SkillPedia Skills Encyclopedia
中文 EN

research-skillsluwill/research-skills

Provides AI agents with a constrained and traceable workflow for research writing and presentation generation,…

No ratings yet Rate this skill
Stars860
Forks99
Watchers860
Open Issues1

InstallOne-line install

Unconfirmed

Whether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:

git clone https://github.com/luwill/research-skills.git

OverviewOverview

Key Features

Provides AI agents with a constrained and traceable workflow for research writing and presentation generation, preventing agents from drifting off-topic, fabricating claims, or skipping human review. Key capabilities include: 1. Four-route contract: forces each task into one of four routes (narrative / method-survey / scoping, etc.) so the agent follows the matching route and avoids mixing task types; 2. Immutable project contract: locks research goals, scope, and constraints at project initialization, and all subsequent steps must comply, preventing mid-task drift from the original setting; 3. claim_ledger discipline: registers source and evidence for every claim and checks them one by one during writing, reducing unsupported assertions and citation mismatches; 4. Human gates stay human: forces a pause at key checkpoints for human confirmation, blocking the agent from auto-approving steps that require human judgment; 5. Caption-based figure detection and figure-to-slide mapping: locates figures from paper captions and maps them to slide pages to auto-generate presentation structure; 6. 17 visual styles with Gemini API integration: calls the Gemini API to render slides in 17 preset visual styles and exports PPTX/PDF; 7. Structured 5-phase workflow: splits the whole task into five sequential phases, each with clear outputs for easy inspection and rollback.

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID1107
Data sourceGitHub
Repositoryluwill/research-skills
CategoryAI & Agent Skills / Research & Academic Workflow
Primary languagePython
LicenseNot specified
Default branchmain
GitHub repository ID1133189020
Node IDR_kgDOQ4sXnA
Rank#855 (position within the source ranking)
Site-wide popularity rank#978 (computed live from Stars, across all 5845 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

02505007501k2026-09-292026-10-112026-09-29 · 8532026-10-11 · 860
  • Now860
  • Previous point · 09-29 853
  • vs previous point +7
  • 2 data points 12 days
02550751002026-09-292026-10-112026-09-29 · 992026-10-11 · 99
  • Now99
  • Previous point · 09-29 99
  • vs previous point ±0
  • 2 data points 12 days

TimelineTimeline

Repository created2026-01-13 02:17:0110 months ago
Data last updated2026-10-26 12:05:0424 days ago
Last commit2026-10-10 12:15:361 months ago

CommitLatest commit

Committed by luwill. Update Category: Documentation Updates. Commit details: docs(medical-imaging-review): learning——案例运行是评审的必要补充. This update refines the documentation for easier onboarding.

3b2e391 luwill 2026-10-10