session-memory
Lists and summarizes all Claude Code memories across projects (no keyword required). Use when the user asks what memories exist, wants to see stored knowledge, asks "what do you remember", or wants an overview of their memory files. Also triggered by: "list memories", "show memories", "what's in my memory". For finding memories by keyword/content, use session-memory-search instead.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-15
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- session-memory
- description
- Lists and summarizes all Claude Code memories across projects (no keyword required). Use when the user asks what memories exist, wants to see stored knowledge, asks "what do you remember", or wants an overview of their memory files. Also triggered by: "list memories", "show memories", "what's in my memory". For finding memories by keyword/content, use session-memory-search instead.
- allowed-tools
- Bash(python3 "${CLAUDE_PLUGIN_ROOT}/scripts/sess_memory_scanner.py":*)
02 资源文件 1
- 脚本scripts/smoke_test.py7.8 KB
03 SKILL.md 正文
Session Memory
List and summarize all memory files across projects.
When to Use
- Wants an overview/listing of stored memories (no keyword needed)
- "what do you remember", "list memories", "show memories"
When NOT to Use
- Finding memories by keyword/content → use
session-memory-searchinstead - Health-checking memories (staleness, broken links, duplicates) → use
session-memory-auditinstead
Step 1: Scan all memories
Run the memory scanner to discover all memory files across projects:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/sess_memory_scanner.py" scan
This defaults to JSON (also accepts --format table for a human-readable table instead) — no
--format flag needed for this skill's own JSON-parsing workflow below.
Optional filters — add based on user request:
--type user|feedback|project|reference— filter by memory type--project FILTER— filter by project name (substring match)
Step 2: Present the results
Parse the JSON output and present as a grouped-by-project table:
For each project that has memories, show:
| # | Name | Type | Age | Indexed |
|---|---|---|---|---|
| 1 | Memory name | type |
Nd | yes/no |
At the top, show the summary line:
Found N memories across M projects — N user, N feedback, N project, N reference
Highlight issues if visible:
- If any memory has
indexed: false, note it: "N memories not indexed in MEMORY.md — run thesession-memory-auditskill to fix" - If any memory has
has_frontmatter: false, note it: "N memories missing frontmatter"
Step 3: Suggest follow-ups
Based on what was found, suggest relevant next steps:
- The
session-memory-auditskill — to health-check and fix issues - The
session-memory-searchskill — to search across memory content
Testing & Validation
Eval suite: evals/session-memory/ — 3 scenarios, skill-tester Quick Workflow blind comparison, all
passed. Eval 3 verified the empty-memories case is handled gracefully, stating plainly that no memories
exist rather than fabricating content.
Last dated run record: evals/session-memory/workspace/iteration-1/eval-{1,2,3}/with_skill/grading.json,
2026-09-03. scripts/smoke_test.py structural self-check also passing as of the same date.
Verify this skill activates on:
- "what do you remember"
- "list my memories"
- "show me what's in my memory"
Verify it does NOT activate on:
- "search my memories for X" →
session-memory-search - "check my memory health" →
session-memory-audit
Quality gates:
- [ ] Follow-up suggestions name the sibling skill, never a
/slash-commandthat doesn't exist in this plugin
04 同仓库更多 Skills
demo
Fixture skill used by scripts.marketplace_ci sync tests.
export-demo
Fixture skill used by scripts.marketplace_ci export tests.
work-to-development
Validate an accepted Linear Issue's readiness for implementation (criteria, dependencies, duplicate/existing artifacts) and request governed branch/worktree creation through git-kit:starting-work — recording work-started Git/GitHub evidence and a deliberate Linear Started transition only after Git identity is read back and verified. Use when asked to start work on a Linear issue, begin development for an accepted issue, or prepare an accepted issue for implementation. Never creates a branch directly — always delegates to git-kit.
work-linking
Create and maintain stable cross-system links and authority labels between Notion and Linear records, and detect/repair drift between them. Use when asked to link a Notion record to a Linear record, check for drift between Notion and Linear, or repair a broken/stale link. Repairs only the bounded non-authoritative copy or link — never chooses by newest timestamp, and never creates a reverse-write loop against either system's own authority.
status-and-learning
Produce a dated, explicitly non-live Linear-to-Notion progress summary, or capture an outcome/learning after work completes. Use when asked to summarize progress to Notion, report portfolio status, or capture what was learned from a completed piece of work — not to disposition open follow-up items (see open-item-management for that). Never runs automatically or continuously — every summary is a deliberate, approved snapshot, not a live sync.
repository-gates
Discover, delegate, record, and invalidate this repository's actual Git/GitHub lifecycle gates (pre-commit, pre-push, PR required checks, Codex delta review, review requirements, merge rights) and the repository-policy provider profile that maps governed operations to git-kit. Use when asked what gates apply to this repository, to discover repository policy before starting Wave 2 work, or to check whether prior gate evidence is still valid after new commits. Discovery and delegation only — never executes a gate's own internal logic, and never invents a gate the repository doesn't actually define (in particular, never assumes a "Review Changes" gate exists).