research-repo-architect
Skill9 starsChanged 3 months agoMITView on GitHub
Organize research code and skill repositories into lightweight reproducible architecture. Use when Codex needs to scaffold or migrate a research repo for different startup stages, separate reusable code from scripts, standardize data/config/results/run directories, add Python src-layout packaging, create AutoDL/HPC-ready entrypoints with smoke/formal gates, keep local work light, or integrate skills/tools/shared-references with mainline and Codex mirrors.
- Installs packages
In this repository47 other files it gives its agents.
- autodl-hpcSkill
- experiment-bridgeSkill
- experiment-planSkill
- human-toneSkill
- idea-discoverySkill
- paper-visualizationSkill
- paper-writingSkill
- rebuttalSkill
- research-blueprintSkill
- research-pipelineSkill
- research-reviewSkill
- resubmit-pipelineSkill
- autodl-hpcSkill
- auto-paper-improvement-loopSkill
- auto-review-loopSkill
- novelty-checkSkill
- paper-figureSkill
- paper-planSkill
- paper-writeSkill
- research-refineSkill
- research-reviewSkill
- experiment-bridgeSkill
- experiment-planSkill
- auto-paper-improvement-loopSkill
- auto-review-loopSkill
- grant-proposalSkill
- idea-creatorSkill
- idea-discoverySkill
- novelty-checkSkill
- paper-figureSkill
- paper-planSkill
- paper-posterSkill
- paper-slidesSkill
- paper-writeSkill
- paper-writingSkill
- research-refineSkill
- research-reviewSkill
- human-toneSkill
- idea-discoverySkill
- paper-visualizationSkill
- paper-writingSkill
- rebuttalSkill
- research-blueprintSkill
- research-pipelineSkill
- research-repo-architectSkill
- research-reviewSkill
- resubmit-pipelineSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
60 rules. About 0 are common, 13 are distinctive, and 47 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈13
Distinctive · estimate
This author's own choices. Worth a look.
47
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 31
Add AutoDL/HPC hooks when experiments may need GPU time, but keep execution gated and manual by default: runbook, preflight, smoke suite, …
- Very specific: line 34
Read ../shared-references/project-guide-protocol.md when creating project memory.
- Very specific: line 47
Read ../shared-references/autosci-lite-patterns.md when scaffolding idea discovery, failure memory, pilot gates, or the macro state machine.
- Very specific: line 51
When the repo will eventually produce a paper package, prefer an ICDE_YU_Memory-style manuscript layout or better: thin main.tex, modular …
- Distinctive: line 58
Start by deciding which path applies:
- Distinctive: line 60
New repo scaffold: Create the architecture first, then add code and experiments into the right layer.
- Very specific: line 64
research blueprint handoff: When a stable method is about to become a formal experiment protocol or paper plan, preserve …
- Very specific: line 68
AutoDL/HPC-ready research project: Add target-machine setup, preflight, smoke, result-transfer, and formal-run approval boundaries without …
- Distinctive: line 69
Lightweight project start: When materials are sparse, create only the minimal brief, plan, architecture, and next-action files needed for …
- Very specific: line 73
AutoSci-lite lifecycle: Use A-E idea paths, append-only failure memory, pilot gates, and the explicit PROJECT_STATUS.md phase map without …
- Very specific: line 86
Keep reusable implementation under src/<package_name>/.
- Very specific: line 87
Put runnable entrypoints under scripts/:
- Very specific: line 92
Put hand-written configs under experiments/configs/ and suite definitions under experiments/suites/.
- Very specific: line 93
Add a short root README.md for installation, smoke checks, data, and reproduction commands.
- Very specific: line 94
Create docs/project/, docs/experiments/, docs/evidence/, docs/paper/, docs/theory/, and docs/runbooks/ as needed.
- Very specific: line 97
Add a conservative .gitignore so raw data, generated runs, caches, model checkpoints, and large binary artifacts are not tracked.
