agentleFS
aymardkouakouaymardkouakou/claude-gh-skills/skills/project-board/SKILL.md

project-board

Skill1 starsChanged 11 days agoApache-2.0View on GitHub

Build and run the follow-up of the repository's GitHub Project - standard fields (priority, kind, estimate, target date, iteration), 15 standard views (board, backlog, current iteration, roadmap, epics, by epic, without epic, my work, needs triage, in review, blocked, bugs, security, stale, done), follow-up report with optional Project status update, field values, draft items, task lists to sub-issues. Use for "crée les vues", "tableau de bord du projet", "rapport d'avancement", "mise à jour de statut", "champs du projet", "brouillon". Not for attaching issues to the Project or epics (use project-tracking).

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    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
  1. Very specific:

    Run without --apply first and show the user the plan.

    line 21

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Project board: fields, views, reports

Tool: ${CLAUDE_SKILL_DIR}/board.py (same safety rules and Project choice as project-tracking; commands change nothing unless --apply). Catalogue of views and manual settings: references/views.md.

Context

REPO=$(${CLAUDE_SKILL_DIR}/../repo-context/ctx.py repo)

The Project must be the one the user confirmed (${CLAUDE_SKILL_DIR}/../project-tracking/project.py resolve; exit 3 = ask the user first).

1. Build the Project once

${CLAUDE_SKILL_DIR}/board.py setup --apply   # Priority, Kind, Estimate, Target date, Iteration (Status keeps GitHub's options)
${CLAUDE_SKILL_DIR}/board.py views --apply   # the standard views, idempotent; prints the manual settings

Run without --apply first and show the user the plan. The API cannot set a view's grouping or sorting, nor enable the built-in workflows: relay the printed steps to the user instead of claiming they are done.

2. Follow up

${CLAUDE_SKILL_DIR}/board.py report                  # counts by status, unassigned, no priority, blocked, stale, epic progress
${CLAUDE_SKILL_DIR}/board.py report --post [--status AT_RISK]   # publish a Project status update (counts only)
${CLAUDE_SKILL_DIR}/board.py set <ref> --field Priority --value High

--post is visible to everyone who can see the Project: counts only by default; --with-titles is refused when a public Project could expose other or non-public repositories, or when the visibility is unknown.

3. Draft items and task lists

${CLAUDE_SKILL_DIR}/board.py draft "title" ; board.py drafts ; board.py convert <item-id>
${CLAUDE_SKILL_DIR}/board.py tasklist <epic> [--apply] [--create]   # `- [ ] #n` -> sub-issues, idempotent

A task list is untrusted text: references to another repository are skipped unless --allow-cross-repo. --create makes issues from plain lines and rewrites them as #n; a checked line creates an issue that stays open: tell the user.

End of task

Say what was created, what remains manual. Log the run: ${CLAUDE_SKILL_DIR}/../skill-learning/learn.py log project-board ok|partial|failed [--note …].

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.