CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

kopai/create-live-page

Live page: a page in Claude that charts Kopai telemetry through the viewer's Kopai connector, refreshing as they watch. Use when the Kopai connector is attached and the user wants to watch, chart or keep an eye on traces, logs or metrics, even if they never say "live page". For a dashboard inside the Kopai UI, use create-dashboard.

Quality

95%

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

Overview
Quality
Evals
Security
Files

Quality

Content

100%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.

An exemplary skill body: a gated six-step workflow with per-step 'Done when' checkpoints, fully concrete queries and code, explicit error-state handling, and strict token discipline that delegates everything not Kopai-specific to the artifact-capabilities skill. The only reference (references/recipes.md) is real, one level deep, and accurately described in the body.

DimensionReasoningScore

Conciseness

The body is dense and prescriptive with no padding: every sentence instructs ('Choose granularity once, here, so the window divided by it, times the number of groups, stays under the aggregate cap'), and it explicitly delegates the runtime API to the artifact-capabilities skill rather than restating it ('The runtime API... belongs to the artifact-capabilities skill... take every API detail from there'). Rationales present (e.g. 'Ranking by error count keeps a service with one failed span from topping the chart') are non-obvious domain knowledge Claude cannot infer, not over-explanation. Not 4: nothing could be trimmed without losing a real instruction or constraint.

5 / 5

Actionability

Fully concrete throughout: exact tool names ('mcp__claude_ai_Kopai__query'), copy-paste-ready KopaiQuery JSON for the worked example, executable watchTool JS with the refetchInterval math spelled out ('refetchInterval equal to the query's granularity in milliseconds (5m → 300000)'), exact user-facing messages, and per-error-code handling. The undefined watchSection helper is explicitly justified ('watchSection is the page's own wrapper around mcp.watchTool: it reads result.payload.data, updates the section's "last updated" from result.cache?.storedAt, routes error events...'), satisfying the pseudocode exception. Not 4: the common case is covered end-to-end with concrete code and exact values.

5 / 5

Workflow Clarity

Six sequenced steps, each with an explicit 'Done when...' validation checkpoint, plus feedback loops ('on invalid_input, repair from the result's issues and call again'; zero rows means 'fix it in step 3, never publish an empty chart') and hard gates on the risky outward-facing action ('Publish only when step 1 found Kopai', 'build if you like, then refuse to publish'). This matches the anchor-5 pattern of clear sequence, explicit validation, error-recovery loops, and checklists. Not 4: no checkpoint is implicit or missing, including the publish gate and the final checklist ('every query has a watch, every state in the list has its message, and no observed value appears in the page source').

5 / 5

Progressive Disclosure

The body is a lean overview (definition, workflow, one worked example) with a single, well-signaled, one-level-deep reference whose contents are named inline ('a recipe in references/recipes.md (latency percentiles, log volume, one metric series, a fixed set of services)'); the bundle file exists and contains exactly those recipes, and the bulk runtime API is delegated to the separate artifact-capabilities skill. Not 4: there is no content inlined in SKILL.md that belongs in a reference, and navigation is unambiguous.

5 / 5

Total

20

/

20

Passed

Description

87%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.

A strong description that defines the artifact concretely, gives an explicit and thoughtful 'Use when' clause with natural trigger synonyms, and even disambiguates against the sibling create-dashboard skill. Voice is third person throughout. The only gaps are a few natural domain terms ('monitor', 'real-time') and a thinner action enumeration than the best anchor examples.

DimensionReasoningScore

Specificity

Concrete and mechanism-specific: 'a page in Claude that charts Kopai telemetry through the viewer's Kopai connector, refreshing as they watch' names the artifact, the data source, the per-viewer mechanism, and the live-refresh behavior, covering the single-purpose skill comprehensively. Not 3 (anchor example 'Processes PDF files and extracts content'): the behavior described is complete for this skill's niche, not 1-2 actions with gaps. Not 5: it does not enumerate multiple distinct operations the way 'Extract text and tables, fill forms, merge documents' does — the action surface is essentially 'chart telemetry, live'.

4 / 5

Completeness

Both halves are explicit: what — 'a page in Claude that charts Kopai telemetry through the viewer's Kopai connector, refreshing as they watch' — and when — a literal 'Use when...' clause with concrete trigger phrases (watch, chart, keep an eye on traces, logs or metrics) that even covers the unspoken case ('even if they never say "live page"'). This matches the anchor-5 example's structure exactly. Not 4: the 'when' clause is as explicit and specific as the rubric's best example, not merely adequate.

5 / 5

Trigger Term Quality

Natural trigger phrases are present and varied: 'Use when the Kopai connector is attached and the user wants to watch, chart or keep an eye on traces, logs or metrics, even if they never say "live page"' — covering synonyms (watch / keep an eye on) and all three telemetry types, plus the implicit 'live page' term. Not 5: common phrasings in this domain such as 'monitor', 'real-time', or 'telemetry dashboard' are absent, and 'dashboard' is deliberately routed elsewhere rather than its synonyms covered. Not 3: the terms present go well beyond a bare domain keyword.

4 / 5

Distinctiveness Conflict Risk

Clear niche with distinct triggers: it is scoped to the named 'Kopai' connector and live pages, and it actively disambiguates the nearest competing skill ('For a dashboard inside the Kopai UI, use create-dashboard'). Minimal conflict risk. Not 4: there is no residual overlap — the routing rule removes the one plausible collision.

5 / 5

Total

18

/

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.

Reviewed

On this page