engineering-paper-router
Skill3 starsChanged 41 days agoMITView on GitHub
Route ambiguous or mixed English engineering paper tasks to the correct engineering paper skill. Use when the user names several paper tasks at once or a mixed request such as revise this draft and prepare submission, respond to comments, or combine drafting, polishing, figure/table work, response drafting, and validation. Beginners and open-ended "where do I start" requests go to engineering-paper-coach guide mode.
In this repository7 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill only to choose the right workflow and required inputs.
- Very specific: line 17
If readiness or completion is requested, include engineering-validation.
- Distinctive: line 19
Stop routing at the first missing input that would make the next step invent facts, citations, line numbers, experiment results, or …
- Distinctive: line 24
Use this skill when the correct engineering paper skill is unclear.
- Distinctive: line 25
Do not use it when the user explicitly names one of the five task skills and the request matches that skill.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Engineering Paper Router
Use this skill only to choose the right workflow and required inputs. Do not write final manuscript prose unless the user explicitly asks to continue after routing.
Core Stance
- Route first; do not draft first.
- Preserve evidence boundaries in the recommended next prompt.
- For mixed tasks, name a primary skill, secondary skills, and workflow order.
- If readiness or completion is requested, include
engineering-validation. - Explain why plausible but non-primary skills should not run first.
- Stop routing at the first missing input that would make the next step invent facts, citations, line numbers, experiment results, or readiness status.
Boundaries
- Use this skill when the correct engineering paper skill is unclear.
- Do not use it when the user explicitly names one of the five task skills and the request matches that skill.
When to Open Extra Files
| File | Open when |
| references/examples.md | Needing routing examples |
| references/failure-modes.md | Avoiding router overreach or single-skill bias |
| ../_shared/evidence-boundary.md | Routing tasks that request strong claims, citations, validation, or missing-evidence work |
| ../_shared/story-spine.md | Full-paper, abstract, introduction, or major revision tasks need story-first ordering |
| ../_shared/ai-assisted-writing-policy.md | User requests AI-polished or venue-ready prose where author responsibility or disclosure may matter |
| ../_shared/output-mode.md | User asks for a short route only |
Routing Table
| User task | Route |
| draft/rebuild title, abstract, Introduction, Methods, Experiments, Discussion, or Conclusion | engineering-writing |
| polish existing prose, improve flow, downgrade claims, translate source notes into English prose | engineering-polishing |
| plan or revise figures, tables, captions, visual roles, page budget, or visual consistency | engineering-figure-table |
| classify reviewer/advisor/editor comments, build revision tracker, draft response letter | engineering-response |
| compile/check manuscript, inspect citations, claim-evidence anchors, figures/tables, readiness | engineering-validation |
| what will reviewers say, is the evidence convincing, pre-submission critique | engineering-paper-auditor (reviewer simulation) |
| review an experiment plan, proposal, or results-table skeleton before experiments finish | engineering-paper-auditor (experiment plan pre-mortem) |
| beginner, "where do I start", a project folder with no specific task | engineering-paper-coach (guide mode) |
Input-State Routing
| Input state | Primary route | Secondary route | Stop condition |
| Thin idea, no method/evidence/boundary | engineering-paper-coach guide mode (stage S0) | engineering-writing scaffold only if the user asks for prose | Do not draft final Abstract/Conclusion |
| Notes plus result tables, no figure responsibilities | engineering-writing | engineering-figure-table | Do not write strong claims before evidence map |
| Existing paragraph with stable claim/evidence | engineering-polishing | engineering-writing only if structure fails | Stop if claim, evidence, and boundary are unclear |
| Caption, table, category names, or visual claims | engineering-figure-table | engineering-polishing for caption wording only | Stop if visual evidence cannot support the requested claim |
| Reviewer/advisor/editor comments | engineering-response | writing/figure-table/validation as needed | Stop before final response if edits are not verified |
| Ready/complete/submittable request | engineering-validation | writing/figure-table/response for blocking fixes | Stop if build, references, or source files are missing |
Mixed Workflow Order
For full-paper work, use this order unless the user gives a narrower task:
engineering-paper-auditor: story-spine and blocker audit if a draft is already written. Without a draft, skip this step; open-ended requests from beginners go toengineering-paper-coachguide mode.engineering-writing: one-sentence thesis, story spine, and contribution-evidence map.engineering-figure-table: visual responsibility and evidence roles.engineering-writing: Methods and Experiments before Introduction.engineering-writing: Introduction, Abstract, Conclusion.engineering-polishing: paragraph flow, terminology, and claim strength.engineering-response: only if comments exist.engineering-validation: before claiming complete, fixed, or ready.
Default Output
Recommended route
- Primary skill:
- Secondary skill:
- Reason:
Task decomposition
- User request contains:
- Primary operation:
- Secondary operations:
Do not use first
| Skill | Why not primary |
Workflow order
| Step | Skill | Required input | Stop condition |
Required inputs
- ...
Evidence boundary
- Do not invent:
- Must verify before claiming ready:
Next prompt to use
[copyable prompt]Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.