configs-targeting

Configure config targeting rules to control which variations serve to different users. Enable percentage rollouts, attribute-based rules, segment targeting, and guarded rollouts.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/agentcontrol/configs-targeting/SKILL.md

Quality

Content

65%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.

Highly actionable with executable curl and Python covering the common targeting cases, but it is held back by redundancy across examples, missing validation checkpoints in the workflow, and a monolithic single-file structure with no progressive disclosure to reference files.

Suggestions

Add an explicit validation/verify step to the workflow (e.g. re-GET targeting after each PATCH and confirm the rule/variation applied) to enable a higher workflow_clarity score.

Move the full Python class and the operator/instruction reference tables into separate files under references/ and link to them, keeping SKILL.md a concise overview.

De-duplicate the percentage-rollout example so it appears once rather than in both the Workflow and Rollout Types/Common Patterns sections.

Dimension	Reasoning	Score
Conciseness	Content is mostly efficient technical reference with little concept padding, but the same addRule/percentageRollout pattern appears three times (Step 3 curl, Rollout Types JSON, Common Patterns Python) and the full ~170-line Python class duplicates much of the curl workflow.	3 / 5
Actionability	Provides fully executable curl commands and a complete copy-paste Python class covering attribute rules, percentage rollouts, fallthrough, segments, and individual targets, plus an error-handling table for common cases.	5 / 5
Workflow Clarity	A clear 3-step sequence (get targeting, edit default rule, add rules) exists, but there are no explicit validation/verification checkpoints for these production-serving changes, so per the destructive/batch cap workflow clarity is held at 3.	3 / 5
Progressive Disclosure	Sections are well-headed, but with no bundle files the entire ~500-line guide — including a large Python class and full operator/instruction reference tables that belong in separate reference files — is inlined in SKILL.md.	3 / 5
	Total	14 / 20 Passed

Description

71%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 specific, action-oriented description with good domain keywords, but it omits any 'Use when...' trigger guidance, which caps completeness. Adding an explicit trigger clause would meaningfully raise the score.

Suggestions

Append a 'Use when...' clause with concrete trigger phrases, e.g. 'Use when configuring which AI config variations serve to users, setting up percentage rollouts, or targeting segments/attributes.'

Add natural synonyms users might say (e.g. 'rollout', 'targeting rules', 'serving variations') to broaden trigger-term coverage.

Clarify the AI-configs scope up front to further reduce overlap with general flag-targeting skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('Configure config targeting rules') and lists multiple concrete capabilities — 'percentage rollouts, attribute-based rules, segment targeting, and guarded rollouts' — giving comprehensive coverage of actions.	5 / 5
Completeness	Clearly answers 'what' (configure targeting rules, enable rollouts/rules) but provides no 'Use when...' clause or equivalent trigger guidance, so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	Includes relevant natural terms a LaunchDarkly user would say ('targeting', 'percentage rollouts', 'segment targeting', 'rollouts'), but lacks synonyms and the explicit 'Use when...' phrasing that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	The 'config targeting' niche is mostly distinct from sibling skills like configs-create and configs-variations, though minor overlap risk exists with the segments skill.	4 / 5
	Total	16 / 20 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
skill_md_line_count	SKILL.md is long (508 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: launchdarkly/ai-tooling
Path: skills/agentcontrol/configs-targeting/SKILL.md
Commit: 0aef88f

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.