agentleFS
ojiudezueojiudezue/productmind-skills/skills/auto-kanban/SKILL.md

auto-kanban

Skill81 starsChanged 6 months agoLicence not identifiedView on GitHub

A capture-first kanban board for agent-driven work. Fights chat-to-plan context loss with one rule: every user push AND every agent mid-turn discovery becomes a card the SAME turn, before acting. Source of truth is a structured YAML data file (committed); markdown and HTML views are regenerated by a render script that shows a STALE banner when code or docs move without a board reconcile; the release script refuses to deploy without naming the cards being shipped and marks them shipped as part of the deploy flow; a hosted board's disposition buttons (done/deferred/declined + approve/investigate on intake cards) queue operator dispositions the agent applies at session start. Load this skill at session start, whenever the user pushes a new idea or request, whenever the agent proposes something mid-turn (a test, a config knob, a bug it just found), and before writing a planning doc (to harvest cards into the plan). Includes the adjacency sweep, finish-the-job rule, an Investigating lane with binary exits, verify-before-work against ground truth, a config-first gate step, card linking, and the unattended overnight-pass contract.

  • Deletes or force-pushes

The file

Show its rules and text

We split this skill into the rules it gives an agent

30 rules. About 0 are common, 21 are distinctive, and 9 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈21

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 9

    Very specific

    Tied to their project's names, files or tools. Probably skip.

The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.

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.