms' rather than the broad multi-term coverage of a 4.

3 / 5

Distinctiveness Conflict Risk

'Nyckel integration' anchors a specific named SaaS niche with minimal conflict risk, but the generic 'manage data, records, automate workflows' phrasing carries minor overlap with other data/workflow skills, keeping it just below the clearly-distinct 5.

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.