Install
$ agentstack add skill-nanorhino-weight-loss-skill-streak-tracker ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Streak Tracker
> ⚠️ SILENT OPERATION: Never narrate internal actions or tool calls.
Philosophy
- Celebrate presence, never punish absence. Streak alive → amplify. Breaks → say nothing.
- Name the effort, not the number. Connect milestones to what it took, not just the count.
- One celebration, then move on. Don't revisit past milestones as motivation.
- Never compare. Never reference longest streak or previous streaks.
What Counts as a "Logged Day"
data/meals/YYYY-MM-DD.json contains at least one meal with actual food data (items or foods array non-empty).
Script
# Get streak info (also persists to data/streak.json)
python3 {baseDir}/scripts/streak-calc.py info \
--data-dir {workspaceDir}/data/meals \
--workspace-dir {workspaceDir} \
--tz-offset {tz_offset}
# Mark milestone as celebrated
python3 {baseDir}/scripts/streak-calc.py celebrate \
--data-dir {workspaceDir}/data/meals \
--workspace-dir {workspaceDir} \
--tz-offset {tz_offset} \
--milestone
info output
{
"current_streak": 7,
"longest_streak": 14,
"streak_start_date": "2026-03-26",
"last_logged_date": "2026-04-01",
"today": "2026-04-02",
"pending_milestone": 7,
"milestones_celebrated": [3]
}
pending_milestone: highest uncelebrated milestone reached.nullif none.- On streak break (current = 2
andpending_milestone` is null:
- State count as
current_streak - 1(today's meal not logged yet). - Add a free half about getting to know the user's eating habits. One sentence. Vary daily.
- Themes: learning their taste, noticing patterns, feeling closer. Always food-related.
Milestone celebration
When pending_milestone is not null, replace the daily line with a bigger celebration. After sending, call streak-calc.py celebrate --milestone .
Milestones and examples → references/streak-milestones.md
No streak line
When current_streak < 2: compose the opening normally. No streak mention.
Break Handling
- Script resets
milestones_celebratedautomatically on new streak. - Say nothing. Never mention a broken streak or compare to previous.
- New streak day 1 starts silently. Milestone 3 re-celebrates as if first time.
User Asks About Streak
Run streak-calc.py info and respond naturally:
- Active: state count and start date.
- None: frame as invitation ("Log a meal and that's day one.").
Data Schema — data/streak.json
Persisted on every streak-calc.py info run. Other skills can read directly.
{
"current_streak": 7,
"longest_streak": 14,
"streak_start_date": "2026-03-26",
"last_logged_date": "2026-04-01",
"milestones_celebrated": [3, 7]
}
longest_streak preserved across streak resets.
Skill Routing
Priority Tier: P4 (Reporting). Data utility — doesn't own conversations. See SKILL-ROUTING.md for conflict resolution.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: NanoRhino
- Source: NanoRhino/weight-loss-skill
- License: MIT
- Homepage: https://nanorhino.com/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.