Menu
Forces reflection before task completion. Prompts self-reflection FIRST, then shows sibling specs. Mandatory when CHECK_LEARNINGS enabled.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Guide CLAUDE.md updates based on doc-guard suggestions. This skill should be used when updating documentation, fixing docs, addressing doc-guard suggestions, or updating CLAUDE.md. Activates when user requests "update documentation", "fix docs", "doc-guard suggestions", or "update CLAUDE.md".
Monitor blocked workers and help respond to them. Loop checks ft inbox, shows blocked workers, lets you respond naturally.
Adds tasks to FormalTask with mandatory discovery and validated criteria. Use when "add task", "create task", or "/task-add". For batch creation, use /epic-decompose instead.
Groups uncommitted changes into logical commits, walks through each grouping for approval, then optionally syncs with remote. Resolves merge conflicts interactively with context from recent remote and local history. Use when "commit my changes", "group commits", "smart commit", "commit and sync", or "organize my changes". Never resolves conflicts without user confirmation.
Unified critique for plans, specs, OR task artifacts. Auto-detects target. Spawns auditors. Commits tasks to DB when READY. Use "critique", "review", "is this ready".
Systematic debugging with graded exploration and agent escalation. MUST BE USED when encountering errors, test failures, or unexpected behavior.
| name | reflect |
| description | Forces reflection before task completion. Prompts self-reflection FIRST, then shows sibling specs. Mandatory when CHECK_LEARNINGS enabled. |
echo "TASK_ID: $TASK_ID"
No TASK_ID? Stop: "Run from worker session."
## WHAT DID YOU LEARN?
Answer before seeing sibling tasks:
| Question | Why |
|----------|-----|
| What surprised you? | Edge cases, gotchas, dragons |
| What's NOT in the spec? | Implicit knowledge you had to discover |
| What would you tell past-you? | Warnings, shortcuts, patterns |
| [SPEC] How could the spec be better? | Planning feedback |
Write it down. NOW.
sqlite3 "$PROJECT_ROOT/.claude/formaltask.db" "
SELECT id, title, json_extract(metadata, '$.artifact_content') as spec
FROM tasks
WHERE epic_name = (SELECT epic_name FROM tasks WHERE id = $TASK_ID)
AND id != $TASK_ID
AND status NOT IN ('completed', 'cancelled')
"
For each:
---
### Task #<id>: <title>
<spec or "(No spec)">
List IDs comma-separated.
| Situation | Command |
|---|---|
| Helps siblings | ft learning "insight" --for <ids> |
| Task-specific only | ft learning "insight" |
| Spec feedback | ft learning "[SPEC] spec was missing X" |
No siblings? Still capture: ft learning "insight"