菜单
Search past Claude Code sessions to recall prior solutions, commands, fixes, and decisions. Use when the user references earlier work ("how did I fix", "last time we", "pick up where we left off", "a few months ago", "what was that … I set up", "didn't I once").
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Sync this Claude Code config against new release notes — find config features added since the pinned baseline that this config should adopt. Use when Claude Code has been updated, when the user asks what's new / what changed / whether to adopt new settings or hooks, after a version bump, or when checking config currency against the latest release. Reports adoptable settings/hooks/env-vars/permissions as a risk-tiered proposal, then bumps the baseline. Do NOT use for auditing existing config quality, debugging hooks, or organizing rules — that is `maintaining-claude-code`.
Monitor and watch GitHub Actions CI/CD pipeline runs in real time. Use when the user has pushed code and wants to watch the build, check CI status, see if tests passed, monitor a pipeline, or wait for a workflow run to complete. Also use after any `jj git push` or `git push` command. Reports pass/fail with failed job logs. Do NOT use for writing or editing CI workflow YAML files, optimizing CI config, or debugging CI configuration — only for monitoring active runs.
Reorganize and clean up messy commit history on a feature branch into logical, reviewable commits. Use when cleaning up commits, preparing a branch for review, separating formatting from logic changes, fixing broken intermediate states, or squashing WIP commits.
Audit and improve Claude Code hooks, rules, and settings.json. Use when adding/debugging a hook, organizing rules, auditing settings.json (permissions, env vars, stale flags), or deciding between hook vs skill vs rule vs CLAUDE.md. For SKILL.md authoring use the skill-creator plugin; for CLAUDE.md audits use the claude-md-improver plugin.
Execute a structured test plan and emit a concise results document (JSON + Markdown). Use when running test plans, executing QA workflows, verifying acceptance criteria systematically, or producing test results documentation.
Query, create, and manage Linear issues from the command line. Use when checking assigned work, viewing issue details, creating new issues, or updating issue status.
| name | searching-history |
| description | Search past Claude Code sessions to recall prior solutions, commands, fixes, and decisions. Use when the user references earlier work ("how did I fix", "last time we", "pick up where we left off", "a few months ago", "what was that … I set up", "didn't I once"). |
| argument-hint | <search-query> |
Search your Claude Code conversation history using hybrid search (text + semantic).
Figure out the search query yourself, then run glhf search — never run it empty and never bounce the question back to the user.
/glhf <query> → use $ARGUMENTS as the query: glhf search "$ARGUMENTS" --compact$ARGUMENTS is empty. Derive concise search terms from what the user is trying to recall (the topic, error text, command, or project they referenced) and run the search with those. Do not ask them to restate it.Example: user says "what was that cargo alias I set up?" → run glhf search "cargo alias" -t Bash --compact. Then read the hits and answer; chain into glhf session <id> --summary if you need fuller context.
# Find past solutions
glhf search "authentication" --compact
# Find commands you've run
glhf search "docker" -t Bash --compact
# Filter by project and time
glhf search "bug" -p myapp --since 1w --compact
# Find errors
glhf search "failed" --errors --compact
# Check recent sessions
glhf recent -l 10
# Get session overview then dive deeper
glhf session abc123 --summary
glhf session abc123 --limit 30
| Command | Purpose |
|---|---|
search | Find content across all sessions |
session | View a specific session's content |
recent | List recent sessions |
status | Show index stats |
index | Update index (incremental by default) |
| Flag | Purpose |
|---|---|
--compact | One-line output, fewer tokens |
-l/--limit | Max results to return (default 10) |
-t/--tool | Filter by tool (Bash, Read, Edit, Grep, etc.) |
-p/--project | Filter by project name (substring match, . = cwd) |
--since | Time filter (1h, 2d, 1w, or date) |
--errors | Only show error results |
--json | Machine-readable JSON output |
| Flag | Purpose |
|---|---|
--summary | Show session summary without content |
-l/--limit | Show only first N messages |
--json | Machine-readable JSON output |
Find past solutions:
glhf search "problem description" --compact
glhf search "specific keyword" --compact
glhf session <id> --summary
Recall commands:
glhf search "git rebase" -t Bash --compact
glhf search "cargo" -t Bash --since 1w --compact
Find errors:
glhf search "error" --errors --since 1d --compact
Browse recent work:
glhf recent -l 10
glhf recent -p myproject
--compact — significantly reduces output tokensglhf session <id> --summary for full context-p . to filter to current project--json when piping to other tools or processing programmaticallyglhf index only re-processes changed files. Use --full to rebuild, --skip-embeddings for text-only indexingglhf index to update