菜单
Configure AGENTS/CLAUDE and docs/agents for tracker, triage labels, and domain docs. Use before issue, PRD, triage, TDD, or diagnosis skills.
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
Bootstrap AI-ready repo governance, traceability, cascade, catalog audits, validation. Deprecated compatibility aliases: init-ai-repo, ai-sdlc-init. Use when setting up AI SDLC.
Deprecated compatibility alias for ai-catapult-init. Use only when legacy prompts invoke "ai-sdlc-init"; otherwise use "ai-catapult-init".
Ship a northstar handoff's goals in an ai-catapult-init repo — ultragoal one-PR-per-goal, deterministic engine-pick, peer review, CI gate, fail-closed merge, cascade closure.
Scaffold a structurally valid eval triplet for a target skill under .ai/evals/. CI checks structure only; the LM-judge runs out-of-band, never in CI.
Deprecated compatibility alias for ai-catapult-init. Use only when legacy prompts invoke "init-ai-repo"; otherwise use "ai-catapult-init".
Intake intent into a tracked, sliced plan in an ai-catapult-init repo — deep-interview + skippable grill-me, always raise an issue, ralplan, write the A→B handoff.
| name | setup-skills |
| description | Configure AGENTS/CLAUDE and docs/agents for tracker, triage labels, and domain docs. Use before issue, PRD, triage, TDD, or diagnosis skills. |
| disable-model-invocation | true |
Scaffold the per-repo configuration that the engineering skills assume:
CONTEXT.md and ADRs live, and the consumer rules for reading themThis is a prompt-driven skill, not a deterministic script. Explore, auto-detect sensible defaults, present everything in one summary, then write. Only ask the user when a genuine ambiguity requires their judgment.
Look at the current repo to understand its starting state. Read whatever exists; don't assume:
git remote -v and .git/config — is this a GitHub repo? Which one?AGENTS.md and CLAUDE.md at the repo root — does either exist? Is there already an ## Agent skills section in either?CONTEXT.md and CONTEXT-MAP.md at the repo rootdocs/adr/ and any src/*/docs/adr/ directoriesdocs/agents/ — does this skill's prior output already exist?.jira/, Jira issue URLs/config files, or docs mentioning a Jira project key/site — signs that Jira Cloud is already in use.scratch/ — sign that a local-markdown issue tracker convention is already in useSummarise what's present and what's missing in ONE round. Auto-detect sensible defaults:
Section A — Issue tracker. Explicit tracker evidence wins over repository hosting. If .jira/, Jira issue URLs, Jira config, or explicit Jira tracker docs are present, default to Jira Cloud even when the git remote is GitHub, Azure DevOps, or GitLab. Otherwise infer from git remote: GitHub defaults to GitHub Issues, dev.azure.com or visualstudio.com defaults to Azure DevOps Boards, and GitLab defaults to GitLab Issues. If none of these are clear, default to local markdown (.scratch/). Only ask the user if none of these are clearly right.
Section B — Triage labels. Default to the five canonical names: needs-triage, needs-info, ready-for-agent, ready-for-human, wontfix. Only ask if the repo already uses different label strings that need mapping.
Section C — Domain docs. Default to single-context (one CONTEXT.md + docs/adr/ at repo root). Only switch to multi-context if CONTEXT-MAP.md exists.
Present all auto-detected defaults together. If the defaults are clearly correct, proceed without asking. Only ask for confirmation when there's genuine ambiguity.
Auto-detect the correct file to edit (CLAUDE.md or AGENTS.md) and write the configuration. Only present a draft for review if the auto-detected defaults are ambiguous.
Auto-detect the file to edit (CLAUDE.md if it exists, else AGENTS.md), then write the ## Agent skills block and the docs/agents/ files. Use the seed templates in this skill folder as starting points, including issue-tracker-ado.md for Azure Boards and issue-tracker-jira.md for Jira Cloud. Mention which skills will now read from these files.