Use when creating GitHub issues, adding tasks to backlog, or when unsure which repo/project an issue belongs to. Triggers on "создай задачу", "issue", "добавь в бэклог", "task routing", "куда положить задачу".
npx skills add https://github.com/serejaris/personal-corp-skills --skill task-routing
Route issues to the correct repo using the routing config from CLAUDE.md. Part of the Personal Corp framework: project-init → task-routing → weekly-planning / weekly-retro.
digraph routing {
"New task" -> "Read routing config from CLAUDE.md";
"Read routing config from CLAUDE.md" -> "Match keywords → target repo";
"Match keywords → target repo" -> "Check duplicates in target repo";
"Check duplicates in target repo" -> "Duplicate found?" [shape=diamond];
"Duplicate found?" -> "Update existing issue" [label="yes"];
"Duplicate found?" -> "Check W-label exists in target repo" [label="no"];
"Check W-label exists in target repo" -> "Create issue in target repo";
}
Find the ### Task Routing section in CLAUDE.md of the current project (or the HQ repo if running from there):
### Task Routing (which issues go where)
routing:
- pattern: "bot, broadcast, onboarding"
repo: owner/bot-repo
- pattern: "content, lessons"
repo: owner/content-repo
- pattern: "strategy, cross-cutting"
repo: owner/main-repo
This config is created by project-init. If it doesn't exist — STOP and tell the user to run project-init first.
Match the task description against routing patterns. Rules:
# Check target repo
gh issue list -R {target_repo} -s open --json number,title --jq '.[].title'
# Check unified project (if configured)
gh project item-list {project_id} --owner {owner} --format json | \
python3 -c "import json,sys; [print(i['title']) for i in json.load(sys.stdin)['items']]"
If a similar issue exists → update it instead of creating a duplicate.
W-labels (W13, W14...) are created by weekly-planning, not manually.
# Check if current week label exists in target repo
gh label list -R {target_repo} | grep "W[0-9]"
weekly-planning run.gh issue create -R {target_repo} \
-t "prefix: title" \
-l "{w_label_if_exists}" \
--body "..."
Issue title prefixes follow conventional commits:
ops: — operational taskfeat: — new featurefix: — bug fixcontent: — content creationresearch: — research taskmenti: — mentoring related| You're about to... | Instead... |
|---------------------|-----------|
| Create issue in current repo without checking routing | Read CLAUDE.md routing config first |
| Add W-label that doesn't exist in target repo | Skip label — weekly-planning will add it |
| Add to Project #4 because "it's the main one" | Check which project the target repo uses. Or let GitHub auto-add handle it |
| Create issue without checking duplicates | Search target repo AND unified project |
| Guess the target repo | Ask the user if no pattern matches |
| Create retro:W{NN} label | Only weekly-retro creates these |
| Mistake | Fix |
|---------|-----|
| Issue about bot created in school-brain | Check routing: "bot" → hsl-mozg |
| W14 label created manually | W-labels come from weekly-planning only |
| Duplicate issue across repos | Search unified project before creating |
| No routing config found | Run project-init first |
| Added to wrong GitHub Project | Let GitHub auto-add handle project assignment |
# 1. Read routing from CLAUDE.md
# routing says: "bot, broadcast" → owner/hsl-mozg
# 2. User says: "создай задачу — рассылка по alumni"
# Keywords: "рассылка" matches "broadcast" → target = owner/hsl-mozg
# 3. Check duplicates
gh issue list -R owner/hsl-mozg -s open --json title --jq '.[].title' | grep -i alumni
# 4. Check W-label
gh label list -R owner/hsl-mozg | grep "W13"
# Found → use it
# 5. Create
gh issue create -R owner/hsl-mozg -t "ops: рассылка по alumni" -l "W13"
Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
Take serejaris/task-routing from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.