CtrlK
BlogDocsLog inGet started
Tessl Logo

fullstack-dev

Full-stack backend architecture and frontend-backend integration guide. TRIGGER when: building a full-stack app, creating REST API with frontend, scaffolding backend service, building todo app, building CRUD app, building real-time app, building chat app, Express + React, Next.js API, Node.js backend, Python backend, Go backend, designing service layers, implementing error handling, managing config/auth, setting up API clients, implementing auth flows, handling file uploads, adding real-time features (SSE/WebSocket), hardening for production. DO NOT TRIGGER when: pure frontend UI work, pure CSS/styling, database schema only.

70

Quality

86%

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

73%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 a clear, validated workflow and well-signaled references to real bundle files, but it is voluminous for patterns Claude largely already knows, leaving conciseness as the weakest dimension.

Suggestions

Move detailed pattern sections (e.g. 9 Caching, 10 File Uploads, 11 Real-Time) into reference files and keep only the decision table plus a one-line pointer in SKILL.md, cutting the body substantially.

Complete the placeholder reconnect logic in the SSE and WebSocket examples (currently '/* reconnect */') so the code is fully copy-paste ready.

Trim ✅/❌ rule boxes that restate widely known conventions (e.g. 'Never store JWT in localStorage') to one-line pointers, retaining only the non-obvious rules.

DimensionReasoningScore

Conciseness

Per-section writing is tight (✅/❌ rule boxes, code over prose), but the ~1000-line body extensively inlines fairly standard patterns (typed fetch wrappers, React Query, SSE/WebSocket boilerplate) that Claude already knows, so it could be tightened by offloading more to references. Not 2 (no fluffy prose padding) and not 4 (the overall volume is genuinely large for familiar material).

3 / 5

Actionability

Mostly copy-paste ready, executable code across TypeScript/Python/Go plus concrete commands ('npx prisma migrate dev', 'alembic upgrade head'), but minor gaps like placeholder reconnect logic ('/* reconnect */') and stubs ('handleMessage', 'cleanupUser') keep it just below the fully-executable anchor.

4 / 5

Workflow Clarity

The mandatory workflow sequences Steps 0–5 in order with an explicit validation Step 4 (build, smoke test via curl /health, integration, real-time checks) and a feedback loop ('If any check fails, fix the issue before proceeding'), plus scaffolding checklists — matching the explicit-validation-with-feedback-loops anchor.

5 / 5

Progressive Disclosure

Good structure with a Quick Navigation table, in-doc anchors, and a Reference Documents table linking to 8 verified reference files one level deep; however, much pattern content (caching, uploads, real-time) remains inlined in the ~1000-line body that could be split out, so it falls short of the appropriately-split anchor at 5.

4 / 5

Total

16

/

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 specific, comprehensive, and clearly distinguishes the skill via explicit positive and negative trigger phrases. It fully answers both 'what' and 'when' in third-person imperative voice without fluff.

DimensionReasoningScore

Specificity

Lists many concrete actions across the domain ('scaffolding backend service', 'implementing auth flows', 'handling file uploads', 'adding real-time features (SSE/WebSocket)'), matching the comprehensive-coverage anchor rather than the minor-gaps anchor at 4.

5 / 5

Completeness

Explicitly answers both what ('Full-stack backend architecture and frontend-backend integration guide') and when ('TRIGGER when:' with concrete phrases plus negative triggers), matching the explicit-what-and-when anchor.

5 / 5

Trigger Term Quality

Comprehensive natural trigger terms users would actually say ('building todo app', 'building CRUD app', 'Express + React', 'Next.js API', 'Node.js backend'), plus an explicit 'DO NOT TRIGGER when' boundary; coverage matches the comprehensive anchor.

5 / 5

Distinctiveness Conflict Risk

Clear niche (full-stack backend + frontend-backend integration) with distinct triggers and an explicit 'DO NOT TRIGGER when: pure frontend UI work, pure CSS/styling, database schema only' boundary, minimizing conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (1052 lines); consider splitting into references/ and linking

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
UnicomAI/wanwu
Reviewed

Table of Contents

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.