CtrlK
BlogDocsLog inGet started
Tessl Logo

auto-claude-optimization

Auto-Claude performance optimization and cost management. Use when optimizing token usage, reducing API costs, improving build speed, or tuning agent performance.

60

Quality

70%

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 ./.claude/skills/auto-claude-optimization/SKILL.md

The canonical home for this skill is auto-claude-optimization in fernandezbaptiste/Skrillz

SKILL.md
Quality
Evals
Security

Quality

Content

57%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 comprehensive, actionable optimization catalog with good section structure, but it suffers from cross-section redundancy, lacks validation for destructive database operations, and inlines ~355 lines of reference material that would benefit from being split into bundle files.

Suggestions

Deduplicate repeated guidance (Ollama embedding config, 'switch to Sonnet', '--skip-qa') so each setting appears once and cross-reference it from other sections.

Add validation/feedback-loop steps around destructive or batch operations such as database cleanup and compaction (e.g., verify episode count before/after --cleanup, back up before compact_database).

Move bulk reference material (cost estimation tables, the full optimal-.env block, model selection tables) into references/ files and link to them one level deep to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is mostly actionable and avoids explaining basics Claude already knows, but repeats the same Ollama/embedding and 'switch to Sonnet' guidance across Token, Memory, Environment, and Quick Wins sections, so it could be tightened materially by deduplication.

3 / 5

Actionability

It provides concrete, mostly copy-paste-ready env vars, bash commands, and Python snippets across many optimization areas, with only minor gaps (e.g., unverified internal API names like memory.search).

4 / 5

Workflow Clarity

This is a tuning catalog rather than a sequenced process, and destructive/batch operations like 'query_memory.py --cleanup --older-than 30d' and database compaction lack validation checkpoints, capping clarity at 3 per the rubric.

3 / 5

Progressive Disclosure

No bundle files exist and all content is inlined in a ~355-line SKILL.md; section headers give some structure, but bulk reference material (cost tables, full env config) that belongs in separate files is inlined with no one-level-deep references.

3 / 5

Total

13

/

20

Passed

Description

83%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 solid description that states the domain, lists concrete actions, and provides an explicit 'Use when' trigger clause in third person. It is mostly specific and distinct, with only minor gaps in keyword coverage and overlap risk.

DimensionReasoningScore

Specificity

The description lists several concrete actions ('optimizing token usage, reducing API costs, improving build speed, or tuning agent performance') but stops short of comprehensive coverage, leaving minor gaps.

4 / 5

Completeness

It explicitly answers both 'what' ('Auto-Claude performance optimization and cost management') and 'when' with concrete trigger phrases in a 'Use when...' clause.

5 / 5

Trigger Term Quality

It surfaces natural phrases users would say ('optimizing token usage', 'reducing API costs', 'improving build speed') with good coverage, though a few common synonyms are missing.

4 / 5

Distinctiveness Conflict Risk

The Auto-Claude-specific niche is mostly distinct, but the broad performance/cost framing could overlap with related Auto-Claude skills (memory, build, troubleshooting).

4 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
fernandezbaptiste/Skrillz
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.