CtrlK
BlogDocsLog inGet started
Tessl Logo

implement-feature

The end-to-end workflow for adding a feature to Meshtastic-Android, in the order that keeps KMP source sets and the architecture intact. Use this whenever you start implementing a new feature or a sizeable behaviour change, before writing any code.

69

Quality

84%

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

86%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 tight, highly actionable workflow that respects token budget and encodes real project-specific knowledge (alias conventions, DI registration pitfalls, dual proguard targets). The only gaps are minor: no code snippets for the ViewModel/UI steps and no explicit failure-recovery loop in the verification step.

DimensionReasoningScore

Conciseness

The body is lean throughout — "Follow MVI/UDF patterns", "Keep the ViewModel free of Android framework dependencies" — assuming Claude's competence with no padding or explanation of known concepts. The only trimmable element is the 2-line restated Description section, which is negligible, so it fits the 5 anchor rather than the 4.

5 / 5

Actionability

Concrete file paths (gradle/libs.versions.toml, AppKoinModule.kt, DesktopKoinModule.kt), copy-paste gradle commands, specific APIs (stateInWhileSubscribed, @Factory, @Single, @KoinViewModel), and a signature example make this mostly executable. It falls short of 5 because steps 2-3 (state/ViewModel and UI) give directives without any code snippet or example pattern.

4 / 5

Workflow Clarity

Six clearly sequenced, dependency-ordered steps with an explicit verification step including commands and conditional additions (kmpSmokeCompile, proguard keep rules, release builds). Below 5 because there is no explicit error-recovery loop (e.g., 'if spotlessCheck or detekt fails, fix and re-run') — checkpoints exist but feedback on failure is only implicit.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files present and no need for external references, so the simple-skill exception applies: well-organized sections with clear headers (numbered workflow steps) score 5. Cross-skill pointers ("see the compose-ui skill", "see testing-ci skill") are clearly signaled inline and are not nested references.

5 / 5

Total

18

/

20

Passed

Description

82%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 an explicit and well-timed 'Use when' clause, clear domain scoping, and natural trigger phrases. The main weakness is specificity: it describes the workflow's purpose and constraints rather than enumerating the concrete actions it covers.

Suggestions

Enumerate 2-3 concrete capabilities in the description (e.g., 'covers dependency aliases, shared MVI ViewModels, Koin DI wiring, and KMP validation') to lift specificity from naming one action to listing several.

Add one or two natural trigger synonyms such as 'add a screen' or 'new functionality' to broaden keyword coverage for users who phrase the request differently.

DimensionReasoningScore

Specificity

"The end-to-end workflow for adding a feature to Meshtastic-Android, in the order that keeps KMP source sets and the architecture intact" names the domain and one concrete action with real constraints, but does not enumerate several specific capabilities (e.g., dependency aliases, ViewModel setup, DI wiring) that a 4 would list. It is clearly above the 2 anchor, which offers only generic actions with no constraints.

3 / 5

Completeness

It explicitly answers what ("end-to-end workflow for adding a feature... keeps KMP source sets and the architecture intact") and when ("Use this whenever you start implementing a new feature or a sizeable behaviour change, before writing any code") with concrete trigger phrases. Not a 4, because the when-clause is already explicit and specific rather than vague or implicit.

5 / 5

Trigger Term Quality

"implementing a new feature" and "sizeable behaviour change" are natural phrases a user would say when needing this skill. A few natural variants ("add a screen", "new functionality") are missing, placing it just below the 5 anchor's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

Triggers are scoped to "Meshtastic-Android" with KMP/architecture-specific language, giving it a clear niche with minimal conflict risk against generic feature-implementation skills. No neighboring anchor fits better since even the 4 anchor admits overlap with closely related skills, which this avoids via repo-specific scoping.

5 / 5

Total

17

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
meshtastic/Meshtastic-Android
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.