Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

usage

Token usage tracking, cost estimation, and usage analytics

Quality

66%

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/usage/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.

This is a fully executable, highly actionable API reference whose main weaknesses are its monolithic inline structure, the absence of any safeguards or validation around the destructive reset operation, and mild padding from console.log boilerplate and generic best-practice advice. Splitting the detailed API into a reference file and adding reset safeguards would lift most dimensions.

Suggestions

Move the full TypeScript API reference into a separate references/ file and keep a concise quick-start overview in SKILL.md.

Add a confirmation/verification step before `/usage reset`, since it destructively clears all usage data with no guidance on when or whether to run it.

Trim the repeated console.log boilerplate and the generic Best Practices section to reduce token overhead.

Dimension	Reasoning	Score
Conciseness	The body is mostly dense reference material with no re-teaching of known concepts, but the repeated `console.log(...)` boilerplate in nearly every example and the generic "Best Practices" section ("Monitor regularly — Check usage weekly", "Cache when possible") are unnecessary tokens that could be trimmed.	3 / 5
Actionability	Every section gives copy-paste-ready TypeScript or exact slash commands — `createUsageService({...})`, `await usage.record({...})`, `/usage estimate <model> <in> <out>` — with realistic parameters and expected outputs covering the common cases.	5 / 5
Workflow Clarity	The create → record → query → format flow is implicit in the section ordering, but no validation checkpoints exist anywhere, and the destructive `/usage reset` ("Clear all usage data") carries no confirmation or verification guidance, capping this dimension at 3 per the rubric.	3 / 5
Progressive Disclosure	Section headers are clear, but roughly 200 lines of full API reference are inlined in SKILL.md with no references to separate bundle files — matching the anchor of content that should live in a separate file sitting inline under an overview heading.	3 / 5
	Total	14 / 20 Passed

Description

53%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 states in third person what the skill does with a couple of concrete capability nouns, but it omits any when-to-use trigger guidance and common synonyms like budget or spending, leaving it mid-scale on the highest-weighted dimensions. It is clearly distinct from unrelated skills yet generic enough in the analytics tail to risk minor overlap.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks about token usage, API costs, spending, or budget limits."

Include natural synonyms users actually say — "spend/spending", "budget", "billing", "API costs" — alongside "cost estimation".

Surface distinctive capabilities from the body (per-user/per-session breakdowns, budget alerts, message footers) to sharpen both the what and the triggers.

Dimension	Reasoning	Score
Specificity	The phrase "Token usage tracking, cost estimation, and usage analytics" names the domain plus two concrete actions (tracking, cost estimation), but "usage analytics" is generic and coverage omits budgets, per-user/per-session views, and footer formatting that the body documents.	3 / 5
Completeness	The description clearly answers "what" but contains no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guideline. It is not a 2 because the "what" is concrete rather than vague.	3 / 5
Trigger Term Quality	"Token usage" and "cost estimation" are natural phrases users would say, but common variations like "spend", "budget", "billing", or "API costs" are absent, matching the "some relevant keywords but missing common variations" anchor.	3 / 5
Distinctiveness Conflict Risk	The AI token-cost accounting niche is mostly distinct with minor overlap risk; however "usage analytics" is generic enough to collide with general analytics or cost-analysis skills, so it does not reach the clear-niche bar of 5.	4 / 5
	Total	13 / 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/usage/SKILL.md
Revision: c930628

Reviewed: 12 days 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.

usage

Table of Contents

Is this your skill?