- Very specific: line 98
If the repo uses project-local skills, keep skill runtime state out of Git by default: .debuffer_skills/traces/, .debuffer_skills/cache/, …
- Very specific: line 99
Keep compact project memory tracked when it exists: idea-stage/IDEA_MEMORY.md and experiments/NEGATIVE_RESULTS.md are decision memory, not …
- Distinctive: line 108
If the reference is a strong manuscript package template, also record what is worth copying at the package-architecture level: section …
- Distinctive: line 127
When idea exploration or experiment planning begins, initialize compact memory only as needed:
- Very specific: line 133
Do not create a full research-wiki/ or graph unless the user asks for a long-lived knowledge base.
- Very specific: line 140
Use rg --files to inventory code, notebooks, scripts, configs, data, and outputs.
- Distinctive: line 141
Read package/build files and the main run scripts.
- Very specific: line 150
Update imports, CLI commands, README instructions, tests, and .gitignore after each phase.
- Very specific: line 151
Never overwrite existing data/raw/, experiments/results/, or user-created run outputs unless the user explicitly asked for that exact …
- Very specific: line 155
Use this path when the repository is a debuffer-style skill pack: it has skills/<name>/SKILL.md, skills/skills-codex/, …
- Very specific: line 157
Read references/skill-pack-architecture.md before editing.
- Very specific: line 158
Treat skills/<name>/SKILL.md as the mainline source of behavior.
- Very specific: line 159
Put reusable cross-skill contracts under skills/shared-references/.
- Distinctive: line 161
When adding or renaming a skill in a skill repo, update all required surfaces in the same pass:
- Distinctive: line 167
Run the repository's inventory and targeted tests after integration.
- Very specific: line 174
Keep skill packages under skills/.
- Distinctive: line 178
Use this path when a normal research project is being operated by skill workflows.
- Very specific: line 180
Keep reusable implementation in src/<package_name>/ and experiment runners in scripts/ as usual.
- Very specific: line 181
Keep skill handoff directories where downstream skills expect them unless the user asks for a breaking migration: idea-stage/, …
- Very specific: line 187
Place Markdown handoff artifacts under docs/ when creating or refreshing them: docs/project/RESEARCH_BRIEF.md, …
- Very specific: line 193
Treat .debuffer_skills/ as runtime state.
- Very specific: line 194
If research-wiki/ exists, preserve it as persistent project memory.
- Distinctive: line 199
Use this path when the repo will run on AutoDL or another SSH GPU/HPC machine.
- Very specific: line 201
Read references/autodl-hpc.md before adding or changing remote-run scripts.
- Very specific: line 202
Keep target-machine setup in scripts/autodl_setup.sh and machine checks/wrappers in scripts/hpc/.
- Very specific: line 203
Keep AutoDL smoke suites under experiments/suites/, with raw outputs under experiments/runs/autodl_smoke/ and preflight reports under …
- Very specific: line 204
Add a pilot gate before formal suites: bounded pilot spec, raw outputs under experiments/runs/pilot/, and pass/fail/inconclusive decision …
- Distinctive: line 207
Keep formal suite definitions disabled or explicitly gated by default.
- Very specific: line 208
Keep AutoDL operational docs in docs/runbooks/AUTODL_HPC_RUNBOOK.md or an equivalent runbook.
- Very specific: line 209
Treat large uploaded data as an explicit manifest concern: expected paths under data/raw/ or data/processed/, with data/DATA_MANIFEST.md …
- Very specific: line 214
Treat src/<package_name>/ as the source of truth for reusable behavior.
- Very specific: line 215
Treat scripts/ as orchestration only: parse args, load config, call package APIs, write outputs.
- Very specific: line 216
Treat experiments/configs/ as hand-written intent and experiments/suites/ as reproducible task selection.
- Very specific: line 217
Treat experiments/runs/ as raw run provenance and experiments/results/ as curated, stable results.
- Very specific: line 218
Prefer metrics.json, summary.md, resolved_config.yaml, and run_metadata.json for experiment output bundles.
- Very specific: line 219
Use --config, --out-dir, and optional --set key=value CLI conventions for experiment scripts.
- Very specific: line 220
Keep data directories present with .gitkeep, but ignore large files under data/raw/, data/interim/, and data/processed/.
- Very specific: line 221
Add .gitattributes with LF line endings for shell scripts when HPC/Linux execution matters.
