메뉴
Create a pull request with full validation. Use when ready to submit work for review.
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
Parallel map-reduce bulk ingest for large source sets. Map phase dispatches read-only knowledge-extractor agents (≤N-wide, default Haiku) emitting per-source JSON extracts; Python routes extracts by target library file (fuzzy-merging new topics, pre-allocating new files, flagging oversized topics); reduce phase dispatches one agent-knowledge-updater per file (parallel, one writer per file); single shelf-index rebuild + one log.md entry. Resumable. Supersedes kb-ingest-batch.
Initialise a project for knowledge base use. Appends the [Knowledge Base] section to the project's CLAUDE.md, creates the library/ directory structure, optionally seeds with three example library files from the Agentic SDLC research, and reports next steps. Run once after installing sdlc-knowledge-base.
Drive agent-knowledge-updater over a batch of staged files in library/raw/. Tracks progress in .batch-progress.json for resume support. Sequential by default; --parallel <N> opt-in (max 5). Single shelf-index rebuild and one consolidated log.md entry at the end.
Health-check the project knowledge base. Looks for contradictions between files, stale claims that newer sources have superseded, orphan files with no inbound cross-references, important concepts mentioned but lacking their own page, missing cross-references, and data gaps. Returns a structured report; does not auto-fix.
Stage source files into library/raw/, converting non-markdown formats via markitdown (PDF/DOCX/PPTX/XLSX/HTML/CSV) or pandoc (TeX/EPUB/RST/ORG). Adds provenance frontmatter. No agent dispatch.
Pure-Python knowledge base statistics dashboard. Reads shelf-index and log.md; emits Inventory, Layer distribution, Domain distribution, Recent Activity, and Staleness sections. No agent dispatch. Read-only.
| name | pr |
| description | Create a pull request with full validation. Use when ready to submit work for review. |
| disable-model-invocation | true |
| argument-hint | [base-branch] |
Run full validation, then create a PR if clean.
/sdlc-core:validate --pre-push
If validation fails, report the issues and stop. Do NOT push or create PR.
Re-verify any test counts cited in the PR body.
--pre-push runs the pytest suite only. If the draft PR body cites results
from integration smokes, E2E suites, soak tests, container tests, or any
other harness outside local-validation.py, re-run those exact suites
in this session and update the counts in the body to match the fresh run.
Example: a PR body saying "266 unit tests, 20/20 container smoke, 8/8
sequential E2E, 18/18 fresh-user-flow" requires pytest tests/ -q,
bash tests/integration/workforce-smoke/run-containers.sh,
bash tests/integration/workforce-smoke/run-e2e.sh, and
bash tests/integration/workforce-smoke/run-fresh-user-flow.sh to all
run this session before the PR is opened.
Session memory of test counts goes stale fast — fixtures grow, assertions drift, environments change. Only numbers you have just observed this session belong in the body. If a suite cannot run in this environment (missing binary, no Docker, etc.), delete the number from the body and say so explicitly rather than leaving a stale figure that cites another machine's result.
If the PR already exists and counts have drifted post-creation, update the body in place rather than closing and recreating:
gh pr edit <number> --body-file <updated-body.md>
Verify required artifacts exist:
docs/feature-proposals/retrospectives/If validation passes, proceed:
git branch -vvgit push -u origin <branch>main unless $ARGUMENTS specifies otherwiseCreate the PR using gh pr create:
gh pr create --title "<short title under 70 chars>" --body "$(cat <<'EOF'
## Summary
<1-3 bullet points summarizing the changes>
## Changes
<List of files modified/created>
## Test plan
- [ ] `/sdlc-core:validate --pre-push` passes
- [ ] CI pipeline passes
<additional test steps as needed>
🤖 Generated with [Claude Code](https://claude.com/claude-code)
EOF
)"