CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/agent-cost-optimizer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

38%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 covers a coherent set of cost operations with concrete pricing data, but it is heavily duplicated across sections, its code examples are non-executable pseudocode depending on undefined helpers, and it is a monolith with no bundle files and a dangling reference. It functions better as a reference dump than as an actionable skill overview.

Suggestions

Consolidate the duplicated sections into one canonical treatment each: model selection and caching appear in both the operations and the strategies section, and ROI is covered in both Operation 6 and the ROI Calculation Framework, roughly halving the body.

Move stable but bulky material (provider pricing tables, alert markdown templates, monthly ROI report templates) into reference files such as references/pricing.md and references/report-templates.md, and fix or remove the dangling "see examples/" pointer.

Replace the pseudocode with executable code: `saveCache(cacheKey, result, ttl: 24 hours)` is invalid TypeScript and `getCurrentMonthUsage`, `readCache`, and `predictCost` are undefined — either provide a scripts/ helper implementing them or drop the pretense of runnable snippets.

Add validation checkpoints to Operations 2, 3, 6, and 7 (e.g., verifying budget-log integrity after writes, or confirming predicted vs. actual cost reconciliation) so workflows match the validate-then-proceed pattern used in Operations 1 and 5.

DimensionReasoningScore

Conciseness

The ~830-line body is noticeably padded: model selection and caching each appear twice (Operations 4-5 and again under "Cost Optimization Strategies"), ROI is covered twice (Operation 6 and "ROI Calculation Framework"), and budget planning twice (Operation 3 and "Budget Management"), fitting the several-unnecessary-sections anchor at 2 rather than the severely-explains-basics anchor at 1.

2 / 5

Actionability

Pricing tables, formulas, and bash snippets are concrete, but the TypeScript is effectively pseudocode: `saveCache(cacheKey, result, ttl: 24 hours)` is invalid syntax and `getCurrentMonthUsage`, `readCache`, and `predictCost` are undefined helpers, matching the incomplete-guidance anchor at 3.

3 / 5

Workflow Clarity

Each operation is presented as a numbered sequence, but validation checklists appear in only 2 of 7 operations (Operations 1 and 5); Operations 2, 3, 6, and 7 proceed with no checkpoints, fitting the steps-present-but-checkpoints-missing anchor at 3 rather than the most-checkpoints-present anchor at 4.

3 / 5

Progressive Disclosure

No reference files exist at all; hundreds of lines of pricing tables, alert templates, and monthly ROI report templates that clearly belong in separate files are inlined, and the only pointer ("For cost reports, see examples/") targets a nonexistent directory, fitting the content-inlined anchor at 2 despite the good header hierarchy.

2 / 5

Total

10

/

20

Passed

Description

88%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 names concrete capabilities, includes an explicit "Use when..." trigger clause with natural phrases, and stays well-scoped to AI agent cost management. Only minor improvements are possible: adding a few trigger synonyms and slightly sharper differentiation from generic budgeting tools.

DimensionReasoningScore

Specificity

"Track token usage, predict costs, enforce budget caps ($50-70/month typical), optimize model selection, cache results, measure cost-to-value" lists six concrete actions with comprehensive coverage of the cost-management domain, matching the top anchor rather than the minor-gaps anchor at 4.

5 / 5

Completeness

The description explicitly answers "what" ("Real-time cost tracking, budget enforcement, and ROI measurement for AI agent operations...") and "when" with a concrete "Use when..." clause of trigger phrases, matching the 5 anchor exactly.

5 / 5

Trigger Term Quality

"Use when tracking AI costs, preventing budget overruns, optimizing spend, measuring ROI, or ensuring cost-effective AI operations" gives good natural-phrase coverage, but common variants like "token usage", "API costs", or "billing" are absent, fitting the good-but-not-comprehensive anchor at 4.

4 / 5

Distinctiveness Conflict Risk

The scope is clearly limited to AI agent cost management with distinct triggers, but it could minorly overlap with generic budgeting or FinOps-style skills, fitting the mostly-distinct anchor at 4 rather than the minimal-conflict anchor at 5.

4 / 5

Total

18

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.