Name: feature-flags-architect
Rating: 70.39999999999999 (1 reviews)
Author: alirezarezvani

feature-flags-architect

Use when adding, retiring, or auditing feature flags. Triggers on "add a flag", "ship behind a flag", "rollout plan", "kill switch", "stale flags", "flag debt", "LaunchDarkly", "GrowthBook", "Statsig", "Unleash", "Flipt", or any progressive-delivery question. Ships flag debt scanner, rollout planner, and kill-switch auditor (all stdlib Python), 4 references on flag taxonomy + provider trade-offs + rollout strategies + lifecycle, plus a /flag-cleanup slash command.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

The canonical home for this skill is feature-flags-architect in alirezarezvani/claude-skills

Quality

Content

75%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 highly actionable with concrete, runnable tooling and well-sequenced workflows that include validation gates. Its main weakness is progressive disclosure: it advertises references, scripts, an asset template, and a slash command that do not exist in the bundle, breaking the overview-to-detail structure it promises.

Suggestions

Create the referenced bundle files (scripts/flag_debt_scanner.py, rollout_planner.py, kill_switch_audit.py; references/flag_taxonomy.md, provider_comparison.md, rollout_strategies.md, flag_lifecycle.md; assets/flag_request_template.md) so the advertised navigation actually resolves.

Move the bulk of the provider-comparison table and flag-type detail into references/provider_comparison.md and references/flag_taxonomy.md, keeping only the decision rules inline in SKILL.md to lean out the overview.

Trim explanatory padding such as 'Most teams treat flags as throwaway if-statements' and condense the 'Verifiable success' section so every remaining token earns its place.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with tight tables and concrete commands, but includes some over-explanation Claude already knows (e.g. 'Most teams treat flags as throwaway if-statements') and a slightly padded 'Verifiable success' section that could be trimmed.	4 / 5
Actionability	Fully executable guidance throughout: copy-paste-ready CLI invocations for all three scripts with realistic flags, concrete detection heuristics, strategy definitions, and exact audit checklist fields.	5 / 5
Workflow Clarity	Four workflows are clearly sequenced with explicit validation checkpoints (kill_switch_audit.py 'must pass before merge', 'should now show one fewer flag'), though Workflow 4's kill-switch validation in staging is implied rather than enforced by a tool call.	4 / 5
Progressive Disclosure	The body references scripts/, 4 references/*.md files, an assets/ template, and a slash command, but none of these bundle paths exist on disk — the structure is advertised but not actually present, so navigation and reference integrity are effectively buried/unverifiable.	2 / 5
	Total	15 / 20 Passed

Description

100%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 excellent: it concisely states concrete capabilities, lists natural trigger phrases a user would actually say, and cleanly separates the 'what' from the 'when'. It uses appropriate third-person voice and avoids vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and artifacts: 'flag debt scanner, rollout planner, and kill-switch auditor (all stdlib Python)' plus '4 references' and a '/flag-cleanup slash command', giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (adds, retires, audits flags; ships scanner/planner/auditor) and 'when' ('Use when adding, retiring, or auditing feature flags') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases users would say: 'add a flag', 'ship behind a flag', 'rollout plan', 'kill switch', 'stale flags', 'flag debt', plus vendor names (LaunchDarkly, GrowthBook, Statsig, Unleash, Flipt) and 'progressive-delivery'.	5 / 5
Distinctiveness Conflict Risk	Clear niche (feature-flag lifecycle management) with distinct, vendor-specific triggers that are unlikely to fire for unrelated skills, minimizing conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 17 missing	Warning

	Total	14 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/skills-feature-flags-architect/SKILL.md
Commit: 19392f7

Reviewed: ~16 hours 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.