- Very specific: line 240
Use assets/repo-template/ for a new repo baseline or as a target shape during migration.
- Very specific: line 241
Read references/architecture.md when deciding where files belong.
- Very specific: line 242
Read references/skill-pack-architecture.md when the repo contains skills, shared references, installer scripts, Codex mirrors, or skill …
- Very specific: line 243
Read references/autodl-hpc.md when the repo mentions AutoDL, /root/autodl-tmp, FileZilla/SFTP, scripts/autodl_setup.sh, …
- Very specific: line 244
Read references/migration-playbook.md before reorganizing an existing repo.
- Distinctive: line 245
Do not copy SpectralStore's graph-compression domain code.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Research Repo Architect
Capability Routing
This is a first-layer entry skill. Keep it loaded as the user-facing route; when a request needs a specialized capability below, resolve the debuffer repo root from .debuffer_skills/installed-skills-codex.txt (repo_root) when available, read the referenced library SKILL.md, then follow that skill. Do not copy the whole library skill into this file.
/system-profile: read../library/experiments/system-profile/SKILL.md./training-check: read../library/experiments/training-check/SKILL.md./run-experiment: read../library/experiments/run-experiment/SKILL.md./overleaf-package: read../library/paper/overleaf-package/SKILL.md./submission-repo-cleanroom: read../library/review/submission-repo-cleanroom/SKILL.md.
Use this skill to turn research code or a skill bundle into a maintainable, reproducible repository. The base style is inspired by SpectralStore: reusable library code lives under src/, scripts are thin entrypoints, configs and suites describe experiments, raw runs are kept separate from curated results, and large artifacts stay out of Git.
Customized Pack Defaults
For research projects, read ../shared-references/lightweight-research-pack.md
when available. Default to a lightweight, AutoDL-first shape:
- Classify startup mode:
venue-only,reference-paper,reference-codebase,idea-doc,existing-repo, orpartial-results. - Local repo work should prepare structure, code, configs, tests, tiny smoke checks, prompts, and audit scripts. Design the scaffold around lightweight local verification plus remote-ready handoff.
- Add AutoDL/HPC hooks when experiments may need GPU time, but keep execution gated and manual by default: runbook, preflight, smoke suite, data manifest, and formal-run approval.
- Read
../shared-references/project-guide-protocol.mdwhen creating project memory. KeepPROJECT_STATUS.mdcurrent so future sessions know the macro phase; keep other Markdown project memory underdocs/category directories, such asdocs/project/PROJECT_BRIEF.md,docs/project/NEXT_ACTIONS.md,docs/evidence/findings.md, anddocs/experiments/EXPERIMENT_LOG.md; create or refreshdocs/project/RESEARCH_BLUEPRINT.md,docs/project/BLUEPRINT_GATE.md, ordocs/project/PROJECT_GUIDE.mdonly at stage gates. - Enforce root Markdown hygiene for ordinary research repos: root
.mdfiles are limited toREADME.md,PROJECT_STATUS.md, and tool-managedAGENTS.md/CLAUDE.mdwhen present. Put all other Markdown underdocs/with a category directory. Read legacy root files when they already exist, but write new or refreshed artifacts todocs/. - Read
../shared-references/autosci-lite-patterns.mdwhen scaffolding idea discovery, failure memory, pilot gates, or the macro state machine. - For external review, create
review-prompts/rather than wiring direct API, MCP, or SSH automation into the repository. - When the repo will eventually produce a paper package, prefer an
ICDE_YU_Memory-style manuscript layout or better: thinmain.tex, modular section files, dedicated figure assets, and contribution-bearing benchmark/discussion sections instead of a flat monolithic manuscript.
Workflow
Start by deciding which path applies:
- New repo scaffold: Create the architecture first, then add code and experiments into the right layer.
- Existing repo migration: Audit first, produce a migration map, then move code in small validated phases.
