jayli/export_codex
skills/export_codex/SKILL.md
Export current Codex CLI session conversation to project-local log files. MUST only trigger when explicitly invoked by skill name (/export_codex) — never auto-trigger.
tools
Updated May 7, 2026
$ install --global
skillsauthnpx skillsauth add jayli/skills export_codexInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 7, 2026, 7:25 AM200.1s2 files scanned
SKILL.md
- name:
- export_codex
- description:
- Export current Codex CLI session conversation to project-local log files. MUST only trigger when explicitly invoked by skill name (/export_codex) — never auto-trigger.
- user-invocable:
- true
export_codex
This skill is only for Codex CLI sessions.
IMPORTANT: This skill must ONLY be triggered when the user explicitly invokes it by name (/export_codex). Do not auto-trigger or context-trigger this skill under any circumstances.
Purpose
Export current-session dialogue (user + assistant) after the latest /clear marker into:
.codex/logs/YYYY-MM-DD-0001.txt
0001 increments automatically per day.
Run
From project root:
python3 .codex/skills/export_codex/export_session.py
Optional:
python3 .codex/skills/export_codex/export_session.py --session /absolute/path/to/rollout-xxxx.jsonl
Notes
- Reads source session files from
~/.codex/sessions. - If no
/clearmarker is found in the current session log, it exports from the first message in that session. - Output is plain text and includes timestamp + role for each message.
Related Skills
jayli/planify
tools
VerifiedTrustedCommunity
Detect and upgrade a skill to plan file-driven mode. Usage - /planify <skill-name>
SKILL.mdUpdated May 7, 2026
jayli/health
development
VerifiedTrustedCommunity
Use when needing comprehensive project health analysis, code quality assessment, security audit, or generating structured health check reports for codebases. Optimized for assessing historical debt vs current code quality.
SKILL.mdUpdated May 7, 2026
jayli/commit
tools
VerifiedTrustedCommunity
Analyze git changes, stage as needed, generate a Conventional Commit message, and create a commit.
SKILL.mdUpdated May 7, 2026
jayli/skills/claude-oil
development
VerifiedTrustedCommunity
--- name: claude-oil description: "为 CLAUDE.md 注入"润滑油"，让第三方模型与 Claude Code 配合更流畅。仅当用户通过 /claude-oil 显式调用时触发，不自动触发。" --- # Claude 润滑油 (claude-oil) > 让第三方模型与 Claude Code 的配合如丝般顺滑 ## 触发条件 **本 skill 仅通过显式调用触发，绝不自动触发。** - ✅ `/claude-oil` — 用户明确输入完整 skill 名称时触发 - ❌ 上下文匹配、关键词匹配、隐式条件 — 均不触发 这是为了避免在执行正常任务时，被本 skill 的执行契约覆盖原有行为。 ## 使用场景 当你通过 `/claude-oil` 显式调用本 skill，且使用第三方模型 API（如 kimi/qwen/glm）接入 Claude Code 时： 遇到这些问题： - 任务执行到一半突然中断等待确认 - 多步骤任务无法自动连续执行 - 工具调用后不知道如何继续 - 出错后只会道歉不会恢复 **使用本 skill，
SKILL.mdUpdated May 7, 2026