メニュー
Set up and operate abi through opencode — how opencode discovers abi skills, slash-commands, and MCP servers. Use when the user asks about opencode config, why an abi skill is not loading in opencode, or how to add a skill to the opencode allowlist.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | opencode |
| description | Set up and operate abi through opencode — how opencode discovers abi skills, slash-commands, and MCP servers. Use when the user asks about opencode config, why an abi skill is not loading in opencode, or how to add a skill to the opencode allowlist. |
opencode loads abi via three mechanisms wired in .opencode.json + opencode.json:
.opencode/skills is a symlink to ../.agents/skills, so every
canonical skill dir is visible to opencode automatically. The .opencode.json
skills array is the allowlist of which skills opencode advertises. To expose
a new skill in opencode, add its dir basename to that array — no file copy..opencode.json slash_commands maps /open /diff /commit /context /features /learn /save /load /status /reset to backing skills
(file-context-loader, git-diff-integration, git-commit-integration,
context-state-reporter, feature-flag-display, sea-learning-controller,
session-persister, session-restorer, agent-status-reporter,
context-resetter). Add a command by pointing skill: at a canonical name.opencode.json mcp wires abi-mcp (via
./mcp/launcher.sh stdio) and skill-loop (the telemetry/registry engine).
.mcp.json mirrors the same for other clients..agents/skills/<name>/SKILL.md."<name>" to the .opencode.json skills array.tools/check_skills.sh <name> to confirm frontmatter is valid..opencode/skills is a symlink; editing a skill there edits the canonical copy.skill-loop writes .skill-telemetry/registry.json + amendments.jsonl
automatically (content-drift proposals). Do not hand-edit the registry.sync-clis/launch.sh syncer does NOT create new target dirs in
.claude/skills//.grok/; it only updates SKILL.md for dirs that already
exist there. opencode needs no sync (symlink), but Claude Code/grok do.Synchronize ABI Markdown and docs claims with executable behavior. Use before editing README, AGENTS.md, CLAUDE.md, GEMINI.md, docs/**/*.mdx, walkthroughs, changelogs, or any old ABI Markdown that mentions WDBX, MCP, GPU, clustering, compression, FHE, agents, or benchmarks.
Validate ABI docs and external collateral against repo evidence and docs/contracts/external-claims-audit.mdx. Use when auditing claims, scanning docs for unsupported QPS/sharding/FHE/AES language, checking one claim before publish, or re-confirming the external-claims audit. Agent procedure only — not a CLI or slash command. Pair with abi-doc-claims-sync when editing docs.
Plan and execute ABI repo work from the TODO board, roadmap/spec docs, Zig 0.17 constraints, and validation gates. Use when the user asks to find ABI todos/roadmaps, organize a large implementation from tasks/todo.md, or decide the next safe work slice. Distinct from the goals skill — that skill owns the persistent ledger tasks/goals.md; this skill plans from the active board and north-star specs.
TUI/dashboard superpower. Launch interactive agent REPL, diagnostics dashboard panes, and slash commands via real abi CLI paths. Use when working on abi tui / dashboard / agent tui. There is no /abi-superpower-tui binary.
Build the abi CLI and non-interactively smoke the diagnostics dashboard — render `abi dashboard` one-shot (stdin from /dev/null forces the non-interactive fallback), assert exit 0 and all 5 panels (System, Plugins, WDBX Storage, Scheduler, Memory). Use to smoke-test `abi dashboard`/`abi tui`/`abi --tui` in CI or headless without hanging in the interactive TUI. Complements run-tui (which drives the interactive path via tmux).
Capture, track, and execute goals for the abi Zig project. Use when the user wants to record a goal, see outstanding goals, update goal status, or break a goal into a verified work slice. Distinct from abi-goal-orchestrator (which plans from the TODO board) — this skill owns a persistent goal ledger and drives goal-to-slice execution.