agentleFS
ShiningPlagueShiningPlague/shiningplague-studio/skills/goal-check/SKILL.md

goal-check

Skill0 starsChanged 4 months agoMITView on GitHub

Use BEFORE /session-close OR when designer asks 'did we hit goals', 'goal status', 'verify outcomes'. Reads active-goals.json, validates each primary + minor goal against actual artifact/outcome state, reports PASS/PARTIAL/DROPPED/CARRY per goal. Gates close if critical fails.

  • Commits and pushes

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 4 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Verify session goals (primary + minors) against actual outcomes.

    line 22
  2. Distinctive:

    Before any git push of session work

    line 32
  3. Distinctive:

    If missing or empty: report "no goals set this session — close can proceed without goal-check, but next time use /goal-set at session …

    line 38
  4. Distinctive:

    All goals PASS → GREEN (close can proceed)

    line 55
  5. Very specific:

    Read unresolved_issues[]. For each:

    line 62
  6. Very specific:

    Update each minor_goals_added[].outcome field with PASS/PARTIAL/DROPPED/CARRY classification

    line 101
  7. Very specific:

    Update each unresolved_issues[].status per designer decision

    line 102
  8. Distinctive:

    If carry-overs exist, designer chooses destination per type (note: "next-session-priorities" is not a literal active.md section name.

    line 107
  9. Very specific:

    Workstream-relevant carry-over: add to active.md → 🚨 OPEN ADOPTION PLAN TODOs → Priorities (numbered list) with [Goal-Defer] prefix per …

    line 108
  10. Very specific:

    Registry-level priority shift: update data/_schemas/system_registry.json → next_session_priorities[] (top-level array)

    line 111

≈ “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.

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

Goal Check — Pre-Close Goal Verification

🌱 ShiningPlague-authored. No upstream version exists. Part of the session-goal tracking system (/goal-set + /goal-add-minor + /goal-check).

Verify session goals (primary + minors) against actual outcomes. Gates /session-close — if critical fails, close pauses for designer remediation. Closes the "shipped but didn't actually achieve goal" failure mode.

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

  • Auto-fire as Step 0 of /session-close (mandatory pre-close gate)
  • Designer asks: "did we hit goals", "verify outcomes", "goal status", "are we done"
  • Before any git push of session work

Procedure

Step 1: Read active-goals.json

If missing or empty: report "no goals set this session — close can proceed without goal-check, but next time use /goal-set at session start."

Step 2: For each goal (primary + minors), verify each expected outcome

For each expected outcome bullet:

  • Find evidence: glob for expected artifact, grep for content marker, git log for commit reference, hook output for state confirmation.
  • Classify:
    • PASS ✅ — evidence found, outcome shipped as specified
    • PARTIAL ⚠️ — some evidence but incomplete
    • DROPPED ❌ — no evidence, abandoned
    • CARRY 🔄 — moved to next session intentionally (designer flagged earlier)

Step 3: Aggregate verdicts

Compute:

  • Goal-level verdict: ALL PASS → goal PASS. Any DROPPED → goal needs review.
  • Session-level verdict:
    • All goals PASS → GREEN (close can proceed)
    • 1+ PARTIAL, 0 DROPPED → YELLOW (close OK with carry-over)
    • 1+ DROPPED, no critical → YELLOW (close OK with carry-over)
    • Critical DROPPED (designer-flagged as must-have) → RED (close PAUSES)

Step 4: Surface unresolved issues from active-goals.json

Read unresolved_issues[]. For each:

  • Status OPEN → flag for designer
  • Status RESOLVING → confirm with designer if shipped
  • Status DEFERRED → confirm carry-over destination (active.md priorities or sprint-status.yaml)
  • Status ACCEPTED → no action

Step 5: Output verification report

## Goal Check — YYYY-MM-DD

### Primary goal: <text>
- Outcome 1 — ✅ PASS (evidence: <file/commit/state>)
- Outcome 2 — ⚠️ PARTIAL (evidence: <partial state>, gap: <what's missing>)
- Outcome 3 — ❌ DROPPED (reason: <why>)
- ...

**Goal verdict:** PASS / PARTIAL / NEEDS-REVIEW

### Minor goals (N)
- MG-1: <text> — DELIVERED ✅
- MG-2: <text> — DELIVERED ✅
- MG-3: <text> — IN PROGRESS ⚠️
- ...

### Unresolved issues (N)
- ISS-XX: <text> — <status> — designer decision: <decision>
- ...

### Session verdict: 🟢 GREEN / 🟡 YELLOW / 🔴 RED

### Recommendation
- GREEN: Proceed with /session-close
- YELLOW: Proceed with explicit carry-over to active.md priorities + sprint-status.yaml
- RED: PAUSE close. Address [critical fails] first. Designer choices: fix now / formally drop with rationale / commit as partial.

Step 6: Update active-goals.json

  • Update each minor_goals_added[].outcome field with PASS/PARTIAL/DROPPED/CARRY classification
  • Update each unresolved_issues[].status per designer decision
  • Append audit_log: {ts, event: "goal_check_run", verdict: "<color>"}

Step 7: Carry-over write

If carry-overs exist, designer chooses destination per type (note: "next-session-priorities" is not a literal active.md section name; see options below):

  • Workstream-relevant carry-over: add to active.md → 🚨 OPEN ADOPTION PLAN TODOs → Priorities (numbered list) with [Goal-Defer] prefix per Item 15b
  • Session-discipline carry-over (next-session must-fire item): add to active.md → 🚨 NEXT-SESSION MUST-FIRE section
  • Sprint-relevant carry-over (fits next sprint): add to production/sprint-status.yaml
  • Registry-level priority shift: update data/_schemas/system_registry.json → next_session_priorities[] (top-level array)
  • Designer confirms each carry-over destination

Cross-skill awareness

  • Step 0 of /session-close MUST call this skill first
  • Pairs with built-in /goal (CC native per-turn evaluator) — this skill is the explicit final check
  • Chain: /goal-check → (YELLOW or GREEN) → /session-close continues. (RED) → close pauses.

Failure modes

  • ❌ Marking PASS without evidence — verification = command/file output, not assertion
  • ❌ Skipping unresolved issues review — they accumulate silently
  • ❌ Auto-marking everything CARRY to avoid hard decisions — push designer for honest disposition
  • ❌ Letting RED close proceed — close is gated, respect the gate

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.