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

96%

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

Quality

Content

92%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 and well-structured: executable commands, concrete rollout strategies, and four workflows with explicit validation/feedback loops on destructive operations. Progressive disclosure is clean with real one-level-deep references; the only mild weakness is some command and table redundancy that could be trimmed for token efficiency.

Suggestions

Remove the duplicated Quick-start commands that reappear verbatim in the per-tool sections, or have Quick start point forward to them.

Collapse the provider table and the adjacent decision-rules list into one block (table + 4 rules) and defer detail to provider_comparison.md to reduce overlap.

Trim the 'Core principle' diagram prose since the lifecycle is restated in the taxonomy table and the flag_lifecycle reference.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence (no "what is a feature flag" preamble; copy-paste commands), but Quick-start commands are repeated in the per-tool sections and the provider table overlaps the decision rules and references — minor tightening possible.	4 / 5
Actionability	Fully executable, copy-paste-ready commands with real flags (e.g. "python scripts/flag_debt_scanner.py --repo . --max-age-days 90 --format json"), enumerated detection patterns, and concrete rollout percentages per strategy.	5 / 5
Workflow Clarity	Four numbered workflows with explicit validation checkpoints and feedback loops ("Run kill_switch_audit.py — must pass before merge", "Test the kill switch in staging BEFORE production rollout", "abort if abort criteria met") on destructive/batch operations.	5 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references (the References section lists 4 real files with one-line descriptions); taxonomy/provider tables sit inline as summaries with pointers to detail files, and all referenced bundle paths exist.	5 / 5
	Total	19 / 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 exemplary: third-person voice, concrete capabilities, a rich set of natural trigger phrases including provider synonyms, and explicit what/when guidance. It is comprehensive without being padded and clearly distinct from generic skills.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ("adding, retiring, or auditing feature flags") plus specific shipped artifacts ("flag debt scanner, rollout planner, and kill-switch auditor", "4 references", "/flag-cleanup slash command") — comprehensive coverage.	5 / 5
Completeness	Explicitly answers both "what" (ships 3 tools, 4 references, a slash command) and "when" ("Use when adding, retiring, or auditing... Triggers on...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Extensive natural trigger phrases users actually say ("add a flag", "ship behind a flag", "rollout plan", "kill switch", "stale flags", "flag debt") plus provider synonyms (LaunchDarkly, GrowthBook, Statsig, Unleash, Flipt) — comprehensive coverage including synonyms.	5 / 5
Distinctiveness Conflict Risk	Clear niche (feature-flag lifecycle) with distinct triggers and named providers; minimal overlap risk with other skills.	5 / 5
	Total	20 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

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

Reviewed: ~6 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.