tool-selection-strategy

Use this skill when deciding which tools to call in an agentic workflow. Always choose the minimal, most direct tool for each step and avoid redundant or speculative tool calls.

Quality

83%

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

Quality

Content

100%Weight 40%Scale 1-3

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 tight, well-structured instruction-only skill that maps concrete scenarios to specific tools with a clear decision sequence and no wasted tokens.

Dimension	Reasoning	Score
Conciseness	The body is lean and directive with no padding or explanation of concepts Claude already knows; every line (principles, heuristic, anti-pattern) earns its place.	3 / 3
Actionability	Despite being instruction-only, it gives concrete, specific mappings (file ops -> Read/Write/Edit, code search -> Grep/Glob, system ops -> Bash), so the guidance is directly actionable.	3 / 3
Workflow Clarity	The numbered decision heuristic is a clear prioritized fallback sequence; no destructive or batch operations are involved, so the validation-checkpoint cap does not apply.	3 / 3
Progressive Disclosure	Under 50 lines with no need for external references, the content is split into well-organized sections (Principles, Decision heuristic, Anti-pattern), satisfying the simple-skill allowance.	3 / 3
	Total	12 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 clearly answers both what and when with an explicit trigger, but its actions are abstract strategy rather than concrete operations and its trigger terms are somewhat generic, leaving room for overlap with other agentic skills.

Suggestions

Replace abstract phrasing with concrete capabilities, e.g. 'Picks the lightest tool for each step (Read/Edit/Grep over Bash or Agent) and batches independent calls.'

Add natural trigger phrasing users would actually say, such as 'which tool should I use', 'too many tool calls', or 'redundant tool calls'.

Narrow the niche to reduce conflict risk, e.g. scoping it to multi-step agentic workflows where tool-call economy matters.

Dimension	Reasoning	Score
Specificity	Names several actions ("choose the minimal, most direct tool", "avoid redundant or speculative tool calls") but they are abstract strategic decisions rather than concrete artifact-level operations, matching the 'names domain and some actions' anchor rather than the multiple-concrete-actions anchor.	2 / 3
Completeness	It explicitly states what the skill does (choose the minimal/direct tool, avoid redundant or speculative calls) and when to use it via the explicit trigger "Use this skill when deciding which tools to call in an agentic workflow", satisfying both what and when.	3 / 3
Trigger Term Quality	Terms like "tools", "agentic workflow", and "tool calls" are relevant but somewhat jargon-heavy and lack common natural variations a user would say, fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	Tool-selection is a broad meta-concern that could overlap with many agentic-workflow skills, so it is somewhat specific but could still trigger for the wrong skill.	2 / 3
	Total	9 / 12 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: aiming-lab/MetaClaw
Path: memory_data/skills/tool-selection-strategy/SKILL.md
Commit: 922caf3

Reviewed: 9 days 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.