orphan-test
A skill with an orphan reference file
- License 许可
- MIT
- 最近更新
- 2026-11-09
- Stars
- ★ 4
- Forks
- 0
01 前言 Front Matter
- name
- memory-log-render
- category
- kernel
- namespace
- aiwg
- platforms
- [ "all" ]
- description
- Generate a human-readable Markdown view from a consumer's JSON Lines event log
02 资源文件 2
- 参考文档references/unused.md97 B
- 参考文档references/used.md55 B
03 SKILL.md 正文
memory-log-render
Convert a consumer's .log.jsonl into a readable log.md Markdown file. The rendered view uses greppable line prefixes and groups events by date.
When to Use
- On demand: user asks "show me the log" or "render the activity log"
- After bulk operations: post-ingest or post-lint when the log has grown
- As part of
memory-lint --fix: regenerate the rendered view if stale
Parameters
--consumer (optional)
Consumer ID. Resolved via ADR-021 D4 precedence: explicit > wrapper > auto-detect.
--tail (optional, default: all)
Only render the last N entries. Useful for large logs.
--since (optional)
Only render entries after this ISO 8601 date.
--output (optional)
Override output path. Defaults to sibling of .log.jsonl → log.md (e.g., .aiwg/research/.log.jsonl → .aiwg/research/log.md).
Operation
- Resolve consumer — determine which log to render.
- Load topology — read
memory.topology.logpath from consumer'smanifest.json. - Read JSONL — parse each line as JSON. Skip malformed lines (warn in output).
- Group by date — cluster entries by
tsdate portion. - Render Markdown — for each entry, produce:
## [2026-04-14] ingest | anthropic-2024-constitutional.pdf
Touched 3 pages: anthropic.md, constitutional-ai.md, summaries/2024-constitutional-ai.md.
Duration: 14.2s. No contradictions.
- Write output — overwrite the
log.mdfile (this is a generated view, not an append). - Log event — append a
log-renderentry to.log.jsonlviamemory-log-append.
Rendered Format
# Memory Log — research-complete
> Generated from `.aiwg/research/.log.jsonl` on 2026-04-14T16:00:00Z
> 47 events total
---
## [2026-04-14] ingest | paper.pdf
Touched 3 pages: entities/anthropic.md, concepts/constitutional-ai.md, summaries/paper.md.
Duration: 14.2s. No contradictions.
## [2026-04-14] lint | health check
0 errors, 2 warnings, 5 suggestions. Duration: 3.4s.
## [2026-04-13] query-capture | Constitutional AI comparison
Created synthesis/constitutional-ai-comparison.md (comparison).
Added 2 cross-references.
---
*Rendered by memory-log-render*
Line Prefix Convention
Every operation line starts with ## [YYYY-MM-DD] <op> | <subject> — this makes the rendered log greppable:
grep "^## \[" .aiwg/research/log.md | tail -5
grep "ingest" .aiwg/research/log.md
Schema Reference
@semantic-memory/schemas/memory-log-event.md
04 同仓库更多 Skills
doc-audit
Documentation drift auditor and normalizer for CLAUDE.md / AGENTS.md projects (supports Claude Code, Codex, and any project using agent instruction files at root and/or per module). Use when the user says "audit docs", "check doc freshness", "doc drift", "docs out of date", "文档审计", "文档漂移", "检查文档", "文档同步", "memory index", "MEMORY.md check", "normalize docs", "整理文档", "更新文档", "update docs", "doc health", "文档健康". Also triggers implicitly when user mentions stale docs, wrong ports in CLAUDE.md / AGENTS.md, or missing memory entries.
project-onboarding
Scan an unfamiliar codebase, generate CLAUDE.md + OVERVIEW.md, and capture domain knowledge that code alone can't tell you. This skill should be used when the user wants to understand a new project, onboard onto a codebase, set up project documentation, create or update CLAUDE.md, or map project architecture. Common triggers include "what does this project do", "help me get started", "I just joined this repo", "document this codebase", "set up dev docs". Also applies when working on any unfamiliar or inherited project, even without an explicit onboarding request — if the user seems lost in a new codebase, this skill can help.
playwright-web-automation
Playwright browser automation with two modes: (A) Record mode — automate web interactions (forms, clicks, screenshots/Canvas export) requiring JS rendering or login state. (B) Direct scripting — render Mermaid diagrams, charts, or HTML to PNG images without recording. Keywords: playwright, codegen, browser automation, web scraping, architecture diagram, render chart, Mermaid to PNG, screenshot export, canvas export. Do NOT trigger for: static page fetching (use WebFetch/curl), pure API calls, or DOM text extraction without interaction.
code-review
Pragmatic code review & pre-push quality gate. Use when the user says "review code", "check code quality", "any issues with this code", "ready to push", "prepare commit", "submit code", "push to remote", or any variation requesting code inspection before merging or pushing.
bad-frontmatter
暂无简介