skills/limitations-scope-writer/SKILL.md
Draft ML/AI limitations, scope, failure cases, ethics, and conclusion caveats. Use to control claim boundaries and reduce overclaiming.
npx skillsauth add a-green-hand-jack/ml-research-skills limitations-scope-writerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Write limitations and scope as claim-boundary control. This skill helps the paper acknowledge real constraints, explain their impact, and preserve the valid contribution.
Use this skill for:
Do not use this skill for hostile review. Use paper-reviewer-simulator for reviewer critique. Use experiment-story-writer for mixed-result results prose. Use paper-writing-memory-manager to propagate scope changes to title, abstract, intro, results, captions, and conclusion. Use paper-draft-consistency-editor for full-draft consistency.
<installed-skill-dir>/
├── SKILL.md
├── references/
│ ├── limitation-patterns.md
│ └── ethics-and-scope.md
└── templates/
└── limitations-scope-plan.md
references/limitation-patterns.md.references/ethics-and-scope.md when writing ethics, broader impact, deployment caveats, data/model risks, or human-subject/domain caveats.templates/limitations-scope-plan.md when creating paper/.agent/limitations-scope-plan.md.paper/.agent/writing-contract.md, paper/.agent/writing-memory/, paper/.agent/paper-evidence-board.md, paper/.agent/experiment-story-plan.md, paper/.agent/provisional-results.md, review-risk notes, and current draft sections when present.Extract:
## Limitations Scope Snapshot
- Target venue:
- Paper archetype:
- Main claims:
- Supported scope:
- Known limitations:
- Failure cases:
- Mixed or negative results:
- Dataset/benchmark constraints:
- Compute/system constraints:
- Human/domain/deployment risks:
- Ethics or broader-impact requirements:
- Claims needing downgrade:
If a limitation undermines the primary claim, route to result-diagnosis, paper-positioning-planner, or paper-evidence-board before writing final text.
Read references/limitation-patterns.md and classify each limitation:
For each limitation, decide whether it requires:
Create or update:
paper/.agent/limitations-scope-plan.md
If there is no paper/ directory and the current directory is the paper repo, save to:
.agent/limitations-scope-plan.md
Use templates/limitations-scope-plan.md.
For each limitation, record:
For each limitation paragraph:
Avoid vague phrases such as "more work is needed" unless the needed work is specified.
Limitations often require edits outside the limitations section. Check:
If a scope correction affects top-level prose, route to abstract-title-contribution-writer or paper-draft-consistency-editor.
Before finalizing:
paper-writing-memory-manager — record the limitation list, any claims that were narrowed or scoped, and which sections (abstract, intro, conclusion, contributions) must be checked for scope consistencytesting
Bootstrap project-local ml-research-skills. Use from global installs when creating a new ML research project, enabling this collection in an existing ML research repo, or deciding whether to install the full bundle locally. Route to project-init for new projects; do not handle paper or experiment work directly.
development
Route project operations tasks — git, memory, bootstrap, remote, workspace, code review, timeline, ops — to the correct skill. Use when the task involves commits, pushes, worktrees, project memory, enabling project-local skills, SSH/server coordination, sidecar runners, or audits. Do not solve the ops task directly.
testing
Route ML/AI paper writing tasks to the correct skill — contract planning, prose drafting, section writing, consistency editing, review simulation, rebuttal, submission, or citation work. Use when the task involves writing, revising, reviewing, or submitting a paper instead of guessing between paper-writing-assistant, paper-writing-contract-planner, paper-reviewer-simulator, auto-paper-improvement-loop, or citation skills. Do not draft prose directly.
data-ai
Project-local router for ML research skill selection. Use inside an initialized ML research project, or while maintaining this skill repo, when the user describes an ML research/paper/experiment/discovery/ops/release workflow and may not know the skill; route to a domain router or high-signal leaf. Do not use for generic non-ML projects.