一键在 Manus 中运行任何 Skill

task-tracker

星标1

分支1

更新时间2026年7月13日 14:17

ACE's project/task state — one board task per iterative thread/project, backed by canopy-web (kanban at /agents/ace). The canonical procedure is fleet-wide and lives in the installed canopy plugin (agent-core/task-tracker.md); this stub binds it to ACE. Use when taking on multi-turn work, when a new request arrives, and at every turn's board-drain and close.

安装

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。

在 Manus 中运行

来源

dimagi-internal

dimagi-internal/ace

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

Task Tracker — ACE (stub over the fleet-canonical core)

Resolve the installed canopy plugin and check freshness:

CANOPY=$(python3 -c "import json,os; d=json.load(open(os.path.expanduser('~/.claude/plugins/installed_plugins.json'))); print(d['plugins']['canopy@canopy'][0]['installPath'])")
bash "$CANOPY/scripts/canopy-update-check.sh"

UPGRADE_AVAILABLE → tell the human and run /canopy:update BEFORE following a stale core.

Read $CANOPY/agent-core/task-tracker.md and follow it exactly, bound to the Identity below. Where it says <slug>/<mailbox>, use this Identity.

Identity

Name: ACE · slug: ace · mailbox: ace@dimagi-ai.com
Board: /agents/ace · Drive folder id env: ace_DRIVE_FOLDER_ID

ACE-local notes (the ONLY hand-edited section — fleet-process changes go to canopy)

Board/task integration is config-gated and best-effort — it NEVER blocks a turn (per config/agent.json _doc: workspace integration is best-effort; the ace-web vs canopy-web question is deliberately open). If canopy agent --help fails or no workbench token exists, note "board: not configured" in the close-out and move on.
Per-opportunity pipeline state stays in Drive (ACE/<opp>/runs/<run-id>/run_state.yaml + comms-logs) — the board tracks counterpart-facing iterative threads/projects, not run state.

同仓库更多 Skills

同仓库

narrative-iteration-review

dimagi-internal/ace

Produce a domain-expert-facing before/after (pre-post) Google Doc for a DDD narrative iteration, and read the expert's edits back. Pull the verbatim CURRENT narration from canopy-web, apply reviewer feedback into a PROPOSED next version, publish a scannable side-by-side doc a non-engineer can review, then read their suggestion-mode edits via the structured Doc. Use when iterating a Connect DDD narrative on expert feedback (e.g. RF Surveys / Sophie), when asked to "make a before/after of the narration", "iterate the narrative on <expert>'s feedback", or "let <expert> sign off on the language".

2026-07-201

app-hq-settings

dimagi-internal/ace

Apply the two HQ-layer standing-instruction settings Nova can't set at build time — camera-only photo capture (appearance="acquire" on Deliver image uploads) and grid menu display on every module — to the deployed draft apps, then resolve the matching Phase-3 residuals. Runs between app-deploy and app-release.

2026-07-171

pdd-to-learn-app

dimagi-internal/ace

Build the CommCare Learn (training) app from the PDD via Nova's /nova:autobuild. Captures nova_app_id and writes a structure summary.

2026-07-151

training-deck-render

dimagi-internal/ace

Render a training deck spec.yaml into a Google Slides deck via the 14-stencil ACE template. Produces a presentable Slides URL.

2026-07-131

app-release-qa

dimagi-internal/ace

Phase 3 § Step 2.8 — structural + install-time QA on the released Learn + Deliver CCZs. Downloads each CCZ via commcare_download_ccz, parses the zip + suite.xml + form XMLs, verifies form counts + Connect-marker presence match the Nova blueprint, then runs commcare-cli `validate` + `play` as install-time runtime gates. AVD-free, Connect-free — purely CCHQ-side. Halts loud on mismatch.

2026-07-131

app-screenshot-capture

dimagi-internal/ace

Run app smoke recipes against a local AVD and capture per-step screenshots for the training deck. Per-opp content only.

2026-07-131

name	task-tracker
description	ACE's project/task state — one board task per iterative thread/project, backed by canopy-web (kanban at /agents/ace). The canonical procedure is fleet-wide and lives in the installed canopy plugin (agent-core/task-tracker.md); this stub binds it to ACE. Use when taking on multi-turn work, when a new request arrives, and at every turn's board-drain and close.

Task Tracker — ACE (stub over the fleet-canonical core)

Resolve the installed canopy plugin and check freshness:

CANOPY=$(python3 -c "import json,os; d=json.load(open(os.path.expanduser('~/.claude/plugins/installed_plugins.json'))); print(d['plugins']['canopy@canopy'][0]['installPath'])")
bash "$CANOPY/scripts/canopy-update-check.sh"

UPGRADE_AVAILABLE → tell the human and run /canopy:update BEFORE following a stale core.

Read $CANOPY/agent-core/task-tracker.md and follow it exactly, bound to the Identity below. Where it says <slug>/<mailbox>, use this Identity.

Identity

Name: ACE · slug: ace · mailbox: ace@dimagi-ai.com
Board: /agents/ace · Drive folder id env: ace_DRIVE_FOLDER_ID

ACE-local notes (the ONLY hand-edited section — fleet-process changes go to canopy)

Board/task integration is config-gated and best-effort — it NEVER blocks a turn (per config/agent.json _doc: workspace integration is best-effort; the ace-web vs canopy-web question is deliberately open). If canopy agent --help fails or no workbench token exists, note "board: not configured" in the close-out and move on.
Per-opportunity pipeline state stays in Drive (ACE/<opp>/runs/<run-id>/run_state.yaml + comms-logs) — the board tracks counterpart-facing iterative threads/projects, not run state.