CtrlK
BlogDocsLog inGet started
Tessl Logo

backend-dev

Coding practices for backend development in Atomic CRM. Use when deciding whether backend logic is needed, or when creating/modifying database migrations, views, triggers, RLS policies, edge functions, or custom dataProvider methods that call Supabase APIs.

72

Quality

88%

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

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.

An exemplary conventions-reference skill: dense with project-specific, non-inferable knowledge, explicitly sequenced with a verification checklist, and appropriately sized with clean delegation to sibling skills. The only dimension short of full marks is actionability, where code appears as fragments and naming patterns rather than complete runnable examples.

Suggestions

Add one minimal copy-paste edge-function skeleton showing the CORS → authenticate() → handler chain, so the middleware convention is executable rather than descriptive.

Include a short example RLS policy snippet demonstrating the WITH CHECK column-whitelisting pattern (e.g. constraining status/type via CHECK or policy), since that security-critical rule is currently stated only as prose.

DimensionReasoningScore

Conciseness

The body is lean and dense with project-specific facts Claude could not know: named views ("contacts_summary", "companies_summary"), named shared utils, the middleware chain order, and a specific migration ID. It explains no general concepts, assumes competence throughout, and every line carries non-obvious information — matching 'every token earns its place'. Not a 4 because there are no trimmable over-explanations anywhere.

5 / 5

Actionability

Mostly concrete, executable guidance: exact view names, file paths in `supabase/functions/_shared/`, the `verify_jwt = false` config setting, an inline call pattern (`httpClient(`${supabaseUrl}/functions/v1/<name>`)`), and named conventions (e.g. `mergeContacts()` → `/functions/v1/merge_contacts`). It stops short of anchor 5's 'copy-paste ready' bar because the code shown is fragments and naming patterns rather than complete, runnable examples (e.g. no full edge-function skeleton or RLS policy snippet), though for a conventions-reference skill the gaps are minor.

4 / 5

Workflow Clarity

The entry instruction sequences the process explicitly — 'Read the relevant section before writing backend code, then check the Red Flags and Verification list' — and the skill closes with a 6-item verification checklist covering exactly its risky operations (view sync, RLS/trigger on new tables, SECURITY DEFINER counts, WITH CHECK column coverage, middleware order). Validation checkpoints are explicit and comprehensive, matching the anchor-5 pattern of clear sequence plus checklists; there are no missing-validation gaps that would cap it at 3 or 4.

5 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/), and none are needed: the ~55-line body is a genuinely lean overview with well-organized sections, and detailed material is delegated via clearly signaled one-level pointers to sibling skills (`Skill({skill: "writing-migrations"})`, `Skill({skill: "frontend-dev"})`). Under the rubric's guidance for short skills with no need for external references, well-organized sections alone warrant a 5, and nothing here should have been split out.

5 / 5

Total

19

/

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 that explicitly answers both what the skill covers and when to use it, with concrete, domain-specific trigger terms. The only weaknesses are minor: an abstract leading verb phrase ('Coding practices') and slight trigger overlap with the sibling migrations skill.

DimensionReasoningScore

Specificity

The description names the domain ("backend development in Atomic CRM") and enumerates concrete artifacts — "database migrations, views, triggers, RLS policies, edge functions, or custom dataProvider methods" — which is several specific actions with only minor gaps. It falls short of a 5 because the leading "what" ("Coding practices") is somewhat abstract and the verbs are generic ("creating/modifying"), rather than fully distinct concrete actions.

4 / 5

Completeness

Both halves are explicit: the "what" ("Coding practices for backend development in Atomic CRM") and a concrete "Use when..." clause with specific triggers ("deciding whether backend logic is needed, or when creating/modifying database migrations, views, triggers, RLS policies, edge functions..."). This mirrors the anchor-5 good example's structure of clear what + explicit when with concrete trigger phrases; a 4 would require the 'when' to be less explicit, which it is not.

5 / 5

Trigger Term Quality

Strong natural keywords a developer would actually say: "backend", "database migrations", "views", "triggers", "RLS policies", "edge functions", "Supabase". A few natural variations are missing (e.g. "Postgres", "SQL", "RPC", "auth"), so it matches 'good keyword coverage; a few natural terms missing' rather than the comprehensive-synonyms anchor at 5.

4 / 5

Distinctiveness Conflict Risk

Scoping to "Atomic CRM" and Supabase-specific terminology ("RLS policies", "edge functions", "dataProvider") gives it a clear niche with minimal conflict against generic skills. Minor overlap risk remains with closely related sibling skills — the body itself delegates migration mechanics to a separate "writing-migrations" skill, yet the description claims "creating/modifying database migrations" as a trigger — which keeps it at 'mostly distinct; minor overlap risk' rather than 5.

4 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
marmelab/atomic-crm
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.