cekura-coordinator

Use when the user asks "what can Cekura do", "what commands are available", "help me with Cekura", "what skills do I have", "show me Cekura features", "what's available", "how do I use Cekura", or needs guidance on which Cekura skill to use for their task. Also relevant as the entry point when a user has just installed cekura-skills for the first time.

Quality

65%

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 ./cekura/skills/cekura-coordinator/SKILL.md

Quality

Content

75%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.

A well-built router skill: exact skill and command names, a per-need routing table with disambiguation rules, and sequenced user journeys make it fully actionable. Its main weakness is redundancy — the same routing information is presented in three overlapping sections (skills table, routing guide, Next Steps), inflating token cost without adding guidance. Organization is otherwise clean, with no bundle files and content appropriately inlined for a catalog skill.

Suggestions

Delete the "Next Steps" section — its list ("New to Cekura → cekura-onboarding", "Designing metrics → cekura-metric-design", ...) restates the skills table almost verbatim; the one useful line ("This skill routes — it doesn't perform tasks itself") belongs in the Purpose section.

Collapse the "Available Skills & Commands" tables into the "Routing Guide" so each destination is described exactly once by the user need it serves, removing the double lookup.

Trim the four "Typical User Journeys" to one representative example (the brand-new-user journey) — the others restate routing rules already covered by the table.

Dimension	Reasoning	Score
Conciseness	The routing information appears three times in different forms: the "Next Steps" list ("New to Cekura → cekura-onboarding", "Connecting an agent → cekura-create-agent", ...) duplicates the skills table nearly 1:1, and the Routing Guide overlaps it again. Not 2 because the tables are lean with no concept over-explanation or padding; not 4 because a full section is pure duplication.	3 / 5
Actionability	Every route is given as an exact, invocable name — skills ("cekura-eval-design", "cekura-self-improving-agent") and slash commands ("/improve-metric", "/setup-mcp", "/cekura-report") — and the routing table maps concrete user asks ("Create a metric that checks X" → "/create-metric") to specific destinations. For an instruction-only routing skill this is copy-paste ready.	5 / 5
Workflow Clarity	The routing flow is explicit ("After confirming the user's need, invoke the matching skill") and the four journeys are clearly sequenced ("Journey 1: 1. /setup-mcp → 2. cekura-onboarding → ..."). Not 5 because there are no validation/error-recovery checkpoints and three overlapping routing sources (skills table, routing guide, next steps) can suggest competing routes for the same ask; not 3 because the sequence and disambiguation rules (e.g. create-vs-update via "/create-metric") are explicit and routing is non-destructive so heavy validation is unneeded.	4 / 5
Progressive Disclosure	No bundle files exist, and for an index/catalog skill whose entire job is to hold the routing table inline, that placement is appropriate; sections are well organized with clear headers. Not 5 because the body runs ~150 lines with redundant sections (Next Steps, journeys) that could be trimmed or split, and not 3 because all inlined content is the catalog the skill needs at load time, clearly signaled and organized.	4 / 5
	Total	16 / 20 Passed

Description

55%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 excellent trigger coverage — natural, varied phrasings that clearly signal when to load the skill — but it is entirely a 'when' clause. It never states what the skill does (route/dispatch to the right Cekura skill or command), leaving the capability side implicit. The result is a description that triggers reliably but tells Claude little about the skill's function once loaded.

Suggestions

Open with an explicit 'what' statement in third person, e.g. "Routes users to the right Cekura skill or command based on what they need. Maintains a catalog of all available Cekura skills, slash commands, and user journeys." before the 'Use when' clause.

State the concrete capabilities once — routing, cataloging available skills/commands, and guiding first-time users — instead of leaving the function implied by triggers alone.

Narrow the overlap with cekura-onboarding: distinguish the first-install entry point (e.g. "first-time orientation questions") from onboarding's setup flow, so "I just installed, where do I start" doesn't ambiguously match both skills.

Dimension	Reasoning	Score
Specificity	The domain is clearly named (Cekura skills/commands), but the description never states an action the skill performs — only "needs guidance on which Cekura skill to use for their task", which is generic. Not 3 because no concrete actions (routing, cataloging) are explicitly stated; not 1 because the domain and scope are concrete.	2 / 5
Completeness	Only the 'when' is present — an extensive 'Use when...' list — while the 'what' (that this skill routes users to the right Cekura skill or command) is absent, matching anchor 2's "only 'when' is present without 'what'". Not 3 because anchor 3 requires a clear 'what'; not 1 because the when is explicit and the domain is identifiable.	2 / 5
Trigger Term Quality	Comprehensive natural trigger phrasings a user would actually say: "what can Cekura do", "what commands are available", "help me with Cekura", "what skills do I have", "show me Cekura features", "what's available", "how do I use Cekura", plus a first-install trigger. Not 4 because coverage of natural synonyms is already extensive with no obvious gaps for a help/routing skill.	5 / 5
Distinctiveness Conflict Risk	"Cekura" branding keeps it mostly distinct from non-Cekura skills. Not 5 because "help me with Cekura" and "entry point when a user has just installed cekura-skills" overlap with cekura-onboarding, and "what's available" is generic enough to compete with other catalog skills.	4 / 5
	Total	13 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: cekura-ai/cekura-skills
Path: cekura/skills/cekura-coordinator/SKILL.md
Commit: 66ac4c0

Reviewed: 8 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.