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.

65

Quality

79%

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/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

63%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 and well-sequenced, with executable code for five frameworks, but it is over-long and monolithic: redundant framework implementations and reference material that should live in separate bundle files inflate the token cost and undermine progressive disclosure.

Suggestions

Move the per-framework implementation guides (Rails, React, Next.js, PHP, Vue) into separate files under references/ and keep SKILL.md as an overview with one-level-deep links, cutting the bulk of the redundancy.

Replace the pseudocode in Steps 1-7 with a single concrete executable example (or explicitly justify the pseudocode as stack-agnostic), so the core guide is copy-paste ready like the framework sections.

Add per-step validation checkpoints (e.g., verify the migration and channel subscription work before moving to the frontend) instead of relying solely on the post-implementation Testing Checklist.

DimensionReasoningScore

Conciseness

The ~890-line body re-implements the same hook/logic across five frameworks plus a pseudocode core; it is dense real code rather than explanations of basics, but the framework duplication is unnecessary token spend that could be tightened.

3 / 5

Actionability

Framework sections (Rails models/migrations, React hook+component, PHP events, Vue composable, Next.js route) are copy-paste executable, but the core Steps 1-7 are unjustified pseudocode, leaving a gap below fully executable.

4 / 5

Workflow Clarity

A clear seven-step build sequence is backed by a Testing Checklist and Common Pitfalls, but mid-flow validation checkpoints are absent and verification is post-hoc rather than per-step.

4 / 5

Progressive Disclosure

Good internal section headers provide structure, but no bundle files exist and framework-specific guides plus DB/email/realtime reference tables that belong in separate files are all inlined in a monolith.

3 / 5

Total

14

/

20

Passed

Description

95%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, third-person description that clearly states what the skill builds and when to invoke it, with natural multi-synonym trigger phrases. Its only weakness is that capability specificity leans on a single verb plus two named components rather than a list of distinct actions.

DimensionReasoningScore

Specificity

Names the domain and concrete deliverables ('floating widget for users', 'admin dashboard for support staff') but relies on essentially one verb ('Build'), so it lists several specific components with minor coverage gaps rather than the multiple distinct verbs of a 5.

4 / 5

Completeness

Explicitly answers both 'what' (build widget + dashboard system) and 'when' ('Use when the user wants...') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Four natural trigger phrases with synonym variation ('live chat, customer support chat, real-time messaging, or in-app support') give comprehensive coverage of terms users would actually say.

5 / 5

Distinctiveness Conflict Risk

Clear support-chat niche with distinct triggers; 'real-time messaging' is slightly broad but the support context anchors it and conflict risk is minimal.

5 / 5

Total

19

/

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.