Tessl • The management layer for AI agent skills

SkillPublic

backend-patterns

Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.

Quality

67%

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 ./.kiro/skills/backend-patterns/SKILL.md

Quality

Content

61%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 well-organized, code-dense pattern reference that respects the reader's intelligence but is structured as a monolithic catalog rather than a skill: everything is inlined in one 600-line file, there are no workflow sequences or validation checkpoints, and some examples are non-executable stubs. Splitting into per-domain reference files and completing the partial code would materially improve it.

Suggestions

Split domain sections (API design, database, caching, auth, rate limiting, jobs, logging) into references/*.md files and keep SKILL.md as a short overview with one small representative example per domain plus clear pointers.

Complete or remove non-executable examples: fill in `vectorSearch`, `execute(job)`, and `findByIds`, and fix the plpgsql `INSERT INTO markets VALUES (market_data)` so the transaction example actually runs.

Add validation/verification guidance for risky operations — e.g. test transactions with a rollback-first check, verify queue jobs with retry and dead-letter handling — and deduplicate the two near-identical caching sections.

Dimension	Reasoning	Score
Conciseness	The body is lean and code-first with almost no explanatory prose — it assumes Claude's competence and every section jumps straight to patterns, matching "Efficient; minor instances of over-explanation that could be trimmed". It is not 5 because "Redis Caching Layer" and "Cache-Aside Pattern" are near-duplicate examples, and "// Other methods..." / "// Job execution logic" stubs add tokens without adding guidance.	4 / 5
Actionability	Most code blocks are concrete, executable TypeScript covering real cases (repository, middleware, RBAC, rate limiting, retry). It is not 5 because key examples are incomplete: `vectorSearch` and `execute(job)` have empty bodies, and the SQL `INSERT INTO markets VALUES (market_data)` will not run as written against a table (jsonb passed as a row value), so a user copying the transaction pattern verbatim would fail.	4 / 5
Workflow Clarity	This is a pattern catalog, not a sequenced workflow: there are no ordered steps, no validation checkpoints, and no error-recovery loops anywhere. Because it covers database operations and background job queues (contexts the rubric flags as needing feedback loops) without any validation guidance, workflow clarity is capped at 3; it stays above 2 because each pattern's usage flow is internally coherent and demonstrated with usage examples.	3 / 5
Progressive Disclosure	The entire 600-line body lives inline in SKILL.md with no bundle files (references/, scripts/, assets/ do not exist) and no pointers to external material. Full domain sections (auth, rate limiting, queues, logging) clearly belong in separate reference files, matching the anchor "Minimal structure; content that clearly belongs in separate files is inlined". It is above 1 because section headers and a "When to Activate" list do provide navigable top-level structure.	2 / 5
	Total	13 / 20 Passed

Description

61%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 domain-specific description with good trigger terms for the Node/Next.js ecosystem, but it reads as a topic list rather than an action list and entirely lacks a "when to use" clause. Adding explicit trigger conditions and concrete actions would lift it substantially.

Suggestions

Add a "Use when..." clause, e.g. "Use when designing REST/GraphQL endpoints, fixing N+1 queries, adding caching or rate limiting, or structuring service/repository layers in a Node.js, Express, or Next.js backend."

Convert the topic list into concrete actions: "Design REST APIs, optimize database queries, add Redis caching, implement JWT auth and rate limiting..."

Include common trigger synonyms users would say (REST, endpoints, middleware, Postgres/Supabase, server) to improve retrieval coverage.

Dimension	Reasoning	Score
Specificity	"Backend architecture patterns, API design, database optimization, and server-side best practices" names the domain and topical areas, but the phrase list is topical rather than action-oriented — no concrete verbs like "Design", "Implement", or "Optimize". This matches the anchor "Names domain and 1-2 concrete actions, but not comprehensive"; it is above score 2 because the named areas (API design, database optimization) are concrete domain topics, but below score 4 because there are no specific actions a user can map to outcomes.	3 / 5
Completeness	The description clearly answers "what" (backend architecture patterns, API design, database optimization for Node.js/Express/Next.js) but contains no "Use when..." clause or equivalent trigger guidance, capping completeness at 3 per the judging guidelines. It is above score 2 because the "what" is specific and multi-faceted, not vague.	3 / 5
Trigger Term Quality	"backend", "API", "database", "Node.js", "Express", and "Next.js" are all terms users naturally say when they need this skill. It falls short of score 5 because common variations users would say — "REST", "endpoints", "server", "SQL/Postgres" — are absent.	4 / 5
Distinctiveness Conflict Risk	Scoping to "Node.js, Express, and Next.js API routes" gives it a clear niche that distinguishes it from backend skills for other stacks. It is not score 5 because "server-side best practices" is broad phrasing that overlaps with general coding-standards or testing 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
skill_md_line_count	SKILL.md is long (601 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	14 / 16 Passed

Repository: affaan-m/ECC
Path: .kiro/skills/backend-patterns/SKILL.md
Revision: d2ef268

Reviewed: 1 month ago

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.

backend-patterns

Table of Contents

Is this your skill?