agentsclimarketplace

Bowen research command center

Skill allenlee0430/bowen-ai-skills/skills/bowen-research-command-center

Reusable Codex and Claude Code skills for research operations, grants, evidence synthesis, lab-in-the-loop planning, file curation, and faculty workflows.

Install
npx -y skills add allenlee0430/bowen-ai-skills --skill bowen-research-command-center

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Build an evidence-backed daily or weekly command view of Bowen Li's active research, manuscripts, grants, talks, collaborations, and decisions. Use when asked what to prioritize, what changed recently, what is blocked, what deadlines are approaching, or how to coordinate multiple research workstreams from local files and connected calendars, mail, or Teams.

SKILL.md

2.4 KB, 402 tokens by cl100k_base, as published. Nobody here has run it

Bowen Research Command Center

Workflow

  1. Read references/operating-map.md before scanning.
  2. Establish the time horizon: today, this week, this month, or a named deadline.
  3. Gather only relevant evidence. Start with recent metadata in the mapped research roots; use connected calendars, email, and Teams only when they can clarify status, commitments, blockers, or decisions.
  4. Cross-check mail-derived blockers against Teams chats, recent threads, mentions, or named project channels. If Teams shows a reply, decision, delegation, or resolution, record the item as resolved or delegated via Teams rather than treating email silence as an open blocker.
  5. Convert evidence into a portfolio table with: workstream, desired outcome, stage, next decision, blocker, deadline, owner, and evidence path or connected-source item.
  6. Rank work by deadline risk, scientific leverage, dependency blocking, and evidence freshness. Do not equate file recency with importance without corroboration.
  7. Return:
    • top three outcomes;
    • decision queue;
    • blocked/delegatable items;
    • deadlines and follow-ups;
    • cross-channel closure notes for items resolved outside email;
    • a short stop-doing list.

Rules

  • Separate verified facts, file-derived inferences, and recommendations.
  • Prefer decisions and outcomes over activity counts.
  • Do not read credentials, identity documents, or private finance records.
  • Treat Teams replies, decisions, delegations, and acknowledgments as valid evidence for closing mail-derived research follow-ups. Preserve the Teams source and timestamp when available.
  • Scope Teams reads tightly by horizon, workstream, named collaborators, unread chats, recent threads, or mentions. Report coverage limits when Teams access is broad, incomplete, or unavailable.
  • Do not send messages, change calendars, create Planner tasks, mark Teams items read, or move files unless explicitly asked.
  • Link each important claim to a local path or connected-source item.

Gives 1 of the 12 instructions most research analysis skills give in 402 tokens

Counted across 1,063 of the 1,754 authors here whose files we hold, read 2026-08-06

  • generate a markdown reportin 32 of 1063, across 17 files
  • cite each claim's sourcehere, and in 31 of 1063, across 14 files
  • define the ideal customer profilein 20 of 1063, across 2 files
  • search for companies matching the criteriain 20 of 1063, across 2 files
  • assign a fit score from one to tenin 20 of 1063, across 2 files
  • format results in a scannable markdown templatein 20 of 1063, across 2 files
  • analyze the codebase to understand the productin 19 of 1063, across 1 file
  • ask clarifying questions about the value propositionin 19 of 1063, across 1 file
  • look for signals of immediate needin 19 of 1063, across 1 file
  • identify the target decision maker rolein 19 of 1063, across 1 file
  • suggest a personalized contact strategyin 19 of 1063, across 1 file
  • provide conversation starters for outreachin 19 of 1063, across 1 file

Said here and by no other author read

  • Read the operating map before scanning
  • Establish the time horizon
  • Gather only relevant evidence
  • Cross-check mail blockers against Teams
  • Convert evidence into a portfolio table
  • Rank work by deadline risk and leverage

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.