borghei/Claude-Skills / personal-productivity/reflect
reflect
VerifiedTurn reflection into decisions by scoring predictions against outcomes and tracking whether commitments held. Use when running a quarterly review, scoring forecast calibration, or reflection keeps producing notes instead of change.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 15.5 KB |
| assets/prediction-log-template.md | markdown | 3.3 KB |
| assets/quarterly-reflection-template.md | markdown | 3.6 KB |
| assets/sample_commitments.json | config | 1.3 KB |
| assets/sample_commitments_quarterly.json | config | 2.5 KB |
| assets/sample_predictions.json | config | 4.7 KB |
| references/calibration-and-forecasting.md | markdown | 18.7 KB |
| references/reflection-cadences.md | markdown | 17.5 KB |
| scripts/calibration_core.py | script | 7.4 KB |
| scripts/calibration_scorer.py | script | 9.0 KB |
| scripts/reflection_prompt_generator.py | script | 11.0 KB |
assets/quarterly-reflection-template.md
View on GitHub# Quarterly Reflection
**Quarter:** _______ **Date:** _______ **Time budget:** 90 minutes
The one cadence where structural change is allowed to happen. Weekly reflection
tunes; this one decides.
---
## 1. Score the predictions (20 min)
```bash
python3 scripts/calibration_scorer.py --input predictions.json --buckets 5
```
| Metric | Value | Reading |
|---|---|---|
| Resolved | ____ | ≥ 20 for a trustworthy estimate |
| Brier | ____ | < 0.20 good; > 0.25 worse than always saying 50% |
| Skill score | ____ | ≤ 0 means no more informative than the base rate |
| Overall gap | ____ | + is overconfident, − is underconfident |
| Worst domain | ____ | Usually your own delivery dates |
**Were the errors in a consistent direction?** _______________________________
---
## 2. Read the quarter's weekly reflections (15 min)
Read all twelve in one sitting. Individually unremarkable; in a batch they show
patterns invisible at weekly resolution.
**Recurring themes (3-5):**
1. _______________________________________
2. _______________________________________
3. _______________________________________
**The same blocker that appeared more than twice:** ___________________________
---
## 3. Prompts (20 min)
**Which quarter-start predictions were wrong, and in what direction?**
**What did I commit to and never start? What does that pattern say about what I actually value — as opposed to what I say I value?**
**Where was I overconfident, and what did it cost in decisions made on that confidence?**
**What did I learn that changed how I work, versus what I merely read about?**
**If I were advising someone else with this quarter's record, what would I tell them to stop doing?**
> This last prompt does disproportionate work. The advice you would give someone
> else is consistently clearer and more decisive, because it carries none of the
> sunk cost or self-image attached to your own record.
---
## 4. Decide (20 min)
### Kill one thing (required)
Every quarterly reflection kills at least one commitment — a recurring meeting,
a project, a metric nobody acts on, a habit that has not paid off.
This is not arbitrary. Commitments accumulate monotonically: each was added for
a reason and none individually feels worth removing, so without a forced removal
four quarters of additions leave no room for anything new.
**Killing:** _______________________________________
**Because:** _______________________________________
### Change one method
**From:** _______________________________________
**To:** _______________________________________
Phrase it as a rule, not an intention. "No meetings before 11:00 on Tuesdays and
Thursdays" is testable next week; "be better about deep work" is not, which is
why intentions survive for years unkept.
### Chronic commitments — decide each
Any commitment carried 3+ cycles. Carrying it again is a decision to never do
it, so make the decision explicitly.
| Commitment | Cycles carried | Decision (date / delegate / kill) |
|---|---|---|
| | | |
| | | |
---
## 5. Next quarter's predictions (15 min)
15-30 predictions with explicit confidence. Include your own delivery dates —
the highest-bias, fastest-resolving, most useful category to log.
| Statement | Domain | Confidence | Resolve by |
|---|---|---|---|
| | | | |
| | | | |
| | | | |
| | | | |
| | | | |
---
## Closing check
- [ ] One commitment killed
- [ ] One method changed, phrased as a rule
- [ ] Every chronic commitment given an explicit decision
- [ ] Next quarter's predictions written with confidence numbers
- [ ] One calibration correction chosen — exactly one
If none of these boxes is ticked, this was a reading exercise rather than a
reflection.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |