github-projects
Skill3 starsChanged 3 months agoMITView on GitHub
Manage GitHub Projects V2 boards — list items by sprint, set status/sprint fields, add issues to boards, query field metadata. Use when working with GitHub project boards, sprint assignments, or board status transitions.
- Installs packages
4 other projects use a version of this.
Adopted by
Most recently taken up by
- andrewzeitlin/claude_skillstheir own version, first seen Oct 8, 2026
- JeanKadang/DOC-GitHub-Practice-Skillstheir own version, first seen Sep 28, 2026
- 0jg/skillstheir own version, first seen Jun 15, 2026
- gauravv-g/claude-skills-collectiontheir own version, first seen Apr 26, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- gauravv-g/claude-skills-collection★ 1same name
- JeanKadang/DOC-GitHub-Practice-Skills★ 1same name
- 0jg/skills★ 0same name
- andrewzeitlin/claude_skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository41 other files it gives its agents.
- cadence-goalsSkill
- ci-feedback-loopSkill
- compoundSkill
- decision-rights-doctrineSkill
- diataxisSkill
- dispatch-gateSkill
- drift-checkSkill
- family-checkSkill
- fix-then-re-review-ladderSkill
- gitSkill
- goal-treeSkill
- handoffSkill
- improvement-loopSkill
- kb-captureSkill
- kb-compileSkill
- kb-coreSkill
- kb-lessons-bridgeSkill
- kb-lintSkill
- l1-supervisorSkill
- l2-supervisorSkill
- lessons-learnedSkill
- lN-lifecycle-doctrineSkill
- lN-review-doctrineSkill
- medical-recordsSkill
- operator-interview-doctrineSkill
- operator-interviewSkill
- operator-reviewSkill
- planning-workflowSkill
- pr-review-fanoutSkill
- pull-taskSkill
- ralph-wiggumSkill
- reviewSkill
- root-cause-depthSkill
- scan-documentSkill
- self-improvementSkill
- self-verifySkill
- skillifySkill
- task-workflowSkill
- testing-without-mocksSkill
- vault-cloudSkill
- verify-inherited-premiseSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 41
When: Before any query operation, or after mutations to refresh state
- Distinctive: line 66
When: Add a GitHub issue to the project board
- Very specific: line 81
All read operations query the local SQLite cache.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
GitHub Projects V2
Consolidated operations for GitHub Projects V2 board management. Provides query and mutation operations backed by a local SQLite cache (project-board-helper) and GraphQL mutations via gh api graphql.
Prerequisites
project-board-helperbinary:go install github.com/pfeff/project-board-helper/cmd/project-board-helper@latestghCLI with project scope:gh auth refresh -s projectsqlite3(ships with macOS)jqfor JSON processing
Cache DB: ~/Library/Caches/<project>/project-board.db
Operations
1. Sync Cache
When: Before any query operation, or after mutations to refresh state
Implementation: Load operations/sync-cache.md
Quick summary: Runs project-board-helper sync to refresh the local SQLite cache from the GitHub API
2. Field Metadata
When: Need field IDs or option IDs for mutations (Status, Sprint, etc.)
Implementation: Load operations/field-metadata.md
Quick summary: Queries field definitions via project-board-helper field <name>, extracts field IDs and option IDs
3. List by Sprint
When: Query board items for a specific sprint, optionally filtered by status
Implementation: Load operations/list-by-sprint.md
Quick summary: SQLite query against cache DB filtering by Sprint field value, with optional Status filter
4. Set Status
When: Change an item's status (e.g., to "In Progress", "Done")
Implementation: Load operations/set-status.md
Quick summary: GraphQL updateProjectV2ItemFieldValue mutation for the Status field. Item must already be on the board.
5. Set Sprint
When: Assign an item to a sprint
Implementation: Load operations/set-sprint.md
Quick summary: GraphQL updateProjectV2ItemFieldValue mutation for the Sprint field. Item must already be on the board.
6. Add to Board
When: Add a GitHub issue to the project board
Implementation: Load operations/add-to-board.md
Quick summary: gh project item-add with project number and owner. Idempotent — safe to call on items already on the board.
7. Lookup Item
When: Need to resolve an issue reference (owner/repo#number) to a project item ID for mutations
Implementation: Load operations/lookup-item.md
Quick summary: project-board-helper lookup <owner/repo> <number> against the local cache
Common Patterns
Read Path (cache-backed)
sync-cache → field-metadata / list-by-sprint / lookup-itemAll read operations query the local SQLite cache. Call sync-cache first to ensure freshness.
Write Path (GraphQL mutations)
lookup-item → set-status / set-sprintMutations require the item ID (from lookup-item) and field/option IDs (from field-metadata).
Add + Configure
add-to-board → sync-cache → lookup-item → set-sprint + set-statusNew items need to be added to the board first, then cache synced to pick up the new item ID.
Quick Reference
| Operation | Tool | Command |
| Sync cache | project-board-helper | project-board-helper sync |
| Field metadata | project-board-helper | project-board-helper field <name> |
| List by sprint | sqlite3 | Query against cache DB |
| Set status | gh api graphql | updateProjectV2ItemFieldValue mutation |
| Set sprint | gh api graphql | updateProjectV2ItemFieldValue mutation |
| Add to board | gh | gh project item-add <number> --owner <owner> --url <url> |
| Lookup item | project-board-helper | project-board-helper lookup <owner/repo> <number> |
Defaults
| Setting | Value |
| Owner | pfeff |
| Project number | 4 |
| Project node ID | PVT_kwHNa8POARiyqQ |
| Cache DB | ~/Library/Caches/<project>/project-board.db |
For full default configuration, see references/project-defaults.md.
Error Handling
| Error | Resolution |
project-board-helper not found | go install github.com/pfeff/project-board-helper/cmd/project-board-helper@latest |
| Auth failure / missing project scope | gh auth refresh -s project |
| Item not found on board | Use add-to-board first, then sync-cache |
| Stale cache | Run sync-cache to refresh |
| Unknown field name | Check available fields with project-board-helper field (no args) |
Progressive Disclosure
operations/*.md— Detailed implementation steps for each operationreferences/graphql-templates.md— Reusable GraphQL mutation and query blocksreferences/project-defaults.md— Default project IDs, field names, and configuration
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.