CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

057-design-feature-toggles

Use when designing, implementing, reviewing, testing, or cleaning up feature toggles, feature flags, kill switches, runtime configuration gates, canary controls, staged rollouts, experiments, or temporary compatibility switches in Java enterprise systems. This should trigger for requests such as Design a feature toggle strategy; Review this feature flag; Add a kill switch safely; Test toggle on and off paths; Clean up an expired feature toggle; Plan controlled rollout and rollback behavior. Part of Plinth Toolkit

69

Quality

87%

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

78%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.

A well-structured instructional skill body: an efficient overview with a clear six-step workflow and exemplary single-file progressive disclosure. It falls short of top marks on actionability (no inline executable examples) and workflow clarity (no explicit failure-recovery loops), and carries some redundancy across the covered/when-to-use/constraints sections.

Suggestions

Merge the 'What is covered in this Skill?' and 'When to use this skill' bullet lists (they overlap heavily and largely repeat the frontmatter trigger list) into one section to cut duplicate tokens.

Add one short inline code snippet in the body — e.g., a minimal typed toggle decision-point or both-paths unit test — so the most common implementation pattern is executable without opening the reference file.

Insert an explicit feedback loop in the workflow, such as 'If release/rollback review or both-paths tests fail, revise the toggle contract and boundaries before re-testing', to give the sequence error-recovery checkpoints.

DimensionReasoningScore

Conciseness

The body is disciplined and assumes Claude's competence (no concept re-teaching), but "What is covered in this Skill?", "When to use this skill", and the Constraints section partially restate one another and the frontmatter trigger list, so minor trimming is possible — anchor 4 ('efficient; minor instances… could be trimmed'), not 3 since there is no unnecessary explanation, only structural overlap.

4 / 5

Actionability

Steps give concrete checklists ("toggle type, stable name, typed decision API, default state, evaluation context, fallback behavior, audit needs, metrics, logs, and cleanup trigger") but the body contains no executable code or commands — all Java examples live in the reference — so it fits 'mostly executable guidance; minor gaps' rather than the copy-paste-ready anchor 5, and comfortably above the vague/pseudocode anchors.

4 / 5

Workflow Clarity

A clear six-step sequence (classify → design → boundaries → review → test → report) with review and test checkpoints, but no explicit feedback loops or error-recovery guidance (no 'if review fails, revise the contract and re-check'), which keeps it below anchor 5's 'explicit validation steps; feedback loops for error recovery'.

4 / 5

Progressive Disclosure

The body is a lean overview that routes all detail to a single verified, well-signaled, one-level-deep reference (references/057-design-feature-toggles.md), linked in the constraints, workflow step 1, and a dedicated Reference section — matching 'clear overview with well-signaled one-level-deep references' exactly; anchor 4 would require organization gaps that are not present.

5 / 5

Total

17

/

20

Passed

Description

91%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 strong description with excellent trigger coverage and an explicit, example-driven when-clause that clearly answers both what and when. Its only weaknesses are lifecycle-verb specificity rather than fully concrete operations, and minor overlap risk with adjacent rollout/deployment skills in the same toolkit family.

DimensionReasoningScore

Specificity

Lists several specific actions paired with concrete toggle artifacts ("designing, implementing, reviewing, testing, or cleaning up feature toggles, feature flags, kill switches"), but the verbs are generic lifecycle categories rather than the fully concrete operations of the anchor-5 example, so it fits 'several specific actions; minor gaps' rather than the level above.

4 / 5

Completeness

Explicitly answers both halves: the what (design/implement/review/test/cleanup of toggles in Java enterprise systems) and a concrete explicit when ("Use when… This should trigger for requests such as…"). Not 4 because the when-clause is already maximally explicit with concrete trigger phrases, not merely adequate.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including synonyms ("feature toggles, feature flags, kill switches, runtime configuration gates, canary controls, staged rollouts") and verbatim user phrasings ("Review this feature flag; Add a kill switch safely; Test toggle on and off paths"), which matches the comprehensive-synonyms anchor; the level below would require missing common variations.

5 / 5

Distinctiveness Conflict Risk

Scoped to "Java enterprise systems" with distinctive toggle vocabulary, but "canary controls, staged rollouts" and "Part of Plinth Toolkit" create minor overlap risk with closely related deployment/rollout and sibling toolkit skills, fitting 'mostly distinct; minor overlap risk' rather than the minimal-conflict anchor 5.

4 / 5

Total

18

/

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

jabrena/plinth

Path

skills/057-design-feature-toggles/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.