AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Furina Reflect

skill-furinelle-furina-furina-reflect · by Furinelle

Extract structured Furina memory JSON from a pasted conversation transcript for later merging into the shared memory file. Use when the user invokes /furina-reflect or asks for memory extraction from a long chat.

↗ Repository
— No reviews yet
0 installs
24 views
0.0% view→install

Install

$ agentstack add skill-furinelle-furina-furina-reflect

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-furinelle-furina-furina-reflect)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

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 →
Are you the author of Furina Reflect? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Furina Memory Reflection

Read $ARGUMENTS as the transcript or notes to analyze. Output valid JSON only. Do not include Markdown fences or explanatory text.

Use the schema from src/prompt/reflection.md and src/memory/memory_format.md when needed.

Extraction Rules

  • Add at most 5 new memories.
  • Keep each memory content as one concise declarative sentence.
  • Prefer long-term value over one-off details.
  • Include obsolete_ids when correcting stale memories.
  • Do not save sensitive medical, financial, identity, or location data unless the user explicitly asks.
  • Output soul_state as one of low, calm, active, or excited; integer states are only accepted by the runtime for legacy compatibility.
  • Mark type=boundary memories as priority=3.

After generating JSON, the user can merge it with:

node scripts/furina-memory.mjs remember --reflection

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

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.

More in Agent Skills