- skill framework or skill repo: Preserve the
skills/,skills/skills-codex/,skills/shared-references/,tools/,templates/,docs/,tests/, andmcp-servers/contracts instead of forcing everything intosrc/andscripts/. - skill-managed research project: Combine the SpectralStore experiment layout with skill runtime artifacts such as
research-wiki/,idea-stage/,refine-logs/,review-stage/,paper/, and.debuffer_skills/. - research blueprint handoff: When a stable method is about to become a
formal experiment protocol or paper plan, preserve
docs/project/RESEARCH_BLUEPRINT.mdanddocs/project/BLUEPRINT_GATE.mdas tracked project memory instead of burying the decisions in terminal logs. - AutoDL/HPC-ready research project: Add target-machine setup, preflight, smoke, result-transfer, and formal-run approval boundaries without weakening source/config/run/result separation.
- Lightweight project start: When materials are sparse, create only the minimal brief, plan, architecture, and next-action files needed for the current startup mode. Avoid generating a full research wiki or large Markdown bundle until the project has evidence worth preserving.
- AutoSci-lite lifecycle: Use A-E idea paths, append-only failure memory,
pilot gates, and the explicit
PROJECT_STATUS.mdphase map without adopting a full wiki platform.
For detailed directory rules, read references/architecture.md. For skill-pack-specific work, read references/skill-pack-architecture.md. For AutoDL/HPC work, read references/autodl-hpc.md. For migration work, also read references/migration-playbook.md.
New Repo Scaffold
- Identify the project slug, package/module name, research objective, first experiment ids, expected data sources, and whether the repo is primarily Python. If the user did not specify a package name, derive a lowercase underscore Python package name from the repo slug.
- Copy or recreate
assets/repo-template/into the target repo. Replace placeholders:{{project_slug}}: repository/project slug, usually kebab-case.{{package_name}}: importable module name, usually snake_case.{{project_title}}: human-facing project title.
- Keep reusable implementation under
src/<package_name>/. Do not put reusable algorithms, models, loaders, metrics, or query logic directly inscripts/. - Put runnable entrypoints under
scripts/:scripts/expN/for paper or study experiments.scripts/data/for download and preprocessing.scripts/analysis/for figures, tables, and summaries.scripts/hpc/for preflight, cluster wrappers, and machine-specific helpers.
- Put hand-written configs under
experiments/configs/and suite definitions underexperiments/suites/. New run outputs must go underexperiments/runs/, notexperiments/results/. - Add a short root
README.mdfor installation, smoke checks, data, and reproduction commands. Usedocs/for internal runbooks and maintenance notes. - Create
docs/project/,docs/experiments/,docs/evidence/,docs/paper/,docs/theory/, anddocs/runbooks/as needed. Do not scatter Markdown files in the repo root beyond the allowlist. - Add a conservative
.gitignoreso raw data, generated runs, caches, model checkpoints, and large binary artifacts are not tracked. - If the repo uses project-local skills, keep skill runtime state out of Git by default:
.debuffer_skills/traces/,.debuffer_skills/cache/,.debuffer_skills/runs/,.debuffer_skills/meta/events.jsonl, and project-local.agents/skills/symlinks. - Keep compact project memory tracked when it exists:
idea-stage/IDEA_MEMORY.mdandexperiments/NEGATIVE_RESULTS.mdare decision memory, not runtime traces.
Startup Mode Scaffolds
venue-only: createdocs/project/PROJECT_BRIEF.md,docs/project/NEXT_ACTIONS.md, a concise venue-risk checklist, and optionalreview-prompts/venue_direction_review_prompt.md.reference-paper: addreferences/ordocs/literature/notes, a claim map, and a reproduction/extension plan before writing experiment code. If the reference is a strong manuscript package template, also record what is worth copying at the package-architecture level: section topology, figure strategy, benchmark-construction handling, and discussion placement.reference-codebase: first audit the upstream repo, license, entrypoints, environment, and tests; add wrapper scripts instead of modifying upstream code blindly.idea-doc: preserve the original idea doc underdocs/project/ordocs/ideas/, extract assumptions intodocs/project/PROJECT_BRIEF.md, and write the smallest falsifiable validation plan.existing-repo: run the migration workflow; avoid overwriting existing data, results, notebooks, or user notes.partial-results: inventory logs/figures/tables first, writedocs/evidence/findings.mdanddocs/experiments/EXPERIMENT_LOG.md, then backfill missing configs or audit scripts.
