phd-skillsfcakyon/phd-skills
A Claude Code skill plugin covering the full PhD research workflow, turning high-frequency research actions such as trai…
No ratings yet
Rate this skill
Stars416
Forks36
Watchers416
Open Issues1
InstallOne-line install
UnconfirmedWhether 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/fcakyon/phd-skills.git
OverviewOverview
Key Features
A Claude Code skill plugin covering the full PhD research workflow, turning high-frequency research actions such as training debugging, experiment launching, paper reproduction and review into auto-triggered skills. Key capabilities include: 1. Automatic training-divergence debugging: when the user asks questions like "why is my loss diverging?", the debug skill auto-triggers and traces the cause of diverging loss step by step through an evidence chain, avoiding blind hyperparameter tuning; 2. Training-run launch guidance: when the user says "launch the new training run", the launch skill triggers and completes the startup configuration of a new training job following a fixed procedure, reducing missing parameters; 3. Paper reproduction and review: built-in paper-reproduction and paper-review skills help reproduce experiments following a paper's method and produce structured reviews of manuscripts; 4. Research context mounting: hooks and MCP mechanisms mount research skills and tools into the session so the agent follows academic conventions instead of improvising.
Use Cases
diagnosing abnormal training loss, starting new training experiments, reproducing academic papers, drafting paper review comments, preparing materials before conference submission, logging research experiments.
Target Roles
AI / Algorithm Engineer, Data Analyst / Data Engineer, Product Manager (PM).
TopicsTopics
RatingUser ratings
Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.
RepositoryRepository
| Skill ID | 2010 |
|---|---|
| Data source | GitHub |
| Repository | fcakyon/phd-skills |
| Category | AI & Agent Skills / Research & Academic Workflow |
| Primary language | Shell |
| License | MIT License |
| Default branch | main |
| GitHub repository ID | 1178594867 |
| Node ID | R_kgDORj_uMw |
| Rank | #1494 (position within the source ranking) |
| Site-wide popularity rank | #1684 (computed live from Stars, across all 5833 entries) |
GrowthStar / Fork growth
One snapshot per day, tracking how Stars and Forks changed
- Now416
- Previous point · 09-29 412
- vs previous point +4
- 2 data points 12 days
- Now36
- Previous point · 09-29 36
- vs previous point ±0
- 2 data points 12 days
TimelineTimeline
Repository created2026-03-11 07:08:308 months ago
Data last updated2026-10-26 12:15:1223 days ago
Last commit2026-09-16 10:00:432 months ago
CommitLatest commit
Version [v1.3.0] committed by fcakyon. Update Category: Documentation & Guidelines Update. Commit details: docs: update citation summary (#14). This update improves usage instructions, deployment guides, and developer docs.