CtrlK
BlogDocsLog inGet started
Tessl Logo

launchdarkly-flag-discovery

Audit your LaunchDarkly feature flags to understand the landscape, find stale or launched flags, and assess removal readiness. Use when the user asks about flag debt, stale flags, cleanup candidates, flag health, or wants to understand their flag inventory.

68

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

72%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 body is a well-structured, actionable guide that leverages progressive disclosure effectively, offloading deep interpretation to two real reference files. Its main weakness is workflow validation: it recommends removal actions and confidence-prioritized cleanup without explicit checkpoints to confirm findings before the user acts.

Suggestions

Add an explicit validation checkpoint in Step 4 (e.g., 'Before recommending removal, verify with get-flag-status-across-envs that the flag is inactive everywhere and confirm no dependencies via check-removal-readiness') so cleanup recommendations cannot be acted on unverified.

Tie each cleanup-priority category in Step 4 to the evidence that must be confirmed before assigning it (e.g., 'Ready to remove' requires both check-removal-readiness returning 'safe' AND cross-env inactive status), creating a feedback loop.

Trim illustrative narrative sentences (e.g., the staging-vs-production story in Step 3) to signal-level statements to lift conciseness toward fully lean.

DimensionReasoningScore

Conciseness

Largely efficient with concrete tool names and parameters rather than generic explanations, though some prose (e.g., 'A flag inactive in production but active in staging tells a different story than one inactive everywhere') could be tightened.

4 / 5

Actionability

Provides concrete, executable guidance naming specific MCP tools, parameters, and return fields (e.g., 'find-stale-flags', 'inactiveDays' default 30, 'includeOnly' values), though it relies on tool semantics rather than copy-paste code as expected for an MCP-driven skill.

4 / 5

Workflow Clarity

A clear six-step sequence with branching by goal is present, but cleanup/removal recommendations are batch-like actions directed to other skills without explicit validation checkpoints confirming findings before advising removal.

3 / 5

Progressive Disclosure

SKILL.md serves as a clear overview with well-signaled one-level-deep references to two real bundle files ([Flag Health Signals], [Removal Readiness Checklist]) that exist on disk; detailed interpretation is appropriately split out.

5 / 5

Total

16

/

20

Passed

Description

95%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 is well-crafted: it states concrete capabilities, uses third-person voice, and provides explicit 'Use when...' triggers with natural phrasing users would actually say. Trigger coverage and completeness are exemplary, with only minor room for additional synonyms like 'toggle' or 'feature toggle'.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('Audit... feature flags', 'find stale or launched flags', 'assess removal readiness') that clearly describe capabilities, with only minor coverage gaps.

4 / 5

Completeness

Explicitly answers both what ('Audit your LaunchDarkly feature flags...') and when ('Use when the user asks about flag debt, stale flags, cleanup candidates, flag health...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural trigger terms users would actually say — 'flag debt', 'stale flags', 'cleanup candidates', 'flag health', 'flag inventory' — covering synonyms and common phrasings.

5 / 5

Distinctiveness Conflict Risk

Clear LaunchDarkly-specific niche with distinct triggers ('flag debt', 'flag inventory') that minimize conflict with other skills; scope is discovery rather than cleanup/targeting.

5 / 5

Total

19

/

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: 3 suspicious

Warning

Total

15

/

16

Passed

Repository
launchdarkly/ai-tooling
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.