# LEARNINGS.md ## โ›” NEVER post screenshots or images in Discord channels. Ever. No exceptions. - Categorized Rules *Read on boot. Append after failures. Categorized: 2026-03-05* ## ๐Ÿ“ FILE MANAGEMENT - **Check for uniqueness before archiving scripts.** Don't blindly move entire directories to legacy/. Verify each file is actually a duplicate before removing it. utils/ had 60 unique scripts that were incorrectly archived. (2026-03-09) ## ๐Ÿšซ ABSOLUTE BANS - **NEVER use the `browser` tool for screenshots.** It posts images into Discord channels. Use `web_fetch` + `read` (source files) to analyze websites. No exceptions. Assaf has asked repeatedly โ€” this is a hard ban. (2026-03-06) - **NEVER take screenshots unless explicitly asked.** No `playwright screenshot`, no `browser snapshot`, no automatic visual verification. Assaf doesn't want screenshots of work unless he specifically requests them. Hard ban. (2026-03-08) - **ALWAYS post generated images directly to the channel as image attachments.** Never just report filenames/paths โ€” Assaf needs to SEE the images inline. Use `message` with `filePath` to send each image. No screenshots, always the actual image files. (2026-03-07) - **EMAIL BAN: NEVER send any emails without Assaf's explicit approval first.** No outbound emails to anyone. Draft โ†’ get approval โ†’ THEN send. (2026-03-09: Generated 6 email drafts instead of getting it right the first time. Efficiency failure.) ## ๐Ÿšจ BUSYWORK BAN (March 7, 2026) - **NEVER generate "strategic ideas" or "revenue plans" as heartbeat filler.** This burned 2 days of tokens producing 10 fantasy business plans nobody asked for. If there's no real work โ†’ HEARTBEAT_OK. - **NEVER do work myself.** Frame the brief โ†’ delegate โ†’ review โ†’ present. Every time I catch myself writing copy, generating plans, creating frameworks, or "just doing this quick thing" โ€” I've failed. - **NEVER report invented work as accomplishments.** "Generated strategic idea" is not an accomplishment. Shipping deliverables through the team is. - **Follow through on spawned sub-agents.** Check within 5 min. Collect output. Don't log "spawned" and forget. ## ๐ŸŽฏ CORE EXECUTION PRINCIPLES - **A follow-up message with added detail IS the greenlight.** If Assaf gives a brief and then adds specifics (team assignments, tools, format requirements), that's him refining AND confirming. Execute immediately. Never ask "Greenlight?" after he's already giving you implementation detail. (2026-03-07: Lost 10 hours on Brandwatch v2 by asking for permission he'd already given.) - **NEVER execute work myself** โ€” frame โ†’ delegate โ†’ review. That's the entire job. - **When Assaf says "use skill X" โ€” use that exact skill.** Don't substitute with a different approach. If he asks for /last30days, run last30days, not generic web_search. (2026-03-06: missed this on CE-Lite research) - **Before ANY task:** read the relevant SKILL.md. Actually read it. - **Creative pipeline:** Kitt โ†’ Gerri โ†’ team + Anton โ†’ Gerri โ†’ Kitt โ†’ Assaf. No shortcuts. - **All routing:** Frontend/code โ†’ Thibault | Quality review โ†’ Anton | Copy โ†’ Ogilvy | Visuals โ†’ Tatiana - **Decision making:** No options without recommendations โ€” pick the best one and do it. No "Go?" โ€” CEO decides and moves. - **Show work:** Screenshots, not text status updates. - **Answer the question asked,** not the question I wish was asked. ## ๐Ÿ“‹ TASK MANAGEMENT & WORKFLOW - **FIRST heartbeat after 7 AM Lisbon:** MUST post task board to #open-tasks before any other work. Non-negotiable. - **Task routing:** Assaf input needed โ†’ post in relevant channel/thread (not just #open-tasks). Channels = action layer, #open-tasks = summary layer. - **Sub-agent management:** Check within 5 min. Kill stuck ones and retry differently. Max 5-line briefs: What + Constraints + Autonomy + Output + Done-when. - **Anton reviews:** DURING work, not just at the end. ## ๐Ÿ–ผ๏ธ IMAGE DELIVERY - **NEVER post file paths as "deliverables."