cs-backend-engineer

Backend-engineering orchestrator. Walks the 7 Matt Pocock forcing questions (read/write ratio + QPS, tenancy, sync vs async, data sensitivity, pattern, RPO/RTO, SLO), picks the language + pattern profile, forks into specialists (api-design-reviewer, database-designer, migration-architect, observability-designer, slo-architect — listed alphabetically; workflow order is dependency-driven) rather than reimplementing their scope. Forks own context. Invoke via /cs:backend-review or Agent({subagent_type:"cs-backend-engineer",...}).

Quality

48%

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

Fix and improve this skill with Tessl

tessl review fix ./.gemini/skills/cs-backend-engineer/SKILL.md

Quality

Content

38%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 well-structured and workflow-oriented but over-verbose, lacks executable code beyond one command line, has no validation feedback loops for destructive operations, and references a bundle directory that does not exist — so its progressive disclosure is effectively broken.

Suggestions

Create the referenced bundle files (forcing_questions.md, composition_map.md, backend_decision_engine.py, profile JSONs) or remove the dangling path references so progressive disclosure actually resolves.

Add explicit validation checkpoints to Workflow 1/2 (e.g., 'validate the API contract with api-design-reviewer before scaffolding; re-run complexity_checker before commit') with fix-and-retry feedback loops for schema migrations.

Tighten name-dropping and parenthetical asides (alphabetical-listing disclaimers, repeated agent path cross-references) to respect the token budget and let each line earn its place.

Dimension	Reasoning	Score
Conciseness	The body is noticeably padded with name-drops, parenthetical asides ('listed alphabetically; workflow order is dependency-driven'), and verbose agent cross-references that a competent reader does not need; several sections could be tightened without losing meaning.	2 / 5
Actionability	It gives one concrete executable command for the decision engine, but most guidance is procedural prose and path pointers rather than copy-paste-ready code, and the referenced scripts/files do not exist, leaving execution underspecified.	3 / 5
Workflow Clarity	Workflows are clearly sequenced into numbered steps, but they involve schema migrations and production changes with no explicit validation checkpoints or validate-fix-retry feedback loops, which caps destructive/batch workflow clarity at 3.	3 / 5
Progressive Disclosure	References point to bundle files (references/, scripts/, profiles/) that are absent, and the body inlines dense knowledge-base and tool listings that belong in those separate files; navigation is mostly broken rather than well-signaled.	2 / 5
	Total	10 / 20 Passed

Description

58%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 specific, third-person, and names concrete capabilities and a clear niche, but it omits an explicit 'Use when...' trigger clause and leans on technical jargon over natural user phrases, capping completeness and trigger quality.

Suggestions

Add an explicit 'Use when...' clause stating the natural situations a user would invoke this skill (e.g., 'Use when picking a backend stack, designing a new service, or root-causing a production incident').

Reframe some trigger terms into natural user language alongside the technical ones (e.g., 'backend architecture review', 'database choice', 'service decomposition') so they match what users actually say.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Walks the 7 Matt Pocock forcing questions', 'picks the language + pattern profile', 'forks into specialists') and names the seven forcing-question axes explicitly, with minor gaps in coverage.	4 / 5
Completeness	It clearly states what the skill does, but there is no explicit 'Use when...' or equivalent trigger guidance for when Claude should invoke it, so per the boundary rule completeness is capped at 3.	3 / 5
Trigger Term Quality	Relevant terms are present (read/write ratio, QPS, tenancy, RPO/RTO, SLO) but these are technical jargon rather than the natural phrases a user would actually say when they need this skill; common synonyms and lay triggers are missing.	3 / 5
Distinctiveness Conflict Risk	It carves a clear backend-orchestrator niche with a named invocation ('/cs:backend-review', a specific subagent_type) and a distinct forcing-questions framing, with only minor overlap risk against neighboring cs-* engineering skills.	4 / 5
	Total	14 / 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
relative_links	Relative link issues: 3 missing, 3 suspicious	Warning

	Total	14 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/cs-backend-engineer/SKILL.md
Commit: 19392f7

Reviewed: ~3 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.