goal-set
Skill0 starsChanged 4 months agoMITView on GitHub
Use at session start (or whenever designer wants to declare session intent) to write the primary session goal to active-goals.json. Designer says 'set goal X', 'goal for today is Y', 'what we're trying to achieve is Z'. Goal persists across chat for /goal-check verification at close.
In this repository68 other files it gives its agents.
- adoptSkill
- architecture-decisionSkill
- architecture-reviewSkill
- art-bibleSkill
- asset-specSkill
- brainstormingSkill
- bug-reportSkill
- bug-triageSkill
- code-reviewSkill
- consistency-checkSkill
- content-auditSkill
- create-architectureSkill
- create-control-manifestSkill
- create-epicsSkill
- create-storiesSkill
- day-one-patchSkill
- design-reviewSkill
- design-systemSkill
- dev-storySkill
- dispatching-parallel-agentsSkill
- estimateSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- gate-checkSkill
- goal-add-minorSkill
- goal-checkSkill
- godot-engineSkill
- helpSkill
- map-systemsSkill
- narrative-designerSkill
- project-stage-detectSkill
- propagate-design-changeSkill
- qa-planSkill
- quick-designSkill
- red-flag-scanSkill
- regression-suiteSkill
- retrospectiveSkill
- review-all-gddsSkill
- safety-pushSkill
- scope-checkSkill
- security-auditSkill
- session-closeSkill
- setup-engineSkill
- sprint-planSkill
- startSkill
- story-doneSkill
- story-readinessSkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- team-artSkill
- team-audioSkill
- team-combatSkill
- team-economySkill
- team-infraSkill
- team-levelSkill
- team-marketingSkill
- team-narrativeSkill
- team-polishSkill
- team-releaseSkill
- team-securitySkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 0 are distinctive, and 4 are 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.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 22
Write the session's primary goal to production/session-state/active-goals.json.
- Very specific: line 48
If primary_goal is already set + frozen: false, ask designer: "Existing goal is X.
- Very specific: line 50
If frozen: true, refuse to overwrite — primary goal is locked until session closes.
- Very specific: line 88
After this fires, /goal-add-minor can append mid-session minor goals
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
Goal Set — Declare Session Primary Goal
🌱 ShiningPlague-authored. No upstream version exists. Part of the session-goal tracking system (
/goal-set+/goal-add-minor+/goal-check).
Write the session's primary goal to production/session-state/active-goals.json. This is the goal that /goal-check validates at session close. Designer-invoked only — the assistant doesn't pick this; designer declares it.
If an artifact named here is absent: say so plainly in one line, skip that step, and continue. Never invent the file to satisfy a checklist, and never fail a close because an optional artifact was never created.
When to fire
- Session start, after designer states clear intent ("today we're authoring game-concept.md", "this session is META framework hardening", "we're shipping the Combat GDD")
- Whenever designer wants to formalize what THIS chat is trying to accomplish
- Auto-propose at session start if designer's first prompt is a workstream × activity declaration
When NOT to fire
- Mid-chat exploratory talk without commitment yet
- Designer hasn't picked a workstream + activity
- Goal would be vague ("do stuff", "work on it") — push back, ask designer to make it concrete
Procedure
Step 1: Read current active-goals.json
cat production/session-state/active-goals.jsonIf primary_goal is already set + frozen: false, ask designer: "Existing goal is X. Replace, keep, or amend?"
If frozen: true, refuse to overwrite — primary goal is locked until session closes. Offer /goal-add-minor instead.
Step 2: Capture goal + expected outcomes
Ask designer for:
- Goal text (1 sentence — what does shipping this session look like?)
- Expected outcomes (3-7 concrete bullets — what artifacts/decisions/behaviors will exist when goal is met?)
Per project-local /brainstorming SKILL: expected outcomes must be concrete (not "improved X" — say what clicks-into-what-result).
Step 3: Write to active-goals.json
Update fields:
session_id:YYYY-MM-DD-<workstream>-<topic-slug>session_started: today's datesession_focus:<Workstream> × <Activity>per session-focus modelfrozen: false (becomes true when designer fires first work-skill like /writing-plans)primary_goal.text: the goal sentenceprimary_goal.set_at: todayprimary_goal.expected_outcomes: the concrete bulletsaudit_log: append{ts, event: "goal_set", note: <goal text>}
Step 4: Update session-start hook awareness
If the project has written the optional tools/generate_session_context.sh (the template never ships it — .claude/hooks/session-start.sh runs it only when it exists), propose extending it to surface the active primary goal at session start. If there is no such script, skip this step — the goal still lives in active-goals.json and /goal-check reads it from there.
Step 5: Confirm + chain-propose
Report to designer:
- "Primary goal locked:
<text>" - "Expected outcomes:
<list>" - "Goal becomes FROZEN when first work-skill fires (per session-focus discipline)"
- "I'll surface it at session close for /goal-check verification"
Propose firing first work-skill if designer has chosen activity (chain-propose).
Cross-skill awareness
- After this fires,
/goal-add-minorcan append mid-session minor goals /goal-checkat session close validates all goals/session-closeStep 0 reads this file for pre-close verification- Pairs with built-in CC
/goalcommand if available (this skill = persistent file-backed wrapper; /goal = per-turn evaluator). Both can coexist.
Failure modes
- ❌ Setting vague goals ("do stuff") — push back for concreteness
- ❌ Overwriting frozen primary goal — refuse, offer /goal-add-minor
- ❌ Skipping expected outcomes — refuse, they're the verification criteria
- ❌ Auto-firing without designer declaration — this is designer-invoked
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.

