메뉴
Maintain and release the crawlkit Go library, preserving downstream compatibility for gitcrawl, slacrawl, discrawl, and notcrawl.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Select, review, repair, validate, and land batches of up to 20 low-risk OpenClaw contributor pull requests using Vincent's maintainer preferences and bounded sub-agent lanes. Use for "next 20", broad contributor PR sweeps, merge-candidate mining, or continued PR-batch work where drafts, maintainer work, trivial one-line changes, UI, security, migrations, and high-risk changes must be excluded.
Recover Codex and Claude sessions from tmux cockpit panes, CX SAVE snapshots, codex-cockpit history, and recent Codex logs without overwriting the useful restore source first.
Manage one tmux agent lane from its matching ops pane, inspect live pane state and Codex logs on cold start, and produce concise manager summaries for OpenClaw and adjacent project work.
Build local semantic review slices by combining clawpatch feature maps, deepsec threat candidates, visual review maps, and optional gitcrawl/discrawl evidence for repos such as openclaw/openclaw.
Initialize, configure, index, start, verify, troubleshoot, or sync codebase-memory-mcp knowledge graphs and the HTTP graph UI for local repositories. Use when the user mentions codebase memory MCP, search_graph, trace_path, graph UI, index_repository, or wants code discovery via the codebase-memory-mcp server.
Template skill for repository authors; excluded from public publishing.
| name | crawlkit |
| description | Maintain and release the crawlkit Go library, preserving downstream compatibility for gitcrawl, slacrawl, discrawl, and notcrawl. |
| license | MIT |
| metadata | {"source":"https://github.com/vincentkoc/dotskills"} |
Maintain crawlkit, the shared Go library for crawl app archive infrastructure. Use this skill to keep shared archive infrastructure reusable, tagged, and safe for downstream app branches.
crawlkit.gitcrawl, slacrawl, discrawl, or notcrawl can merge
against a released crawlkit tag.crawlkit Go module release.Work in /Users/vincentkoc/GIT/_Perso/crawlkit unless the user points at a
different checkout.
Read repo-local AGENTS.md, README.md, CONTRIBUTING.md, and
docs/publishing.md before release or compatibility work.
Keep provider-specific logic out of crawlkit. Shared mechanics belong in
packages such as config, store, snapshot, mirror, state, output,
progress, tui, cache, and control.
Run the library gate with workspace masking disabled:
GOWORK=off go mod tidy
git diff --exit-code -- go.mod go.sum
GOWORK=off go vet ./...
GOWORK=off go test -count=1 ./...
For release checks, verify the signed tag and public Go proxy:
git tag -v <version>
GOPROXY=https://proxy.golang.org GONOSUMDB= go list -m github.com/vincentkoc/crawlkit@<version>
For downstream readiness, inspect app branches read-only. Confirm they are
clean, rebased, require the released crawlkit version, and pass:
GOWORK=off go test ./...
<app> --help
<app> --version
<app> metadata --json
<app> status --json
<app> tui --json
Use temp HOME, XDG_CONFIG_HOME, and XDG_CACHE_HOME for CLI smokes.
Never mutate live app archives.
v0.4.0.crawlkit change or readiness report.