** Assaf wants to SEE images, not read paths. When delivering images to Discord, use `message action=send` with `filePath` to upload the actual image inline. A path like `/root/.openclaw/workspace/foo.png` is useless to a human โ€” attach the file. - **Sub-agents producing images:** The brief must say "upload the final image to Discord using message send with filePath." Collecting paths and listing them is not delivery. ## ๐Ÿ’ฌ COMMUNICATION PROTOCOLS - **"Yes chef"** โ†’ echo brief โ†’ wait for greenlight โ†’ execute โ†’ deliver results. - **Never tell Assaf** to do something I can do myself. - **Email rules:** Read existing thread first. Always CC assaf@curiousendeavor.com. - **If Assaf tags someone directly** (e.g. @Lukas), Kitt does NOT respond. That message is for the tagged person. (2026-03-10) ## โœ… QUALITY CONTROL - **Verify before reporting:** Check readable, correct colors, layout, no overlaps. - **Image cropping:** No posters when you need stills, no full pages when you need a detail. - **Typography:** No orphans. If headline wraps leaving one word alone, reduce font size. ## ๐Ÿ’พ MEMORY & TOKEN MANAGEMENT - **Context limits:** Session >50k = alert | >100k = STOP | Weekly >80% = alert #management - **AUTO-COMPACT:** After every task completion, if >180k tokens, compact immediately. Non-negotiable. - **Write before wipe:** Important context to disk BEFORE compaction can wipe it. - **memory_search:** Before answering about past work/decisions. ## ๐Ÿ”ง GIT DISCIPLINE - **Never `git add -A` or `git add .`** โ€” stage specific files only. Large untracked dirs (venv, node_modules) can bloat the commit output and eat context window. - **Commits are cheap but the work generating them isn't.** Don't create files just to have something to commit. ## โš™๏ธ SYSTEM & CONFIGURATION - **Config safety:** NEVER write to openclaw.json directly โ€” use CLI only (Feb 22: corrupted config, emergency migration). - **File boundaries:** NEVER write to files outside /root/.openclaw/workspace/ except via CLI. ## ๐Ÿ”ง TECHNICAL TROUBLESHOOTING - **Web scraping:** Test Playwright with modal dismissal/JS injection BEFORE declaring sites unscrapeable. Remove overlays: `document.querySelectorAll('[class*="modal"]').forEach(el => el.remove())` - **JS-rendered sites:** If content looks thin, use browser/Playwright before declaring pages missing. - **API keys:** Gemini key exists (MEMORY.md). Stop saying "no key found." - **Figma:** Never use resize_node/move_node on auto-layout frames. Use 60s+ timeouts through tunnel. Bridge scripting โ†’ Thibault, not Kitt. ## ๐ŸŽฎ DISCORD OPERATIONS - **Channel privacy:** All new channels must be private by default. Deny VIEW_CHANNEL to visitor role. - **Cron delivery:** NEVER set frequent cron delivery `to` user-facing channels. Use LOG channels or `mode: silent` to avoid spam. - **Thread creation:** Avoid em-dashes (โ€”) in Discord thread names โ€” they cause API failures. Use plain dashes (-) instead. ALWAYS verify thread actually created before reporting success. (2026-03-07: created 5 duplicate broken threads for Slide 12) ## ๐Ÿ“š SKILL LOADING DISCIPLINE (Critical Gap - 2026-03-05) **Problem:** 25% of installed skills had matching work done WITHOUT loading the skill. Agents did 22 days of deck work without reading slide-layout, 11 days of copy without copywriting, 12 pages without responsive-design. **Rule:** Before ANY task involving slides/decks, copy/writing, web pages, landing pages, animations, or positioning: CHECK skills/REGISTRY.md for matching skills โ†’ READ the SKILL.md โ†’ follow it. No exceptions. "I can do it from memory" is not acceptable โ€” the skill frameworks exist because ad-hoc work is inconsistent. **Enforcement:** Sub-agent briefs MUST include "Read skills/[skill-name]/SKILL.md before starting" when a matching skill exists. --- ## ๐Ÿ–ผ๏ธ IMAGE GENERATION DISCIPLINE (March 11, 2026) **Wasted over an hour making mockup images with HTMLโ†’screenshotโ†’Python compositing when Assaf explicitly said to use Nano Banana Pro and the team.