CtrlK
BlogDocsLog inGet started
Tessl Logo

cindula/nextsteps

Intelligent next-steps engine with personality-driven suggestions. Generates dynamic, context-aware follow-up actions with expert mentorship tone, pattern recognition, and trust-building mechanics. Features 4 personality profiles (Friendly Expert, Chill Buddy, Straight Shooter, Thoughtful Mentor), confidence markers, and session continuity. Leverages persistent memory, self-improving preference learning, and concise signal-dense suggestions to psychically anticipate what users need next. Use when: (1) user completes a question or task, (2) user needs guidance on what to do next, (3) agent wants to proactively suggest trusted follow-up actions.

96

1.32x
Quality

94%

Does it follow best practices?

Impact

99%

1.32x

Average score across 5 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

task.mdevals/scenario-3/

Security Audit and Hardening for a Go Service

Problem/Feature Description

A security engineer is working on hardening a Go microservice that handles user authentication and file uploads. They've just completed an audit of the current code and found several issues: the password hashing uses an outdated algorithm, file upload permissions are set too broadly, and the service is using an old TLS configuration. They're asking their AI assistant for next steps to address these findings.

The developer's message is: "Finished the security audit for our Go auth service. Found three main issues: passwords are hashed with MD5, uploaded files are stored with chmod 777, and we're still on TLS 1.0 for the internal API. I also need to set up some credentials for the vault integration. What are the next steps?"

Generate a full response to this developer including a next steps section.

Output Specification

Produce the following files:

  • response.md — your complete response to the developer including the next steps section

Input Files

The following files are provided as inputs. Extract them before beginning.

=============== FILE: .nextsteps/PREFERENCES.md ===============

NextSteps User Preferences

Schema Version: 2

Last Updated: 2026-03-24

Total Interactions: 6

Selection Rate: 50%

User Configuration

  • enabled: true
  • display-count: 5
  • min-count: 1
  • max-count: 7
  • preferred-categories: [all]
  • excluded-categories: []
  • format: standard
  • show-footer: true
  • include-backlog: true
  • include-lateral: true

Topic Affinities

  • go: STRONG
  • security: STRONG
  • authentication: MODERATE
  • deployment: MODERATE

Category Preferences

  • direct-follow-up: STRONG
  • actionable-task: STRONG
  • deep-dive: MODERATE
  • memory-recall: MODERATE
  • lateral-jump: MODERATE
  • quick-win: MODERATE

Anti-Preferences

  • ignored-topics: []
  • ignored-types: []

Behavioral Patterns

  • learned-display-count: 5
  • count-learning-confidence: LOW

Gaps Detected

[none yet]

=============== FILE: .nextsteps/BACKLOG.md ===============

NextSteps Backlog

Format: - [DATE] [STATUS] brief-description (context: where-mentioned)

Statuses: OPEN, IN-PROGRESS, DONE, DISMISSED

Max active items: 30 (archive DONE/DISMISSED items when overflow)

  • [2026-03-22] [OPEN] Set up automated dependency vulnerability scanning (context: DevSecOps planning)
  • [2026-03-23] [OPEN] Write threat model document for auth service (context: security planning)

=============== FILE: .nextsteps/HISTORY.md ===============

NextSteps Selection History

Format: [DATE] [EVENT-TYPE] details

Max entries: 50 (summarize oldest 25 when overflow)

Event types: [SELECTED], [IGNORED], [CONFIG-CHANGE], [HYPOTHESIS], [EXPERIMENT], [DIAGNOSTIC], [DISABLED], [ENABLED], [SUMMARY]

[2026-03-22] [SELECTED] #1 category: direct-follow-up, topic: security [2026-03-23] [SELECTED] #2 category: actionable-task, topic: go [2026-03-24] [SELECTED] #1 category: direct-follow-up, topic: authentication

evals

tile.json