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.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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.

A lean, highly specific feature-flag reference with concrete commands and config values, but it functions as a single inline catalog rather than an overview with sequenced workflows or one-level-deep references.

Suggestions

Add a short numbered workflow for the primary task (e.g. 1. decide platform targets, 2. edit crates/xberg/Cargo.toml, 3. add to the relevant aggregate sets, 4. run `task verify:feature-parity`, 5. fix any flagged deltas) to lift workflow_clarity above 3.

Split the larger reference blocks — the aggregate-sets table, CI parity guard, and build profiles — into separate files under references/ and link to them from SKILL.md so the body serves as a navigable overview (improves progressive_disclosure).

Add a brief 'adding a new feature' checklist that names the aggregate sets and guarded supersets a new feature must be added to, turning the implicit CI rule into an explicit pre-commit step.

Dimension	Reasoning	Score
Conciseness	The body is dense and information-packed with no padding — it never explains what Cargo features, ORT, or tract are, and every line states a specific fact, feature name, config value, or command, assuming Claude's competence.	5 / 5
Actionability	It gives concrete, executable guidance — the exact parity command `python3 scripts/ci/check-feature-parity.py crates/xberg/Cargo.toml`, exact config values `PdfConfig.backend` parses ("native", "pdfium"), and explicit directives like "Read the manifest before assuming a member" — but it is reference-catalog oriented rather than fully step-by-step, leaving minor gaps.	4 / 5
Workflow Clarity	The primary tasks named in the description (adding, wiring, debugging a feature) are not sequenced into steps; the CI parity-guard section does provide one explicit validation checkpoint with clear "fails CI" consequences and a guarded-pairs table, but the overall workflow sequencing is implicit rather than laid out.	3 / 5
Progressive Disclosure	The document is well-sectioned with clear `##` headers and a table, but it is a ~110-line monolithic inline reference with no pointers to separate reference files; substantial sections like the aggregate-sets table and CI parity guard could be split out so SKILL.md acts as an overview.	3 / 5
	Total	15 / 20 Passed

Description

92%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, specific, third-person description that clearly states both the capability scope and explicit load triggers scoped to a single crate's feature-flag policy. Only minor synonym coverage is missing from the trigger terms.

Dimension	Reasoning	Score
Specificity	The description enumerates many concrete coverage areas ("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", "build profiles") and concrete actions ("adding, wiring, or debugging a Cargo feature", "reasoning about what compiles on WASM/Android/Windows/macOS-intel targets"), giving comprehensive coverage rather than the minor gaps of a 4.	5 / 5
Completeness	It explicitly answers both what (the full enumerated scope of xberg Cargo feature flags) and when ("Load when adding, wiring, or debugging a Cargo feature, or when reasoning about what compiles on WASM/Android/Windows/macOS-intel targets") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural terms a user would say are present ("Cargo feature", "Cargo feature flag", "compiles on WASM/Android/Windows/macOS-intel", "build profiles", "PDF backend"), but a few common synonyms/extensions (e.g. "feature gate", `Cargo.toml`) are missing, so it falls just short of the comprehensive synonym-and-extension coverage of a 5.	4 / 5
Distinctiveness Conflict Risk	It is tightly scoped to `crates/xberg` and its specific feature-flag policy with distinct platform triggers, giving it a clear niche with minimal risk of firing for an unrelated skill.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing, 1 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: xberg-io/xberg
Path: .ai-rulez/skills/feature-flag-policy/SKILL.md
Commit: 04336bd

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.