Name: tools
Rating: 64 (1 reviews)
Author: launchdarkly

tools

Give your agents capabilities through tools (function calling). Helps you identify what your agent needs to do, create tool definitions, and attach them to config variations.

Quality

76%

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/agentcontrol/tools/SKILL.md

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable and concise with a clear validated workflow; the only softer dimension is progressive disclosure, since some inline multi-provider detail could be externalized and no bundled reference files accompany the skill.

Suggestions

Consider moving the per-provider conversion snippets into a dedicated references file (one level deep) to keep SKILL.md as an overview and improve progressive disclosure.

If multi-provider tracking payloads belong with this skill, bundle the referenced ../built-in-metrics files locally so the skill is self-contained.

Add a short top-of-file pointer/TOC to the per-provider sections so navigation to a specific provider is immediate.

Dimension	Reasoning	Score
Conciseness	The body is lean: concrete JSON payloads, a compact provider-conversion table, and executable Python snippets with no padding explaining what function calling is; every section earns its place for a genuinely multi-provider task.	3 / 3
Actionability	Provides fully executable JSON request bodies, complete per-provider Python conversion snippets, exact MCP tool names, and exact stop-reason checks per provider — copy-paste ready.	3 / 3
Workflow Clarity	A clear four-step sequence (identify → create → attach → verify) with an explicit verification step and recovery guidance (clobber-warning, 'report the bug'), satisfying the validation-checkpoint requirement.	3 / 3
Progressive Disclosure	No bundled references/scripts/assets exist in this skill; the body relies on cross-skill ../built-in-metrics references that are one level deep and clearly signaled, but the inline per-provider conversion snippets are content that could arguably be split out.	2 / 3
	Total	11 / 12 Passed

Description

60%

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 is specific and action-oriented but omits an explicit 'Use when...' trigger, leaving the 'when to use' half implicit and capping completeness and distinctiveness.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g., 'Use when adding function-calling tools to a LaunchDarkly AI config or attaching tool definitions to a variation').

Broaden trigger terms with phrasings a user would naturally say, such as 'function calling', 'give the agent tools', or 'attach tools to a config', to improve trigger-term coverage.

Sharpen distinctiveness by foregrounding the LaunchDarkly AI-config context so it is less likely to fire for generic tooling tasks.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'identify what your agent needs to do, create tool definitions, and attach them to config variations' — matching the anchor for listing several specific actions.	3 / 3
Completeness	Clearly states what the skill does but lacks an explicit 'when to use'/'Use when...' trigger clause; per guidelines a missing Use-when clause caps completeness at 2.	2 / 3
Trigger Term Quality	Includes relevant terms ('tools', 'function calling', 'tool definitions', 'config variations') but they lean technical/LaunchDarkly-specific and miss common natural variations a user would say, so not full coverage.	2 / 3
Distinctiveness Conflict Risk	The LaunchDarkly AI-config tooling niche is fairly distinct but could overlap with generic function-calling skills, and without explicit triggers it is not maximally distinguishable.	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
relative_links	Relative link issues: 1 missing, 5 suspicious	Warning

	Total	15 / 16 Passed

Repository: launchdarkly/ai-tooling
Path: skills/agentcontrol/tools/SKILL.md
Commit: add614f

Reviewed: 3 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.