agent-cost-optimizer

Real-time cost tracking, budget enforcement, and ROI measurement for AI agent operations. Track token usage, predict costs, enforce budget caps ($50-70/month typical), optimize model selection, cache results, measure cost-to-value. Use when tracking AI costs, preventing budget overruns, optimizing spend, measuring ROI, or ensuring cost-effective AI operations.

Quality

72%

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 ./skills/agent-cost-optimizer/SKILL.md

Quality

Content

52%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 content is rich and actionable but suffers from significant verbosity and duplication, plus a monolithic structure with no progressive disclosure. Splitting reference material into bundle files and trimming redundant/time-sensitive filler would substantially improve it.

Suggestions

Remove the 'Industry Context (2025)' marketing section and deduplicate content that appears in both Operations and Strategies (ROI report templates, caching code, model selection).

Move stable reference material (pricing tables, ROI/budget report templates) into files under references/ and link to them one level deep, instead of inlining everything in SKILL.md.

Isolate time-sensitive 2025 dates and pricing rates in a clearly marked, easily-updatable section (or a references file) so they do not bloat the main body.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose and padded: the 'Industry Context (2025)' section explains market trivia Claude already knows, content is duplicated across Operations and Strategies (ROI report templates, caching code, model selection), and time-sensitive 2025 dates/rates are embedded inline rather than isolated.	2 / 5
Actionability	Provides mostly executable TypeScript functions (calculateCost, selectModel, generateCacheKey, calculateROI) plus JSON and bash snippets, with only minor gaps such as undefined helper calls (trackTokens, readCache) and the invalid 'ttl: 24 hours' syntax.	4 / 5
Workflow Clarity	Seven numbered operations are clearly sequenced with validation checklists in some (Ops 1 and 5) and a feedback loop for budget enforcement (check, block/warn, suggest alternatives), though validation is inconsistent across operations.	4 / 5
Progressive Disclosure	No bundle files exist, yet the body is an 830-line monolith that inlines pricing tables and ROI report templates that belong in separate reference files, and it references a non-existent 'examples/' directory.	2 / 5
	Total	12 / 20 Passed

Description

92%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, well-structured description that concretely states both capabilities and trigger conditions in third person. Minor room to add a few more synonyms or artifact references for trigger term breadth.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Track token usage, predict costs, enforce budget caps, optimize model selection, cache results, measure cost-to-value' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Clearly answers 'what' (cost tracking, budget enforcement, ROI measurement) and explicitly answers 'when' via a 'Use when...' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases like 'tracking AI costs', 'preventing budget overruns', 'optimizing spend', 'measuring ROI' are present, but a few common synonyms are missing and no file extensions or artifact types are named.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (AI agent cost optimization) with distinct triggers, making overlap with other skills minimal; uses third-person noun-phrase voice throughout.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (830 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	14 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/agent-cost-optimizer/SKILL.md
Commit: 93ed392

Reviewed: 1 day 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.