promote
Promote select cross-repo transcendent learnings into the context-library engineering journal as proposed, gated, idempotent entries.
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。
菜单
Promote select cross-repo transcendent learnings into the context-library engineering journal as proposed, gated, idempotent entries.
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。
基于 SOC 职业分类
Route proposed Team Mimir profile behavior changes into target-owned Hermes dialogue after producer-owned custody classification.
Compile and review an approved Workflow Contract for Codex V2 graph, profile, write, check, reviewer, fallback, and external-action consistency without launching work.
Explicitly run an operator-approved Infiquetra Workflow Contract as a root-orchestrated Codex V2 DAG with exact profiles, runtime receipts, bounded writes, one independent review, one remediation, and one targeted recheck.
Deep-dive one chosen Infiquetra idea into a right-sized requirements document before planning.
Run a structured Infiquetra code-quality review at the work-to-PR boundary. Reads the merge-base diff, runs a built-vs-planned audit plus judgment-selected review lenses, validates findings, writes a durable review artifact, appends to the work-thread saga, and routes — without mutating code. Triggers on "review this PR", "code review", "check my diff", "pre-PR review", or a /work hand-in before shipping.
Review Infiquetra plans, requirements, and SDLC documents for implementation readiness.
| name | promote |
| description | Promote select cross-repo transcendent learnings into the context-library engineering journal as proposed, gated, idempotent entries. |
saga:promote is a journal-promotion workflow, not an outcome orchestration
subcommand. It scans repo-local engineering journals, identifies the few lessons
that deserve org-wide status, and prepares context-library journal changes
behind an explicit approval gate.
Use plugins/saga/scripts/promote_scan.py as the deterministic backbone:
python3 plugins/saga/scripts/promote_scan.py scan --workspace-root ~/workspace/infiquetra --json
python3 plugins/saga/scripts/promote_scan.py key --repo <repo-name> --rule '<rule text>'
infiquetra-context-library from the candidate pool.promote-keys comments so promotion cannot
feed itself.**Transcendent.** markers are strong nominees, and exact
recurrence clusters are deterministic evidence, but final clustering and
distillation remain operator judgment.infiquetra-context-library/docs/engineering-journal/LEARNINGS.md.The single source of truth for markers, key generation, promoted entry shape, ledger comments, and self-feed behavior is:
plugins/saga/skills/promote/references/promotion-contract.md