feat(atlassian): implement milestone M1 - scaffold skill and shared runtime

skills/atlassian/codex/SKILL.md

@@ -0,0 +1,75 @@
+---
+name: atlassian
+description: Interact with Atlassian Cloud Jira and Confluence through a portable task-oriented CLI for search, issue/page edits, comments, transitions, and bounded raw requests.
+---
+
+# Atlassian (Codex)
+
+Portable Atlassian workflows for Codex using a shared TypeScript CLI.
+
+## Requirements
+
+- Node.js 20+
+- `pnpm`
+- Atlassian Cloud account access
+- `ATLASSIAN_BASE_URL`
+- `ATLASSIAN_EMAIL`
+- `ATLASSIAN_API_TOKEN`
+
+## First-Time Setup
+
+```bash
+mkdir -p ~/.codex/skills/atlassian
+cp -R skills/atlassian/codex/* ~/.codex/skills/atlassian/
+cd ~/.codex/skills/atlassian/scripts
+pnpm install
+```
+
+## Prerequisite Check (MANDATORY)
+
+Run before using the skill:
+
+```bash
+cd ~/.codex/skills/atlassian/scripts
+node -e "require.resolve('commander');require.resolve('dotenv');console.log('OK: runtime dependencies installed')"
+test -n \"$ATLASSIAN_BASE_URL\"
+test -n \"$ATLASSIAN_EMAIL\"
+test -n \"$ATLASSIAN_API_TOKEN\"
+pnpm atlassian health
+```
+
+If any check fails, stop and return:
+
+`Missing dependency/config: atlassian requires installed CLI dependencies and valid Atlassian Cloud credentials. Run setup and configure ATLASSIAN_* env vars, then retry.`
+
+## Supported Commands
+
+- `pnpm atlassian health`
+- `pnpm atlassian jira-search --jql "..."`
+- `pnpm atlassian jira-get --issue ABC-123`
+- `pnpm atlassian jira-create ... [--dry-run]`
+- `pnpm atlassian jira-update ... [--dry-run]`
+- `pnpm atlassian jira-comment ... [--dry-run]`
+- `pnpm atlassian jira-transitions --issue ABC-123`
+- `pnpm atlassian jira-transition ... [--dry-run]`
+- `pnpm atlassian conf-search --query "..."`
+- `pnpm atlassian conf-get --page 12345`
+- `pnpm atlassian conf-create ... [--dry-run]`
+- `pnpm atlassian conf-update ... [--dry-run]`
+- `pnpm atlassian conf-comment ... [--dry-run]`
+- `pnpm atlassian conf-children --page 12345`
+- `pnpm atlassian raw --product jira|confluence --method GET|POST|PUT --path ...`
+
+## Safety Rules
+
+- Default output is JSON; prefer that for agent workflows.
+- Use `--dry-run` before any mutating command unless the user clearly wants the write to happen immediately.
+- Jira long-text fields are converted to ADF locally.
+- Confluence page bodies are storage-first in v1.
+- `--body-file` must point to workspace-scoped files only; do not use arbitrary system paths.
+- `raw` is for explicit edge cases only and does not allow `DELETE`.
+
+## Notes
+
+- Atlassian Cloud is the only first-class target in v1.
+- This skill exists so Codex, Claude Code, Cursor Agent, and OpenCode can share the same command surface even when MCP access differs.