For every startup mode, create or update PROJECT_STATUS.md with the current
macro phase, target venue, last accepted artifact, next gate, blockers, and the
phase map from project-guide-protocol.md.
When idea exploration or experiment planning begins, initialize compact memory only as needed:
idea-stage/IDEA_MEMORY.mdfor accepted/rejected/pilot-status idea entries.experiments/NEGATIVE_RESULTS.mdfor failed or inconclusive run evidence.
Do not create a full research-wiki/ or graph unless the user asks for a
long-lived knowledge base.
Existing Repo Migration
- Inspect before editing:
- Run
git status --short. - Use
rg --filesto inventory code, notebooks, scripts, configs, data, and outputs. - Read package/build files and the main run scripts.
- Run
- Classify every important file into one of these destinations:
src/,scripts/,experiments/configs/,experiments/suites/,experiments/runs/,experiments/results/,experiments/visualizations/,data/,docs/, or archive. - Present or record a migration map before moving files when the repo is large or risky. Include root Markdown cleanup: keep only the allowlist in root, move other Markdown into
docs/project/,docs/experiments/,docs/evidence/,docs/paper/,docs/theory/,docs/runbooks/, ordocs/archive/. Preserve user changes and do not delete old locations until imports, commands, and tests pass. - Move in phases:
- Package reusable code into
src/<package_name>/. - Convert ad hoc scripts into thin CLI entrypoints.
- Move hard-coded parameters into YAML configs.
- Route new outputs to
experiments/runs/. - Move only reviewed, canonical outputs to
experiments/results/orexperiments/visualizations/.
- Package reusable code into
- Update imports, CLI commands, README instructions, tests, and
.gitignoreafter each phase. - Never overwrite existing
data/raw/,experiments/results/, or user-created run outputs unless the user explicitly asked for that exact replacement.
Skill Repo Integration
Use this path when the repository is a debuffer-style skill pack: it has skills/<name>/SKILL.md, skills/skills-codex/, skills/shared-references/, tools/, AGENT_GUIDE.md, or installer scripts.
- Read
references/skill-pack-architecture.mdbefore editing. - Treat
skills/<name>/SKILL.mdas the mainline source of behavior. Treatskills/skills-codex/<name>/SKILL.mdas the Codex mirror that must preserve semantics while changing reviewer/tool routing only. - Put reusable cross-skill contracts under
skills/shared-references/. Put shared executable helpers undertools/. Put single-owner helpers underskills/<owner>/scripts/and keep compatibilitytools/shims when existing skills or installs depend on them. - Any helper invocation in a skill must use the canonical resolver chain from
integration-contract.md: owner layer 0 when applicable, then.debuffer_skills/tools/<helper>,tools/<helper>, and the repo root recorded in the install manifest. - When adding or renaming a skill in a skill repo, update all required surfaces in the same pass:
skills/<name>/SKILL.mdskills/skills-codex/<name>/SKILL.md- overlays only if reviewer routing differs
docs/SKILLS_CATALOG.md- count-bearing docs/tests such as
AGENT_GUIDE.md, the single rootREADME.md, and inventory tests
- Run the repository's inventory and targeted tests after integration. For this pack, prefer:
python tools/check_skills_inventory.py
python -m pytest tests/test_codex_skill_mirror.py tests/test_codex_install_update.py tests/test_install_*_tools_symlink.py- Keep skill packages under
skills/.src/is for reusable project/library code, not for declarativeSKILL.mdbundles.
Skill-Managed Research Projects
Use this path when a normal research project is being operated by skill workflows.
