l1-promote
Review L2 session facts and promote valuable ones to L1 Atomic Memory. Use at end of session or when L2 accumulates facts worth keeping permanently. Runs add-fact.sh for each promoted fact.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-14
- Stars
- ★ 13
- Forks
- 2
01 前言 Front Matter
- name
- l1-promote
- description
- Review L2 session facts and promote valuable ones to L1 Atomic Memory. Use at end of session or when L2 accumulates facts worth keeping permanently. Runs add-fact.sh for each promoted fact.
03 SKILL.md 正文
L1 Promote Skill
When to trigger
- End of session: "promote facts", "save session facts", "l1-promote"
- When L2 has 3+ facts and session is wrapping up
- After
/sessionshows facts worth keeping permanently - "cuối session", "lưu facts", "promote l2 lên l1"
What to do
Step 1 — List current L2 facts
bash .claude/scripts/search-session-facts.sh
If output is empty or "no session facts found": report "No L2 facts to promote" and stop.
Step 2 — Evaluate each fact for promotion
For each L2 fact, apply this filter — promote only if:
| Criterion | Promote | Skip |
|---|---|---|
| Still true beyond this session? | ✓ | ✗ |
| Reusable in future sessions? | ✓ | ✗ |
| Specific enough to be useful? | ✓ | ✗ |
| About session state only (e.g. "currently editing X")? | ✗ skip | |
| Duplicate of existing L1 fact? | ✗ skip |
Present the list to the user with your recommendation (promote/skip) for each. Ask: "Promote these? [y/n for each or 'all'/'none']"
Step 3 — Run add-fact.sh for approved facts
For each fact approved by the user:
bash .claude/scripts/add-fact.sh
add-fact.sh is interactive — guide the user through:
name: short slug (kebab-case)type: decision | constraint | pattern | reference | warningscope: yamtam | project | globalvalue: the fact contentconfidence: verified | likely | unverifiedtags: comma-separated
Pre-fill from the L2 fact content where possible to reduce typing.
Step 4 — Clear promoted facts from L2
After all promotions:
bash .claude/scripts/clear-session.sh
Confirm with user before clearing. If user wants to keep some L2 facts for next session, skip clear.
Step 5 — Report
L1 Promote Summary
──────────────────
L2 facts reviewed: N
Promoted to L1: N
Skipped: N
L2 cleared: yes/no
Promoted facts are now in memory/L1_atomic/
Search with: /memory <keyword>
Constraints
- Never promote facts about current file state, git branch, or session-specific context.
- Never auto-promote without user confirmation.
- Never run
add-fact.shnon-interactively — it requires user input for quality control. - If
add-fact.shis missing, say so and stop.
04 同仓库更多 Skills
openai--sentry--sentry
Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.
ito-basket-compare
Compare Itô prediction-market baskets against a user's knowledge base, portfolio notes, financial context, watchlist, or research thesis. Use for read-only basket comparison and gap analysis without investment advice or live trading.
implementing-network-traffic-baselining
Build network traffic baselines from NetFlow/IPFIX data using Python pandas for statistical analysis, z-score anomaly detection, and hourly/daily traffic pattern profiling
detecting-evasion-techniques-in-endpoint-logs
Detects defense evasion techniques used by adversaries in endpoint logs including log tampering, timestomping, process injection, and security tool disabling. Use when investigating suspicious endpoint behavior, building detection rules for evasion tactics, or conducting threat hunting for stealthy adversary activity. Activates for requests involving evasion detection, defense evasion analysis, log tampering detection, or MITRE ATT&CK TA0005.
implementing-microsegmentation-with-guardicore
Implementing microsegmentation using Akamai Guardicore Segmentation to map application dependencies, create granular network policies, visualize east-west traffic flows, and enforce least-privilege communication between workloads across data centers and cloud.
ramdisk-tmpfs-patterns
暂无简介