CtrlK
BlogDocsLog inGet started
Tessl Logo

feature-flag-policy

Cargo feature flags for crates/xberg — ORT-incompatible targets (WASM, Android x86_64 emulator), type-only and tract inference companion features, WASM/Android-safe variants, PDF backend, mutually-exclusive ORT variants, platform-conditional deps, aggregate feature sets, and build profiles. Load when adding, wiring, or debugging a Cargo feature, or when reasoning about what compiles on WASM/Android/Windows/macOS-intel targets.

67

Quality

80%

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 ./.ai-rulez/skills/feature-flag-policy/SKILL.md
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, information-dense reference that assumes Claude's competence and gives concrete feature/cfg/profile specifics. Its main gap is the absence of verification commands for confirming target-specific compilation, which leaves workflow clarity at the midpoint.

Suggestions

Add a verification snippet for each target aggregate, e.g. `cargo check --target wasm32-unknown-unknown --no-default-features --features wasm-target`, so users can confirm a feature set compiles before committing changes.

De-duplicate the wasm-target/android-target composition between the prose paragraph and the Aggregate Sets table — keep the canonical definition in one place and reference it from the other.

Include one short TOML example showing a mutually-exclusive ORT variant choice (ort-bundled vs ort-dynamic) in context, to make the actionability fully copy-paste ready.

DimensionReasoningScore

Conciseness

The body is dense and assumes Cargo/Rust competence without explaining basic concepts, but the prose description of `wasm-target`/`android-target` composition is repeated in the Aggregate Sets table, a minor redundancy that could be trimmed.

4 / 5

Actionability

Guidance is concrete and specific — exact feature names, implication rules ("layout-detection implies layout-types"), exact cfg predicates, and exact profile values (opt-level="z", codegen-units=1) — but it lacks copy-paste TOML snippets, leaving a minor gap versus fully executable guidance.

4 / 5

Workflow Clarity

Content is organized by category rather than as a sequenced workflow, and although the skill is about "debugging a Cargo feature" and "reasoning about what compiles", there are no verification checkpoints (e.g., a `cargo check --target wasm32-unknown-unknown --features wasm-target` command) to confirm a configuration compiles on a target.

3 / 5

Progressive Disclosure

The skill is a single self-contained file with clear section headers (ORT-Incompatible Targets, PDF Backend, ORT Variants, Platform-Conditional, Aggregate Sets, Build Profiles) and a summary table, no nested references, and no need for external bundle files — well-organized one-level structure.

5 / 5

Total

16

/

20

Passed

Description

87%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 highly specific, explicit about both capabilities and load triggers, and scoped to a clear niche. Its only weakness is that the capability list is category-driven rather than verb-action-driven, which keeps specificity and trigger_term_quality just below maximum.

DimensionReasoningScore

Specificity

Enumerates a comprehensive, concrete set of capability domains ("ORT-incompatible targets", "type-only and tract inference companion features", "WASM/Android-safe variants", "PDF backend", "mutually-exclusive ORT variants", "platform-conditional deps", "aggregate feature sets, and build profiles") but frames them as noun-phrase categories rather than crisp verb-actions, sitting just below the verb-driven anchor 5 example.

4 / 5

Completeness

It clearly states what (the full feature-flag surface for crates/xberg) and explicitly states when with concrete trigger phrases ("Load when adding, wiring, or debugging a Cargo feature, or when reasoning about what compiles on ... targets"), matching the anchor 5 example that answers both what and when.

5 / 5

Trigger Term Quality

The trigger clause "Load when adding, wiring, or debugging a Cargo feature, or when reasoning about what compiles on WASM/Android/Windows/macOS-intel targets" supplies natural terms a Rust developer would say ("Cargo feature", "compiles on WASM/Android/Windows"), with only minor synonym gaps keeping it below the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

The niche is sharply scoped to Cargo feature flags for a specific crate (crates/xberg) with ORT/WASM/Android specifics, giving it distinct triggers and minimal overlap risk with other skills.

5 / 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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
xberg-io/xberg
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.