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-2/

{
  "context": "Tests whether the agent correctly handles HISTORY.md overflow (51 entries > 50 max): summarizing the oldest 25 into a [SUMMARY] block, deleting those individual entries, and keeping only the summary plus the newest 25 entries. Also verifies that the next steps generation proceeds correctly after this maintenance step.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "HISTORY.md entry count reduced",
      "description": "The output HISTORY.md has fewer entries than the 51-entry input (overflow was processed, not ignored)",
      "max_score": 10
    },
    {
      "name": "SUMMARY block present",
      "description": "HISTORY.md contains a [SUMMARY] entry block (the summarized form of the oldest 25 entries)",
      "max_score": 15
    },
    {
      "name": "Oldest 25 entries removed",
      "description": "HISTORY.md no longer contains the 2026-01-05 through 2026-01-29 individual entries as separate lines (they were the oldest 25 and should be summarized)",
      "max_score": 12
    },
    {
      "name": "Newest 25 entries retained",
      "description": "HISTORY.md retains individual entries from 2026-02-01 onward (the newer 26 entries minus the one summarized, keeping approximately 25-26 recent entries)",
      "max_score": 10
    },
    {
      "name": "SUMMARY includes period",
      "description": "The [SUMMARY] block includes a date period field (e.g., 'period: 2026-01-05-2026-01-29' or similar range)",
      "max_score": 8
    },
    {
      "name": "SUMMARY includes entry count",
      "description": "The [SUMMARY] block includes an entries count field (e.g., 'entries: 25')",
      "max_score": 8
    },
    {
      "name": "Next steps section present",
      "description": "response.md includes a Next Steps section with suggestions (generation was not blocked by the maintenance operation)",
      "max_score": 7
    },
    {
      "name": "Correct suggestion count",
      "description": "The next steps section shows exactly 5 suggestions (matching display-count: 5)",
      "max_score": 8
    },
    {
      "name": "Context-relevant suggestions",
      "description": "At least 2 suggestions are specifically related to the D3 chart work just completed (e.g., mention testing, accessibility, Storybook, TypeScript types, performance, animation, or tooltip improvements)",
      "max_score": 10
    },
    {
      "name": "Standard format used",
      "description": "The next steps section uses the standard format with '## ⚡ Next Steps' header and numbered emoji-prefixed items",
      "max_score": 7
    },
    {
      "name": "Not blocked by overflow",
      "description": "The response does NOT indicate that next steps could not be generated, or that there was an error processing history — the agent proceeded with generation after maintenance",
      "max_score": 5
    }
  ]
}

evals

tile.json