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

criteria.jsonevals/scenario-5/

{
  "context": "Tests whether the agent correctly processes multiple customization requests (format change, category exclusion, count change), validates and applies them to PREFERENCES.md, logs each change in HISTORY.md, and enforces the security rule preventing secrets from persisting in .nextsteps/ files.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "format updated to compact",
      "description": "PREFERENCES.md shows 'format: compact' (changed from standard)",
      "max_score": 8
    },
    {
      "name": "lateral excluded",
      "description": "PREFERENCES.md shows 'excluded-categories: [lateral-jump]' or equivalent (lateral suggestions excluded as requested)",
      "max_score": 8
    },
    {
      "name": "display-count set to 3",
      "description": "PREFERENCES.md shows 'display-count: 3' (changed from 5)",
      "max_score": 8
    },
    {
      "name": "CONFIG-CHANGE logged for format",
      "description": "HISTORY.md contains a [CONFIG-CHANGE] entry for the format property change (old: standard, new: compact)",
      "max_score": 8
    },
    {
      "name": "CONFIG-CHANGE logged for count",
      "description": "HISTORY.md contains a [CONFIG-CHANGE] entry for the display-count property change (old: 5, new: 3)",
      "max_score": 8
    },
    {
      "name": "CONFIG-CHANGE logged for excluded-categories",
      "description": "HISTORY.md contains a [CONFIG-CHANGE] entry for the excluded-categories / lateral change",
      "max_score": 8
    },
    {
      "name": "Secret removed from BACKLOG.md",
      "description": "The output BACKLOG.md does NOT contain the string 'postgres://', 's3cr3tpassword', or 'db_conn=' (the connection string secret is removed)",
      "max_score": 12
    },
    {
      "name": "No secret in any .nextsteps/ file",
      "description": "Neither PREFERENCES.md nor HISTORY.md contain any secret patterns such as 'password=', 'secret=', 'sk-', or 'token='",
      "max_score": 10
    },
    {
      "name": "Compact format next steps",
      "description": "The next steps section in response.md uses compact format (e.g. '⚡ Next: [1] Title | [2] Title | [3] Title') rather than the full numbered list standard format",
      "max_score": 10
    },
    {
      "name": "Correct count in output",
      "description": "The next steps section shows exactly 3 suggestions (matching the newly configured display-count: 3)",
      "max_score": 10
    },
    {
      "name": "No lateral suggestions shown",
      "description": "The next steps section does NOT include any 💡 Lateral/Out-of-the-Box suggestions (they are now excluded)",
      "max_score": 10
    }
  ]
}

evals

tile.json