agentleFS
paslavskyipaslavskyi/llm-wiki/.claude/skills/kb-goal/SKILL.md

kb-goal

Skill1 starsChanged 33 days agoMITView on GitHub

Use when the owner creates or edits a product Goal in dialogue — "створи Goal «...» — він включає ...", "додай до цілі ...", "покажи ціль ...". Creates the GOAL- note, discovers existing notes for its scope via recall, elicits/researches and captures new notes, and reports composition. Goals are independent of the operational plan (kb-plan).

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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:

    Discover existing knowledge: use kb-recall (MAP → domain indexes → notes) for each idea the owner listed.

    line 18
  2. Distinctive:

    Never mark progress by hand — it is derived.

    line 34
  3. Distinctive:

    Do not touch PLAN-001 here — planning is kb-plan's job.

    line 40

≈ “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.

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

kb-goal — create and maintain product goals

Goal: a goal note (GOAL-, domain roadmap) = назва + опис + scope (ids of member notes). Progress is COMPUTED (share of scope with status accepted) — never stored. Goals are orthogonal to PLAN-001: scope items may sit in the plan's queue, backlog, or nowhere.

Flow for «Створи Goal "..." — він включає <ідеї/пункти>»

  1. Create the note via kb-capture conventions (omit id — the pipeline assigns the next GOAL-; type goal; domain roadmap; scope: []; topic — the roadmap area's TOP- node, if the map has one; write through npm run kb:write).
  2. Discover existing knowledge: use kb-recall (MAP → domain indexes → notes) for each idea the owner listed. Report what was found and WHY it belongs; add confident matches to scope, ask about doubtful ones.
  3. Formulate the new: for each idea with no note — analyze; ask clarifying questions where the intent is ambiguous; research (web / deep-research) if knowledge is missing; then capture new notes of the correct types (FEAT/FR/STORY/Q/RISK/...) via kb-capture and add their ids to scope.
  4. Report composition: goal id, scope list (found vs newly created), computed progress, and whether any scope items are already in PLAN-001 (queue/backlog) — without implying the goal itself is planned.

Editing an existing goal

  • «додай X до цілі» / «прибери X» → update the goal note's scope through the write pipeline (npm run kb:write with full note content). The pipeline heals: dedupe, deprecated→live resolution, no self-refs; validate gates dangling ids.
  • Never mark progress by hand — it is derived. A goal is "done" when all scope is accepted; celebrate it, don't store it.

Rules

  • One goal = one theme. Two unrelated themes in one request → two goals.
  • scope items must be live notes; capture before adding.
  • Do not touch PLAN-001 here — planning is kb-plan's job. If the owner says «і бери в роботу» — finish the goal, then invoke kb-plan.

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.