stripe-projects
stripe projects
honest-forget
Graceful memory compression with integrity — summarize before forgetting, never fabricate
Full skill instructions
"Summarize before forgetting. Never fabricate."
Graceful memory compression that preserves wisdom. Compress context gracefully when budget is exceeded. Extract wisdom, create pointers, and let go with integrity.
Compress context gracefully when budget is exceeded. Extract wisdom, create pointers, and let go with integrity. Never silently lose information or fabricate what was forgotten.
ASSESS → EXTRACT → COMPRESS → POINTER → RELEASE
Before forgetting, understand what you have:
assessment:
file: "path/to/file.md"
tokens: 5000
contains:
decisions: ["List of decisions made"]
learnings: ["What was learned"]
questions_answered: ["Q&A pairs"]
dead_ends: ["What didn't work"]
importance:
for_current_task: "high|medium|low"
for_future_reference: "high|medium|low"
Compress iterations into lessons:
wisdom:
id: "wisdom-001"
title: "LEARNED: [Pattern/Pitfall]"
compressed_from:
iterations: "45-55"
original_tokens: 15000
lesson: |
The core insight in one paragraph.
pitfalls:
- "What to avoid"
example:
good: "What works"
bad: "What doesn't"
retrieval_hint: |
When to recall this wisdom:
- [trigger condition]
Leave breadcrumbs for retrieval:
pointer:
to: "path/to/archived/content"
summary: "One line about what's there"
retrieve_when:
- "Specific condition"
contains:
- "What you'll find there"
| Field | Required | Purpose |
|---|---|---|
file | ✓ | Path to content |
tokens | ✓ | Size estimate |
importance | ✓ | How critical |
decisions | Choices made | |
learnings | What was learned | |
dead_ends | Failed approaches |
| Field | Required | Purpose |
|---|---|---|
id | ✓ | Unique identifier |
title | ✓ | Brief summary |
lesson | ✓ | Core insight |
compressed_from | Source info | |
pitfalls | What to avoid | |
example | Good/bad examples | |
retrieval_hint | When to recall |
| Field | Required | Purpose |
|---|---|---|
to | ✓ | Archive path |
summary | ✓ | One-line description |
retrieve_when | Trigger conditions | |
contains | What's there |
| File | Purpose |
|---|---|
FORGET.yml | Current forgetting session |
WISDOM.yml | Extracted lessons |
POINTERS.yml | Retrieval breadcrumbs |
archive/ | Compressed content |
| Command | Syntax | Action |
|---|---|---|
ASSESS | ASSESS [file] | Evaluate what's there |
EXTRACT | EXTRACT [wisdom] | Pull out lessons |
COMPRESS | COMPRESS [level] | Create summary |
POINTER | POINTER [to] | Leave retrieval hint |
RELEASE | RELEASE [file] | Remove from context |
| Level | Ratio | Keeps | Use When |
|---|---|---|---|
| FULL | 1:1 | Everything | Still actively needed |
| WISDOM | ~5:1 | Lessons, decisions, key facts | Work is done, wisdom remains |
| SUMMARY | ~10:1 | Essence and pointers | Background reference only |
| POINTER | ~50:1 | Just retrieval hints | Rarely needed, but should remember it exists |
DO:
DON'T:
Say: "I compressed earlier iterations. The wisdom I retained is X."
Offer: "I can retrieve the original if needed."
Don't: "Make up details that feel right."
Always include in context:
FORGET.ymlWISDOM.ymlPOINTERS.ymlstripe projects
Harvest every `ponytail:` comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals ponytail leaves behind get tracked instead of rotting into "later means never". One-shot report, changes nothing.
okx dex market
okx agentic wallet
gmgn portfolio
okx dapp discovery
okx agent payments protocol
Stripe payment processing with checkout sessions, subscriptions, webhooks, and customer management.
Build comprehensive 3-5 year financial models with revenue projections, cost structures, cash flow analysis, and scenario planning for early-stage startups. Use this skill when creating financial projections, calculating burn rate or runway, modeling fundraising scenarios, or preparing investor-r...
Stock and cryptocurrency analysis with portfolio management and multi-dimensional scoring.
Real-time crypto derivatives positioning, whale tracking, liquidations, and institutional ETF flows across 37 specialized tools.
Master dbt (data build tool) for analytics engineering with model organization, testing, documentation, and incremental strategies. Use when building data transformations, creating data models, or implementing analytics engineering best practices.
ChainClarity explains 700+ crypto whitepapers in plain English, with layered summaries, comparisons, research tools, alerts, and a $4.99 Pro plan.
Stay Ahead with Finalle.ai: The Ultimate Financial News and Tools Platform
AI-powered Pine Script code generator for TradingView
Research stocks at the speed of thought.
Empower your investment strategies with AI signals, option flow data, and advanced chart patterns.
Danelfin review covering its AI stock and ETF scores, rankings, portfolio tools, current pricing, strengths, risks, and alternatives for investors.
A software for comprehensive market sentiment analysis.
'Stock Correlations' App by Freshly.ai: Reveal Stock Patterns and Trends