CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

76%

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 ./skills/agentcontrol/configs-targeting/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%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 skill is highly actionable with an explicit, verified workflow and strong error-recovery guidance — its strongest dimensions. Its weaknesses are redundancy (Common Patterns duplicates earlier examples, the Python class restates the MCP flow) and a monolithic structure where operators, rollout shapes, and the REST client belong in separate reference files.

Suggestions

Move the Python REST client, operators table, and rollout config shapes into references/ files (e.g., references/rest-client.py, references/operators.md) and link to them from SKILL.md.

Cut or collapse the 'Common Patterns' section, since its model-routing example duplicates the Step 3 attribute-rule payload almost exactly.

Trim the Python class to the methods that add unique value (variation-ID lookup and the turnTargetingOn workaround) instead of restating every MCP step.

DimensionReasoningScore

Conciseness

The body is mostly operational, but the 'Common Patterns' section repeats the Step 3 attribute-rule example nearly verbatim (selectedModel/contains/sonnet) and the ~165-line Python class largely duplicates what the MCP JSON steps already demonstrate. It fits 'mostly efficient but could be tightened' rather than the minor-trim anchor at 4.

3 / 5

Actionability

Fully executable throughout: complete MCP call payloads with all required fields, a working Python class hitting the semantic patch endpoint with correct headers, and an error table mapping each status code to cause and solution. Copy-paste ready and covers the common cases.

5 / 5

Workflow Clarity

A clear five-step sequence ends with explicit verification ('Call get-agent-configs with section: "targeting" again and confirm the fallthrough, rules, and targets match what the user approved'), every write requires confirm: true with user agreement shown first, and the error-handling table provides recovery guidance for failed calls.

5 / 5

Progressive Disclosure

Section headers make the document navigable, but all reference material (operators table, instruction kinds, rollout config shapes, the full REST client class) is inlined in one ~480-line SKILL.md with no bundle files. This matches 'some structure but content that should be separate is inline' rather than the well-split anchor at 4.

3 / 5

Total

16

/

20

Passed

Description

62%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 communicates concrete capabilities with mostly natural trigger terms, but it omits any 'when to use' guidance and does not disambiguate the LaunchDarkly AI-configs domain from generic flag/config targeting. Adding an explicit 'Use when...' clause with user-facing trigger phrases would address the two weakest dimensions.

Suggestions

Add a 'Use when...' sentence with concrete triggers, e.g., 'Use when the user wants to control which AI config variation serves which users, roll out variations gradually, or target segments.'

Include natural synonyms users would say, such as 'who gets which model/variation', 'gradual rollout', or 'target specific users', to broaden trigger coverage.

Name the platform or product context (LaunchDarkly AI configs) so the description does not collide with feature-flag targeting skills.

DimensionReasoningScore

Specificity

The description lists four concrete actions ("Enable percentage rollouts, attribute-based rules, segment targeting, and guarded rollouts") beyond the domain statement, matching the 'several specific actions; minor gaps' anchor. It falls short of 5 because individual targeting and the default/fallthrough rule are unmentioned.

4 / 5

Completeness

The "what" is clearly stated (configure targeting rules, enable rollouts/rules/segments), but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Good natural keyword coverage: "targeting", "rollout", "segment", "percentage rollouts" are phrases users would plausibly say. A few natural synonyms (e.g., "who gets which variation", "target users") are missing, keeping it below the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

Terms like "variations", "guarded rollouts", and "segment targeting" are domain-specific, but the description never names LaunchDarkly or distinguishes AI configs from feature flags, so rollout/targeting requests could equally trigger sibling flag-targeting skills. It is somewhat specific with residual overlap, not 'mostly distinct'.

3 / 5

Total

14

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

launchdarkly/ai-tooling

Path

skills/agentcontrol/configs-targeting/SKILL.md

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.