Menü
Archive Claude Code conversation logs into the current project as JSONL and readable Markdown
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Use when someone is about to lose access to a machine (shared server, lab box, cloud/VM instance, expiring rental) and needs to preserve all their work before it's gone. Systematically finds everything that exists ONLY on that machine — unpushed commits, stashes, untracked/uncommitted files, dirty submodules, non-git dirs, loose files, and large gitignored artifacts — and backs it up to GitHub / HuggingFace / an off-machine archive, non-destructively. Triggers on "losing access to this machine", "back up everything before I lose the server", "migrating off this box", "decommission", "my instance expires".
Use when preparing a paper's camera-ready or arXiv release — de-anonymizing an accepted submission, packaging an arXiv tarball, checking dual-submission safety against a concurrent venue (e.g. a paper accepted at a workshop that's also under review at NeurIPS/ICML), or flagging reviewer-requested post-review additions. Encodes a byte-identity discipline (the public version changes ONLY author/venue metadata, never content), a numbers-from-scripts integrity gate, and the arXiv mechanics that actually bite.
Spin up one or more fresh-context subagents to critically evaluate a proposed theory, hypothesis, interpretation, or experimental design before committing to it. Use when the user says "have an agent critique this" / "get a second opinion on" / "is this design sound" / invokes /critique, or proactively before running any experiment or committing to a non-trivial theoretical claim.
Use when launching a multi-hour neural-network training, fine-tune, or other long GPU job autonomously from Claude Code and you need to catch failures (NaN, stuck-at-chance, dead process, throughput collapse, OOM) early instead of waking up to a wasted GPU window.
Use when the user asks to check, audit, or improve a website or web project for accessibility (a11y), WCAG compliance, screen reader support, keyboard navigation, color contrast, or alt text. Triggers a plan-mode investigation against the TeachAccess design and code checklists, then implements approved fixes.
Consolidate scattered research notes, logs, experiment outputs, and submodule docs into a single living research paper. Use when the user wants to pull together multiple source documents into one structured paper.
| name | archive-logs |
| description | Archive Claude Code conversation logs into the current project as JSONL and readable Markdown |
| disable-model-invocation | true |
Archive the Claude Code conversation logs from this project into the project itself, for auditability and transparency.
Find logs: Look in ~/.claude/projects/<encoded-path>/ where the encoded path replaces / with - in the current working directory path. List *.jsonl files (top-level only, not subdirectories).
Identify sessions: For each JSONL, extract the first user message to understand the session topic. Skip files with 0 user messages. Assign descriptive numbered names (e.g. 01_initial_setup.jsonl, 02_feature_work.jsonl).
Check for duplicates: If logs/conversation/ already exists, compare against existing files to avoid re-archiving.
Copy JSONL files into logs/conversation/ in the project.
Create a converter script at scripts/jsonl_to_markdown.py that converts JSONL to readable Markdown. The JSONL format:
type fielduser and assistant contain message.content (string or array of content blocks)text (render), tool_use (show tool name + concise input), tool_result (abbreviate), thinking (omit)<system-reminder> tags from user messagesRun the converter to generate .md files alongside the .jsonl files.
Scan for secrets: Install detect-secrets (uv add --dev detect-secrets or ensure it's available), then run detect-secrets scan logs/conversation/ on all archived files (both .jsonl and .md). If any secrets are detected:
echo $API_KEY, env variable dumps, credential outputs.Write logs/conversation/README.md listing each session.
Report what was archived (and whether the secret scan passed cleanly).