Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Persistent Memory Bridge — measured AI agent skill | DecimalAI

stijnman/persistent-memory-bridge

SkillScore95Maintained

Bridges session memory to persistent storage across conversations. Use when continuity needed or user says remember this, persistent memory. Triggers: r emember this, persistent memory, save to memory, recall later.

by stijnman

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Knowledge Management pack

decimalai skills pull stijnman-persistent-memory-bridge

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/stijnman-persistent-memory-bridge/SKILL.md

Raw file: /s/stijnman-persistent-memory-bridge/SKILL.md ↗ · machine-readable summary at /s/stijnman-persistent-memory-bridge.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 7d ago

Yes — +68% lift+16% tokens0% turns95% of whole cases pass with skill (21/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	166%	0%
case-02	✗→✓	▲ Improved	112%	0%
case-03	✗→✓	▲ Improved	53%	0%
case-04	✗→✓	▲ Improved	-9%	0%
case-05	✗→✓	▲ Improved	84%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

stijnman / grok-custom-skills

.grok/skills/persistent-memory-bridge/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

Persistent Memory Bridge

When to Use

User says remember this or task matches this capability
User says persistent memory or task matches this capability
User says save to memory or task matches this capability
User says recall later or task matches this capability

Workflow

Extract durable facts: preferences, project state, decisions.
Run memory-sanitizer before persist.
Write to semantic-memory-manager store.
Confirm what was saved; offer forget option.

Integrations

semantic-memory-manager
memory-sanitizer
user-preference-profiler

Error Handling

| Failure | Response | |---------|----------| | Storage full | Prune lowest-trust entries first. |

Gotchas

Never persist secrets or credentials.

Example

Input: User request matching triggers above. Output: Structured result per workflow with integrations invoked as needed.

Want to see if stijnman/persistent-memory-bridge would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.