CtrlK
BlogDocsLog inGet started
Tessl Logo

chat-widget

Build a real-time support chat system with a floating widget for users and an admin dashboard for support staff. Use when the user wants live chat, customer support chat, real-time messaging, or in-app support.

58

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/chat-widget/SKILL.md

The canonical home for this skill is chat-widget in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

52%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 content is technically rich and actionable, with solid workflow sequencing and concrete framework examples. Its main weaknesses are heavy verbosity and a monolithic structure that should be split into reference files for progressive disclosure.

Suggestions

Move the per-framework implementations (Rails, Next.js, Laravel, Vue) and the Database/Email/Real-Time option tables into separate files under references/ and keep SKILL.md as a concise overview that links to them one level deep.

Replace the 'pseudo' blocks for models, channels, and controllers with runnable code in a single reference language, or explicitly justify why pseudocode is preferred over copy-paste examples.

Add an explicit validation checkpoint inside the main 7-step flow (e.g., verify migration/schema and broadcast plumbing before building the frontend) rather than relying only on the post-implementation Testing Checklist.

DimensionReasoningScore

Conciseness

At ~880 lines the body is noticeably verbose: it re-explains design rationale, repeats the same broadcasting/job logic across multiple framework variants (Rails, React, Next.js, Laravel, Vue), and includes comparison tables and DB/email sections that assume knowledge Claude already has. Several sections could be moved to reference files or condensed.

2 / 5

Actionability

Provides mostly executable, concrete guidance—real Ruby migrations, TypeScript hooks, and TSX components that are largely copy-paste ready—though the core implementation uses labeled 'pseudo' blocks rather than directly runnable code, introducing minor gaps.

4 / 5

Workflow Clarity

Steps 1–7 give a clear sequence with a validation-oriented testing checklist and a Common Pitfalls section covering race conditions and dedup, but the main flow lacks an explicit mid-process validate-then-proceed checkpoint; the checklist and pitfalls partially compensate.

4 / 5

Progressive Disclosure

The skill ships as a single monolithic SKILL.md with no bundle files in references/scripts/assets, and framework-specific (Rails/Next.js/Laravel/Vue), database, email, and realtime-option sections that clearly belong in one-level-deep reference files are all inlined, making it hard to navigate.

2 / 5

Total

12

/

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.

The description cleanly states both capability and trigger conditions with natural, third-person phrasing and no fluff. It is strong overall, with only minor gaps in enumerated sub-features and synonym coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Build a real-time support chat system with a floating widget for users and an admin dashboard for support staff') but leaves specific sub-features (archiving, notifications, channels) implicit rather than enumerated.

4 / 5

Completeness

Explicitly answers both what ('Build a real-time support chat system with a floating widget... and an admin dashboard') and when ('Use when the user wants live chat, customer support chat, real-time messaging, or in-app support') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Covers strong natural phrases ('live chat', 'customer support chat', 'real-time messaging', 'in-app support') but misses common synonyms and file/format terms, leaving a few natural terms absent.

4 / 5

Distinctiveness Conflict Risk

The real-time support-chat framing carves a fairly clear niche distinct from generic chat or notification skills, though 'real-time messaging' could overlap with broader messaging/notification skills.

4 / 5

Total

17

/

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 (898 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.