- Keep reusable implementation in
src/<package_name>/and experiment runners inscripts/as usual. - Keep skill handoff directories where downstream skills expect them unless the
user asks for a breaking migration:
idea-stage/,refine-logs/,review-stage/,paper/, andresearch-wiki/. - Inside
paper/, prefer a thinmain.tex,sections/for prose,figures/for final assets,tables/for generated fragments when useful, andappendix/for appendix-only assets. - Place Markdown handoff artifacts under
docs/when creating or refreshing them:docs/project/RESEARCH_BRIEF.md,docs/experiments/EXPERIMENT_PLAN.md,docs/paper/NARRATIVE_REPORT.md,docs/project/RESEARCH_BLUEPRINT.md, anddocs/project/BLUEPRINT_GATE.md. Read legacy root-level versions as fallback only. - Treat
.debuffer_skills/as runtime state. Keep traces, caches, wakeup state, and local skill symlinks out of Git unless the project explicitly wants reproducible agent provenance. - If
research-wiki/exists, preserve it as persistent project memory. Do not move it underdocs/orexperiments/. - Experiment outputs still go under
experiments/runs/; curated tables and figures still go underexperiments/results/andexperiments/visualizations/.
AutoDL/HPC-Ready Research Projects
Use this path when the repo will run on AutoDL or another SSH GPU/HPC machine.
- Read
references/autodl-hpc.mdbefore adding or changing remote-run scripts. - Keep target-machine setup in
scripts/autodl_setup.shand machine checks/wrappers inscripts/hpc/. - Keep AutoDL smoke suites under
experiments/suites/, with raw outputs underexperiments/runs/autodl_smoke/and preflight reports underexperiments/runs/preflight/. - Add a pilot gate before formal suites: bounded pilot spec, raw outputs under
experiments/runs/pilot/, and pass/fail/inconclusive decision recorded before formal approval. - Keep formal suite definitions disabled or explicitly gated by default. Require a dry-run and user approval before formal execution.
- Keep AutoDL operational docs in
docs/runbooks/AUTODL_HPC_RUNBOOK.mdor an equivalent runbook. - Treat large uploaded data as an explicit manifest concern: expected paths under
data/raw/ordata/processed/, withdata/DATA_MANIFEST.mdupdated for anything not tracked in Git. - Preserve the evidence boundary: smoke output validates engineering readiness only; curated claims and paper-facing tables are generated locally from audited raw runs.
SpectralStore-Style Rules
- Treat
src/<package_name>/as the source of truth for reusable behavior. - Treat
scripts/as orchestration only: parse args, load config, call package APIs, write outputs. - Treat
experiments/configs/as hand-written intent andexperiments/suites/as reproducible task selection. - Treat
experiments/runs/as raw run provenance andexperiments/results/as curated, stable results. - Prefer
metrics.json,summary.md,resolved_config.yaml, andrun_metadata.jsonfor experiment output bundles. - Use
--config,--out-dir, and optional--set key=valueCLI conventions for experiment scripts. - Keep data directories present with
.gitkeep, but ignore large files underdata/raw/,data/interim/, anddata/processed/. - Add
.gitattributeswith LF line endings for shell scripts when HPC/Linux execution matters. - In skill repos, keep generated runtime traces under
.debuffer_skills/traces/and keep reviewer trace references in audit artifacts instead of pasting reviewer summaries into main artifacts. - For AutoDL/HPC repos, keep deploy-key bootstrap, FileZilla/SFTP data exceptions, smoke pass criteria, and formal-run approval gates in a runbook instead of burying them in terminal history.
Validation
For Python repos, validate with the smallest reliable sequence:
python -m pip install -e ".[dev]"
python -c "import {{package_name}}; print('{{package_name}} import ok')"
python -m pytest
python -m ruff check src scriptsFor experiment structure, validate one dry run or tiny smoke task that writes only to experiments/runs/local_checks/.... Confirm no command writes directly to experiments/results/ unless it is an explicit curation or visualization step.
Resource Usage
- Use
assets/repo-template/for a new repo baseline or as a target shape during migration. - Read
references/architecture.mdwhen deciding where files belong. - Read
references/skill-pack-architecture.mdwhen the repo contains skills, shared references, installer scripts, Codex mirrors, or skill workflow artifacts. - Read
references/autodl-hpc.mdwhen the repo mentions AutoDL,/root/autodl-tmp, FileZilla/SFTP,scripts/autodl_setup.sh,scripts/hpc/preflight_autodl.py,run_autodl_smoke.sh, or formal-suite gating. - Read
references/migration-playbook.mdbefore reorganizing an existing repo. - Do not copy SpectralStore's graph-compression domain code; copy only the repository architecture and reproducibility conventions.
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.

