CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

dev

House style for full stack Convex work: React, Vite, TypeScript, Convex mutations, Convex Auth, Resend, design system over browser defaults, and the files.md, changelog.md, task.md habit. Edit it to match your project after installing. Use when building features, writing Convex functions, or making code changes in a project that uses this style.

Quality

81%

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

68%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 disciplined, lean house-style skill: concrete rules, named APIs, and specific commands with essentially no filler. Its weakest point is workflow clarity — the documentation lifecycle (PRD, task.md, changelog, update-project-docs) is scattered across bullets rather than presented as a sequence — and the resource link list and missing format examples leave small organization and actionability gaps.

Suggestions

Add a short ordered documentation workflow (e.g., 1. PRD in prds/ before non-trivial work, 2. track in task.md during, 3. changelog + update-project-docs after landing) so the lifecycle is explicit rather than implied across separate bullets.

Show a one-line example of a files.md entry and a task.md section so 'one line per file' and 'To Do, In Progress, Completed' translate to an unambiguous output format.

Move the 13-link Convex resource list into a references file (e.g., references/convex-docs.md) and keep two or three most-used links inline, slimming the body while preserving the full list one level deep.

DimensionReasoningScore

Conciseness

The body is lean and directive throughout — terse bullets like 'Patch directly when the write does not depend on the current document' with no explanation of concepts Claude already knows. Minor trim candidates remain: 'This is house style. Edit it to match your project after installing.' duplicates the description, and the '[Add palette, type scale, and spacing rules for this project.]' placeholder is template scaffolding rather than content, fitting the 4 anchor's 'minor instances ... that could be trimmed'.

4 / 5

Actionability

Concrete, executable guidance throughout: specific APIs ('read the caller with ctx.auth', 'Promise.all() for independent reads'), a specific command ('git log --date=short -n 10'), and hard prohibitions ('Never window.confirm, alert, or prompt'). Minor gaps keep it below 5: no example of a files.md entry or task.md section format, so 'one line per file' and 'To Do, In Progress, Completed' leave the exact output format ambiguous.

4 / 5

Workflow Clarity

The documentation lifecycle is only implied rather than sequenced — 'A PRD in prds/ before non trivial multi step work' and 'After a change lands, load update-project-docs' give before/after markers, but there is no ordered flow connecting task.md tracking, changelog updates, and doc refresh, and no validation checkpoints. This matches the 3 anchor ('sequence present but checkpoints missing or implicit'); nothing here is destructive or batch, so the workflow cap does not apply.

3 / 5

Progressive Disclosure

A single-file skill (~95 lines) with clear, well-organized sections and no bundle files to navigate (assets/ holds only unreferenced logos). The 13-link resource list under Convex is borderline inline bulk that could live in a references file to keep the body leaner, which is exactly the kind of 'minor organization gap' the 4 anchor describes; structure is otherwise good.

4 / 5

Total

15

/

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, concise, and specific about both the stack it covers and when to use it. The explicit 'Use when' clause with concrete triggers anchors completeness at the top level; only broader synonym coverage and slightly more action-oriented phrasing keep specificity and trigger quality at 4.

DimensionReasoningScore

Specificity

Enumerates many concrete specifics — 'React, Vite, TypeScript, Convex mutations, Convex Auth, Resend, design system over browser defaults, and the files.md, changelog.md, task.md habit' — covering the stack comprehensively, but the 'what' is a subject-matter enumeration rather than performed actions, so it stops short of the 5 anchor's 'multiple specific concrete actions'.

4 / 5

Completeness

Clearly answers both: the 'what' ('House style for full stack Convex work: ...') and an explicit 'when' with concrete trigger phrases ('Use when building features, writing Convex functions, or making code changes in a project that uses this style'), matching the 5 anchor exactly.

5 / 5

Trigger Term Quality

Includes natural terms users would say — 'building features, writing Convex functions', 'React', 'TypeScript', 'Convex', 'Resend' — with good coverage, but misses common synonyms and variations like 'auth', 'email', 'frontend', or 'full stack' as standalone triggers, so it does not reach the 5 anchor's comprehensive synonym/extension coverage.

4 / 5

Distinctiveness Conflict Risk

'Full stack Convex work' with the specific Convex/Resend stack carves a clear niche with minimal conflict risk, but generic terms like 'React', 'TypeScript', and 'making code changes' leave minor overlap with general frontend or coding-style skills, fitting the 4 anchor 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

waynesutton/convexskills

Path

skills/dev/SKILL.md

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.