CtrlK
BlogDocsLog inGet started
Tessl Logo

claude-advanced-tool-use

Advanced tool use patterns including tool search, programmatic calling, and production orchestration. Use when scaling to 10,000+ tools, optimizing token usage, or implementing production tool systems.

60

Quality

71%

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/claude-advanced-tool-use/SKILL.md

The canonical home for this skill is claude-advanced-tool-use in fernandezbaptiste/Skrillz

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 well-structured with genuinely executable Tool Search code and clean one-level-deep references to real bundle files. Its main weaknesses are repeated statistics across sections and uneven code coverage — only one of the three headline features gets an inline example.

Suggestions

Collapse the duplicate statistics spread across Overview, Feature Comparison Matrix, and Compound Effect into a single source-of-truth to tighten conciseness.

Add a short inline code snippet for Programmatic Tool Calling (and ideally a tool-examples input_schema block) so all three headline features have executable guidance in the body.

Frame the Implementation Strategy steps with explicit validation/measure checkpoints (e.g., "Verify token savings before adding the next feature") to lift workflow clarity.

DimensionReasoningScore

Conciseness

The body is mostly efficient and avoids explaining basic concepts, but the same statistics (85%, 37%, 72%→90%) and feature summaries are restated across the Overview, Feature Comparison Matrix, and Compound Effect sections, so it could be tightened.

3 / 5

Actionability

The Tool Search quick start provides fully executable, copy-paste-ready Python with real model IDs and beta headers, but the other two features (programmatic calling, tool examples) lack inline code and defer entirely to references.

4 / 5

Workflow Clarity

The Implementation Strategy gives a clear 5-step sequence with a measure-and-iterate feedback loop, and the "What Happens" walkthrough is well sequenced; checkpoints are present though not framed as explicit validation gates.

4 / 5

Progressive Disclosure

Structure is good: an overview body with a dedicated References section pointing to four real, one-level-deep reference files (tool-search-patterns, programmatic-tool-calling, production-patterns, performance-optimization), though the body still inlines a fair amount (full code blocks, matrix, compound-effect restatements) that borders on over-long for an overview.

4 / 5

Total

15

/

20

Passed

Description

75%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 cleanly answers both what the skill does and when to use it, with concrete numeric triggers and a distinct advanced-tool-use niche. It is held back from the top band by the somewhat abstract "production orchestration" phrasing and a few missing natural synonyms.

Suggestions

Replace the abstract "production orchestration" with one or two concrete actions (e.g., "orchestrating multi-step tool workflows", "batching dependent tool calls") to lift specificity.

Add common natural synonyms a user might actually say, such as "tool discovery", "reducing tool tokens", or "MCP tool overload", to broaden trigger-term coverage.

Consider naming the API surface (e.g., the advanced-tool-use beta) in the description so it is unmistakably distinct from generic tool-use skills.

DimensionReasoningScore

Specificity

Names three concrete feature areas — "tool search, programmatic calling, and production orchestration" — giving several specific capabilities, though "production orchestration" stays somewhat abstract, keeping it just below comprehensive.

4 / 5

Completeness

Both a "what" (the three advanced tool-use patterns) and an explicit "when" (the Use-when triggers) are present; the "what" is pattern-level rather than fully concrete, so it sits just below the top anchor.

4 / 5

Trigger Term Quality

The "Use when" clause offers concrete triggers ("scaling to 10,000+ tools, optimizing token usage, or implementing production tool systems") with good keyword coverage, but a few natural synonyms are missing.

4 / 5

Distinctiveness Conflict Risk

"Advanced tool use" with 10K-tool/token-optimization triggers carves a clear niche distinct from basic tool use, with only minor overlap risk against related Claude tooling skills.

4 / 5

Total

16

/

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

relative_links

Relative link issues: 1 missing, 1 deeper-than-1-level

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.