Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

metrics

System metrics, telemetry, and performance monitoring

Quality

59%

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 ./src/skills/bundled/metrics/SKILL.md

Quality

Content

65%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 highly actionable API reference with concrete executable code and commands, but it is a monolithic 330-line inlined document with padded console.log demos and no progressive disclosure into reference files. It works as a catalog but lacks workflow sequencing and file structure.

Suggestions

Move the bulk TypeScript API reference into a references/REFERENCE.md and keep SKILL.md as a concise overview with one-level-deep links.

Trim the repetitive console.log formatting blocks down to the essential method call plus a one-line note on returned fields.

For multi-step operations (e.g. set-alert-then-handle, export-then-analyze), add a short sequenced workflow with a validation checkpoint.

Dimension	Reasoning	Score
Conciseness	The API listing itself is on-topic, but every section pads a multi-line console.log formatting demo (System, API, WebSocket, Trade, Latency, Errors) that is illustrative and could be trimmed, fitting 'mostly efficient but includes some unnecessary explanation or could be tightened'.	3 / 5
Actionability	It provides copy-paste-ready TypeScript with real imports and full option objects, plus concrete chat commands with exact syntax, matching 'fully executable; copy-paste ready code or commands; specific examples cover the common cases'.	5 / 5
Workflow Clarity	This is a reference catalog of independent API calls rather than a multi-step process, so there is no sequenced workflow or validation checkpoints; it is organized but provides no workflow guidance, sitting at the 'steps listed but checkpoints missing' midpoint.	3 / 5
Progressive Disclosure	All ~330 lines are inlined in SKILL.md with no bundle files or external references, and the full TypeScript API reference arguably belongs in a separate REFERENCE.md; good section headers provide navigation, fitting 'some structure but content that should be separate is inline'.	3 / 5
	Total	14 / 20 Passed

Description

36%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 a terse domain label rather than a capability statement: it names the metrics/telemetry area but gives no concrete actions and no 'Use when' trigger guidance. It is distinguishable but thin on both specificity and completeness.

Suggestions

Add concrete action verbs, e.g. "Collect, query, and alert on system metrics, telemetry, and performance data".

Append an explicit trigger clause: "Use when monitoring system health, tracking latency/telemetry, or building a metrics dashboard."

Include natural synonyms users say (observability, latency, health checks, dashboard) to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("System metrics, telemetry, and performance monitoring") but lists only topic nouns with no concrete action verbs, matching the anchor 'Names the domain but actions are minimal or generic' rather than the entirely-vague 1 or the 1-2-concrete-actions 3.	2 / 5
Completeness	It offers only a vague 'what' (domain topic nouns, no actions) and has no 'Use when...' clause or equivalent trigger guidance, matching 'Has a vague what and no when'; the missing-trigger cap of 3 does not rescue it from 2.	2 / 5
Trigger Term Quality	It includes relevant natural terms ("metrics", "telemetry", "performance monitoring") a user might say, but the set is thin and misses common variations/synonyms like observability, latency, health, or dashboard, fitting 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	The metrics/telemetry niche is somewhat specific, but "performance monitoring" broadly overlaps with logging, observability, and general monitoring skills, fitting 'somewhat specific but could still overlap with similar skills'.	3 / 5
	Total	10 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: alsk1992/CloddsBot
Path: src/skills/bundled/metrics/SKILL.md
Revision: c930628

Reviewed: 1 month ago

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.

metrics

Table of Contents

Is this your skill?