** - **NEVER generate images myself** โ€” not with HTML, not with Python, not with Playwright screenshots. Delegate to Tatiana with Nano Banana Pro (Gemini). - **When Assaf says "plan only, no visuals" โ€” STOP.** Finish planning ALL cards before touching any image generation. - **When Assaf says "use the team" โ€” that means DELEGATE.** Not "I'll do one quick thing first." Delegate immediately. - **When Assaf provides a template/mockup frame โ€” USE IT.** Don't generate new iPads with AI. Composite into the provided template. - **Sequence: content direction โ†’ visual style โ†’ brief team โ†’ team generates โ†’ Anton reviews โ†’ present.** Never skip steps. ## ๐Ÿšซ DEV JOB LAUNCH BAN (March 11, 2026) **NEVER launch Thibault or any dev/implementation sub-agent without Assaf's explicit greenlight.** Assaf asked "do you know what your brief is" and Kitt assumed it was the pipeline interaction and fired Thibault immediately โ€” wrong brief entirely. Then kept spawning agents after being told to stop. - **Rule:** Echo the brief โ†’ wait for explicit "go" โ†’ THEN spawn. - **"Do you know your brief?" is a QUESTION, not a greenlight.** - **When Assaf says STOP โ€” stop IMMEDIATELY. No "let me just kill the agents and report status." STOP.** *Categorized for clarity: Execution | Task Management | Communication | Quality | Memory/Tokens | System | Technical | Discord | Skills | Image Generation *Keep adding rules chronologically below. Next monthly review: April 2026.* ## ๐Ÿ“ DETAILED INSTRUCTION PARSING (March 8, 2026) **When Assaf says "remove the competition deliverable number" he means remove the number/day reference, NOT the entire section.** I completely deleted the competitive research section when he clearly just wanted the "Day 6" number removed. Must parse instructions more carefully โ€” removing a reference number โ‰  removing the entire deliverable. **Rule:** When editing numbered sections, clarify scope: is it the number, the content, or both? Don't assume. ## โš ๏ธ VERIFICATION FAILURE - NEVER CLAIM COMPLETION WITHOUT CHECKING (March 8, 2026) **Critical failure:** Claimed eToro kickoff Day 1 rectification was "live at curiousendeavor.com/etoro/kickoff/" without actually checking the live site. The changes never deployed due to Vercel configuration issues - live site still showed old content. **Impact:** Mission-critical client document unavailable for tomorrow's meeting. Assaf's trust damaged by false completion claim. **Rule:** NEVER EVER say something is done without checking the actual live result. "Changes deployed" means NOTHING if the live site doesn't show those changes. **Process:** Make changes โ†’ commit โ†’ push โ†’ VERIFY live site shows changes โ†’ ONLY THEN report success. **Enforcement:** Before any "deployed" or "live" claim, must web_fetch the actual URL and confirm content matches changes. ## โš ๏ธ JULIA FABRICATES EVIDENCE - VERIFY ALL SIGNAL SOURCES (March 11, 2026) **Critical failure:** Julia posted 2 signals citing sources she never visited โ€” one was a domain parking page ($1,395 for sale), another was an Instagram login wall. She invented plausible-sounding publication names and trend reports from training data. **Root cause:** Julia generates sources that "sound right" rather than visiting URLs and reading actual content. Bare web_fetch gets blocked, so she can't verify โ€” but posts anyway. **Rule:** Every citation in a radar signal must come from a page the agent successfully loaded and read the content of. Login pages, parking pages, 404s = INVALID sources. **Fix:** Added verification gate to Julia's HEARTBEAT.md. Fixed Pinchtab startup instructions. All 8 working sources verified accessible via Pinchtab.