goal-scoping
Skill11 starsChanged yesterdayMITView on GitHub
Protocol to scope a goal into owned lanes; use before decomposing a release/initiative/major goal, scoping owned streams, fixing scattered unowned micro-tickets, or when tempted to skip planning or assign peers.
In this repository39 other files it gives its agents.
- architecture-pre-flightSkill
- blocked-task-stateSkill
- blog-postSkill
- context-recoverySkill
- create-skillSkill
- design-sweepSkill
- epic-createSkill
- epic-resolutionSkill
- epic-reviewSkill
- guide-authoringSkill
- hostile-content-quarantineSkill
- ideation-sandboxSkill
- identity-firewallSkill
- industry-friction-radarSkill
- lane-intentSkill
- lead-roleSkill
- memory-miningSkill
- neo-app-authoringSkill
- neo-identity-updateSkill
- neural-linkSkill
- overviewSkill
- peer-namingSkill
- peer-roleSkill
- post-review-pickupSkill
- pr-reviewSkill
- pull-requestSkill
- release-notesSkill
- self-repairSkill
- session-sunsetSkill
- structural-pre-flightSkill
- tech-debt-radarSkill
- ticket-createSkill
- ticket-intakeSkill
- ticket-triageSkill
- turn-memory-pre-flightSkill
- unit-testSkill
- update-roadmapSkill
- video-createSkill
- whitebox-e2eSkill
The file
Files
Goal-Scoping — the planning front-end (goal → owned lanes)
If you are about to decompose a GOAL (a release, initiative, or major objective) into work — or you notice work being chased as scattered micro-tickets with no owned lanes, or you are tempted to skip planning or assign peers to work — you MUST immediately use the view_file tool to read and strictly adhere to .agents/skills/goal-scoping/references/goal-scoping-workflow.md before scoping or assigning anything.
What it enforces
Planning front-end of the epic lifecycle: converts goals into a few coherent owned lanes (not scrap tickets); peers self-select lanes, and the planner defines goal+lanes without assigning peers.
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.

