CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

engineering-skills

Index of the engineering-team skills bundle for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw, and 6 more tools. Architecture, frontend, backend, QA, DevOps, security, AI/ML, data engineering, Playwright, Stripe, AWS, MS365 (stdlib-only Python tools). Use when browsing or choosing among engineering-team role skills — load only the one specialist SKILL.md you need, never bulk-load the bundle.

69

Quality

87%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

An exemplary index/router body: token-efficient tables, executable quick-start commands, and clean one-level-deep routing to 32 specialist skills. Weaker points are internal consistency (32 vs 23 skills counted, unlisted scripts) and a couple of dangling pointers (CLAUDE.md) that leave minor gaps in actionability and workflow clarity.

Suggestions

Reconcile the skill count: the intro claims '32 production-ready engineering skills' but the three tables list only 23 (13 core + 5 AI/ML/Data + 5 specialized) — either list the missing 9 or correct the number.

Replace the generic 'python3 <skill>/scripts/<tool>.py --help' placeholder with a listing or manifest of the '30+ scripts' (at least name the most useful ones per category) so the Python tools section is as actionable as the skills tables.

Resolve the dangling 'Check CLAUDE.md for tool usage examples' pointer — state where CLAUDE.md lives in the bundle or drop the rule.

DimensionReasoningScore

Conciseness

Dense tables, terse Quick Start commands, and a lean Rules section with no explanations of concepts Claude already knows; only trivial marketing fluff ("production-ready"), matching anchor 5's 'every token earns its place'.

5 / 5

Actionability

Provides concrete executable commands ('/read engineering-team/skills/senior-fullstack/SKILL.md', 'npx agent-skills-cli add alirezarezvani/claude-skills/engineering-team', 'python3 <skill>/scripts/<tool>.py --help') and folder names that make load paths constructible, but the generic '<skill>/scripts/<tool>.py' placeholder lacks a script manifest and 'Check CLAUDE.md' is a dangling pointer.

4 / 5

Workflow Clarity

The single routing action (pick folder from table, load that SKILL.md) is unambiguous and no destructive/batch cap applies, but the headline '32 production-ready engineering skills' conflicts with the 23 enumerated (13+5+5), '30+ scripts' has no inventory, and the CLAUDE.md reference is unresolved — matching anchor 4's minor gaps rather than 5.

4 / 5

Progressive Disclosure

Model index structure: overview tables route to one-level-deep per-skill SKILL.md folders and per-skill scripts, clearly signaled with no nested references, matching anchor 5. No bundle files (references/, scripts/, assets/) exist alongside this SKILL.md to verify against, so the score reflects the reference structure itself.

5 / 5

Total

18

/

20

Passed

Description

83%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 description: third-person, explicit 'Use when' trigger, comprehensive domain enumeration, and clear routing intent. Minor deductions for a narrow action set and trigger keywords that overlap with the specialist skills it indexes.

DimensionReasoningScore

Specificity

States its concrete function (index/browse/choose/load a single specialist SKILL.md) and comprehensively enumerates domains ("Architecture, frontend, backend, QA, DevOps, security, AI/ML, data engineering, Playwright, Stripe, AWS, MS365"), but the action set is inherently narrow for an index skill, so it matches anchor 4 rather than 5's multiple distinct concrete actions.

4 / 5

Completeness

Explicitly answers both "what" ("Index of the engineering-team skills bundle..." with enumerated domains) and "when" ("Use when browsing or choosing among engineering-team role skills") with a concrete trigger clause in third person, matching anchor 5 rather than 4's weaker 'when'.

5 / 5

Trigger Term Quality

Includes natural user-facing terms ("Playwright", "Stripe", "AWS", "frontend", "DevOps") plus agent-tool names, giving good keyword coverage, though a few natural phrasings users would say (e.g., "code review", "CI/CD", "test generation") are absent, keeping it below anchor 5.

4 / 5

Distinctiveness Conflict Risk

Clear niche as a router for this specific bundle, self-resolving overlap ("load only the one specialist SKILL.md you need, never bulk-load the bundle"), but broad domain terms like "security", "AWS", and "Stripe" overlap with the specialist skills themselves, leaving minor conflict risk per anchor 4.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

Total

15

/

16

Passed

Repository

alirezarezvani/claude-skills

Path

engineering-team/skills/engineering-skills/SKILL.md

Revision

27cfcd0

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill