跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
数据与分析

why

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.

Lauren Tan (poteto) · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add MindGoblinStudios/grim-tome --skill why

技能说明


name: why description: "Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior." disable-model-invocation: true mutation: true license: MIT source_url: https://github.com/cursor/plugins/blob/main/pstack/skills/why/SKILL.md source_ref: 11713c683fe4add4fd403ea880580abbc9e0875f original_skill: original/UPSTREAM.md metadata: author: Lauren Tan (poteto) pack: pstack lifecycle: beta

Original skill: why from pstack by poteto (MIT) — nested copy at original/UPSTREAM.md.

Beta: manual-only; invoke it by name. Mutation: harness-neutral subagent, model routing, and MCP discovery (no pstack-models.mdc rule, pinned model slugs, or Cursor-only paths), plus a no-subagent fallback.

Why

Investigate the motivation and intent behind code. The companion how skill answers what the code does and how it works. why answers what forces led to its shape.

If your harness lets you pick models per subagent, use a fast model for investigators and your strongest reasoning model for the synthesizer; otherwise inherit the parent's model.

Spawn subagents that keep tool and MCP access. Do not use a read-only mode that strips MCP access (for example Cursor's Ask mode): it disables the MCP-backed investigators and the synthesizer's citation spot-checks. Investigators still shouldn't write anything. If the harness can't spawn subagents, run each investigator's search yourself, one category at a time, then synthesize with the same templates.

Operating Posture

Operate as a careful, cautious, and precise investigator. Be honest about what you know vs what you're inferring. Read references/epistemics.md for the full confidence framework and phrasing guide. The synthesizer must follow it.

Step 1. Understand the Target and the Question

The target is usually a chunk of code, a pattern, a feature, or a named design decision. The question is usually a design rationale, a tradeoff, a motivating edge case, an external constraint, dead code, or a broad history sweep.

If the target is vague ("why do we do it this way?" with no clear referent), make your best guess from conversation context (open files, recent edits, cursor location, what was just discussed). State your interpretation briefly so the user can redirect if you're off, then proceed.

Step 2. Establish the Code Anchor

Before spawning investigators, build the seed context inline: file paths and line ranges, key symbols (functions, classes, constants), the last few commits touching the target, PR numbers from merge commits (pattern (#1234) in the subject line), and any linked ticket IDs. Run git blame -L <start>,<end> <file> for last-touch commits, git log --follow -p -- <file> for full history with patches through renames, git log --oneline -20 -- <file> for recent commits with PR numbers visible, and git log -1 --format=%B <commit> to extract PR numbers. Then pull the PR bodies and discussion for any substantive commit: gh pr view <number> --json title,body,author,createdAt,mergedAt,labels,closingIssuesReferences,comments,reviews. This anchor goes to every investigator and to the synthesizer.

Step 3. Spawn Parallel Investigators

Default to the full parallel investigation. The goal is a complete coverage map, not a minimal one. Document the null, don't skip the search.

Discovery

Before spawning investigators, list the MCP servers and connectors available in this harness: its tool list or MCP catalog when present (in Cursor, the mcps/ directory it exposes).

Map each available MCP to one evidence category:

  1. Source control history
  2. Issue / ticket tracker
  3. Long-form documents
  4. Real-time team chat
  5. Infrastructure observability
  6. Error / exception tracking
  7. Product analytics warehouse

Source control is always available through git and gh. For the other six, classify using the MCP name, server instructions, tool names, and resource descriptors. If an MCP could fit more than one category, choose the one matching its primary evidence. Record ambiguous cases in the coverage map.

Spawn one investigator per category that has a matching MCP, all in a single message so they run concurrently, each owning exactly one tool or MCP. Don't ask one agent to cover multiple MCPs.

Each investigator's prompt is references/investigator-prompt.md filled in, plus:

  • the category playbook references/sources/<source>.md for the selected MCP, adapted from the examples in references/source-playbook.md
  • references/sources/incident-postmortem.md if the target code looks defensive (null checks, retry logic, timeout handling, rate limiting, feature flags, egress guards, OOM handlers)
  • the code anchor and the user's original question

Investigator roster, one per available evidence category

Each category below is uniquely positioned to surface one shape of "why", shown after "Best at". Use it to know what to expect back, to name a gap when a category returns empty, and, only in the rare provably-irrelevant case, to justify a skip.

  1. Source control (git history, gh for PRs, code comments, tests). Always spawn, the only guaranteed source. Best at implementation-time rationale captured during review.
  2. Issue / ticket tracker (e.g. Linear, Jira, GitHub Issues, Plane, Shortcut MCP). Best at the product or business forcing function. Strongest when the why is external to engineering.
  3. Long-form documents (e.g. Notion, Confluence, Google Docs, Coda MCP). Best at long-form design rationale, written out before it bec
阅读完整来源 ↗