CtrlK
BlogDocsLog inGet started
Tessl Logo

cekura-onboarding

Use when the user says "get started with Cekura", "set up Cekura", "onboard to Cekura", "I'm new to Cekura", "help me set up my agent", "how do I use Cekura", "walk me through Cekura", "configure my project", "first time using Cekura", or needs guidance on initial platform setup. Covers two onboarding paths: **testing** (default — build evaluators and run simulated calls) and **observability** (ingest production call logs and evaluate them).

72

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Risky

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, concise orchestration hub with strong workflow sequencing and validation gates. Its main weakness is that the phase files it delegates to are absent from the bundle, which both limits the body's standalone actionability and breaks the progressive-disclosure navigation it relies on.

Suggestions

Add the missing phaseN-*.md files referenced in the Phases table (phase0-path.md, phase2-agent.md, phase3-testing-metrics.md, etc.) so the delegated executable steps are actually reachable and the disclosure chain resolves.

Inline one minimal executable connection step (e.g. the first aiagents_list / projects_create call from api-quickstart.md) directly in SKILL.md so the body is actionable even before a phase file is read.

Verify every referenced path resolves to an existing file — including the ../cekura-create-agent/* sibling references — since broken links defeat progressive disclosure.

DimensionReasoningScore

Conciseness

Lean operational prose that assumes Claude's competence — no re-explanation of generic concepts, just Cekura-specific protocol (phase table, execution model, ID rules). Nearly every token earns its place; not the level below because there is no padded explanation of things Claude already knows.

3 / 3

Actionability

Gives concrete orchestration guidance (named tools like aiagents_list/projects_create, explicit announce/read/gate protocol) but the per-phase executable detail is delegated to phaseN-*.md files that are not present in the bundle, leaving key details missing — the 'some concrete guidance but incomplete' anchor. Not a 3 because the body itself contains no copy-paste-ready API call or executable step.

2 / 3

Workflow Clarity

Clear phased sequence in a table (Phase 0/2 shared, 3T-6T and 3O-6O branching) with explicit gate conditions, a verification gate per path, and a feedback loop ("If a call fails, fix the cause... never claim a step is done until the call succeeds"). Matches the explicit-validation-and-feedback-loops anchor.

3 / 3

Progressive Disclosure

The hub-and-spoke design is well-signaled and one level deep, and the two present references (api-quickstart.md, client-setup.md) are real and clearly linked. However, scored against the actual bundle, the 11 phaseN-*.md files the body centrally depends on are missing, so the intended navigation is broken in practice — the 'some structure but references not fully resolvable' level rather than the top anchor.

2 / 3

Total

10

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that pairs an explicit 'Use when...' trigger list with concrete per-path actions. It clearly answers both what the skill does and when to invoke it, with low conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across two paths — "build evaluators and run simulated calls" (testing) and "ingest production call logs and evaluate them" (observability) — matching the 'lists multiple specific concrete actions' anchor.

3 / 3

Completeness

Explicitly answers both what (two onboarding paths with their concrete actions) and when via a clear 'Use when the user says...' trigger clause, satisfying the top anchor.

3 / 3

Trigger Term Quality

Rich set of natural phrases a user would actually say ("get started with Cekura", "I'm new to Cekura", "walk me through Cekura", "configure my project", etc.), giving strong coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Tightly scoped to Cekura platform onboarding with Cekura-branded triggers, forming a clear niche unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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

relative_links

Relative link issues: 10 missing

Warning

Total

15

/

16

Passed

Repository
cekura-ai/cekura-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.