菜单
Investigate a spike task from an Epic's backlog using the Epic's dedicated repo clone, and save a findings report the team can decide from. Use when the user mentions a spike, スパイク調査, or wants a technical question from the backlog researched against the actual codebase.
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
| name | investigate-spike |
| description | Investigate a spike task from an Epic's backlog using the Epic's dedicated repo clone, and save a findings report the team can decide from. Use when the user mentions a spike, スパイク調査, or wants a technical question from the backlog researched against the actual codebase. |
A spike is a time-boxed research task whose deliverable is knowledge, not code. This skill runs the research against the Epic's dedicated clone and leaves a report next to the Epic's other machine-managed data.
Identify the spike item. If the user named one, use it. Otherwise list
the Epic's items (node "${CLAUDE_PLUGIN_ROOT}/scripts/monday/list-items.mjs")
and look for spike markers — a name starting with Spike / [Spike] /
スパイク, or a type/status column that marks spikes on this board. If
nothing matches, show the candidates and ask; do not guess. When the board
uses a different convention, note it for setup-scrum-context so it can
be recorded.
Load the question. get-item.mjs <itemId> plus the item's saved
updates (.pm/backlog/updates/<itemId>.json) and, if scaffolded,
pbi/<itemId>-*/acceptance.md — the spike's question and its
"done when we know X" criterion. If the question is ambiguous, confirm it
with the user before spending investigation effort.
Prepare the code. Run
node "${CLAUDE_PLUGIN_ROOT}/scripts/repo/sync-repo.mjs" "<groupName>" so
the dedicated clone (.pm/repo/repo-state.json → mirrorPath) is current
on the epic branch. The clone is the spike's dedicated workspace — never
investigate in the user's own development checkout. Read-only: no edits,
no branch switching beyond what sync-repo.mjs did.
Investigate. Answer the spike question with evidence: trace the
relevant code paths in the mirror (file:line citations), consult library
docs where the question involves external dependencies, and run read-only
commands in the mirror if needed. Delegate broad sweeps to a read-only
exploration agent (code-explore) and fold back conclusions. Time-box:
when findings are sufficient to decide, stop — a spike ends at "enough to
decide", not at exhaustive coverage.
Write the report to .pm/reports/spikes/<itemId>-<slug>.html — a
self-contained HTML document (inline CSS, no external assets, same
conventions as the progress report): the question, what was examined,
findings with file:line evidence, options with trade-offs, and a
recommendation. Slug: short kebab-case from the item title.
Close the loop. Report the recommendation + report path in chat. Offer
(user approval required — monday writes are workspace-visible) to post the
conclusion and report location as an update on the monday item via the
monday-api-mcp server, and/or to set the item's status via
update-item-status.mjs.
repo configured for the Epic → the spike may still be researchable
from docs alone; say the code view is unavailable and ask whether to
proceed docs-only or configure the repo first.MONDAY_TOKEN missing → scripts exit 1; point to the plugin README.sync-repo.mjs --repo-url/--epic-folder overrides
rather than silently investigating the wrong codebase.Cross-check an Epic's user stories, PBIs, and acceptance criteria against the actual implementation in its repo, and propose fixes for mismatches, missing/unfinished descriptions, and unclear wording. Use when the user wants a consistency check between backlog and code, 整合性チェック, or asks whether the backlog still reflects what is really implemented.
Load a PBL Epic's working context — backlog snapshot, repo sync data, and the Epic summary — refreshing stale data first, so the conversation can start from the Epic's current state. Use when the user wants to load/open an Epic, asks "where are we on <Epic>", Epicをロード, or starts a session about a specific Epic's status.
Generate an HTML report of an Epic's currently-implemented spec and its upcoming planned features, reconciled from the backlog snapshot and the repo's actual state. Use when the user wants a "what exists now vs what's coming" summary, 仕様まとめ, or a feature-status overview for stakeholders.
Read or update the product backlog on monday.com. Use when the user asks about backlog items, monday.com boards, tickets, or tasks tracked in monday.com.
Generate a sprint-review HTML document for a PBL Epic — done items with demo pointers, sprint metrics, and an agenda — from the monday.com board and its Drive snapshot. Use when the user wants sprint review material, a demo agenda, or to prepare for a sprint review / スプリントレビュー.
Generate a PBL Epic's progress & completion-forecast HTML report from its Drive snapshot. Use when the user wants a progress/status report, or a burndown/completion forecast for a PBL Epic.