Step-by-step guides to get the most out of your AI agent. No coding required.
Set your expectations right. Everything your agent can do out of the box, what needs setup, and what's not possible yet.
A practical 90-minute workflow for non-technical users to get one real result fast and avoid setup spiral loops.
The single most impactful thing you can do. Give your agent a name, a voice, and a personality with ready-to-use templates.
What models are, what they cost, how to get API keys, and which model is right for you.
A practical workflow to reduce token burn fast with smaller turns, strict output limits, and compact handoffs.
Talk to your AI agent from any Discord server. Full walkthrough plus troubleshooting for the most common issues.
A deterministic fix flow for Developer Portal account/session drift that blocks bot app creation.
Set up your agent on Telegram in under 5 minutes. The easiest channel to get running.
A practical setup + troubleshooting guide for adding your heyron agent to Google Chat spaces without getting stuck.
A practical first-run guide for local OpenClaw setup with a smoke-test flow and deterministic troubleshooting.
A deterministic setup for remote browser control: stable endpoint, origin/token checks, canary test, then real workflows.
Configure key + voice ID correctly, avoid free-tier gotchas, and run a known-good voice smoke test in minutes.
A quick fix for text-only Telegram replies: validate key + voice access and run a deterministic two-turn voice smoke test.
Why your agent "forgets" things, how memory actually works under the hood, and how to make important things stick.
A simple privacy audit flow to verify what your agent can access, what it remembers, and how to reduce oversharing risk.
A fast containment and prevention workflow for accidental data leakage in shared channels.
A simple redaction-first workflow to protect client information while still getting useful agent output.
Where file attachments work, where they don't, and workarounds for getting images and documents to your agent.
A practical guide to getting better outputs from your agent using a simple 4-part prompt formula and real before/after examples.
A 3-minute copy/paste format to report issues with exact evidence, clear repro steps, and destination context.
A simple 3-minute flow to use the active support path, submit complete evidence, and avoid retry loops.
A fast reopen format with fresh repro proof so unresolved issues don't get stuck in repeated support loops.
A quick route to active support when legacy channels are archived, with a copy/paste evidence packet for faster triage.
Delegate work safely with a manager+workers pattern, strict role boundaries, and a clean final merge workflow.
Complete guide to the OpenClaw Control UI. What every page, button, and field does — so you never feel lost.
Fix stale-file confusion with a fast versioning + quote-proof workflow so your agent uses the latest draft every time.
Recover fast when edits land in the wrong file by using a path-proof workflow, dry-run patching, and explicit do-not-touch boundaries.
Stop screenshot hallucination loops with a fast visibility test, recovery flow, and support-ready escalation packet.
A plain-English guide to session length, bloated chats, lost work, and the 4 habits that keep your progress safe.
A fast recovery pattern for long-chat degradation: preserve what matters, use a compact handoff, and avoid context bloat loops.
A fast recovery flow for post-reset silence, including clean-surface ping tests, permission checks, and session-mismatch fixes.
Why this is usually expected, how to verify your setup in 2 minutes, and when it’s a real issue worth escalating.
A plain-English guide to approval prompts: what they mean, when to approve, when to deny, and how to avoid getting stuck.
Fix repeated approval loops by approving exact commands, understanding allow-once scope, and avoiding command mismatch gotchas.
A fast fix for config save failures caused by redacted placeholder values being treated as real secrets.
Fix over-editing loops with a scope-lock workflow: target exactly what should change, protect everything else, and verify with diff proof.
A fast diagnostic checklist for laggy replies, long-running tasks, approval pauses, and getting back to reliable speed.
Fix execution-layer freeze loops where normal chat works but file/command tasks hang, using a canary-first recovery flow.
Break stale-session retry loops after config/key changes with a proof-first canary workflow.
Recover safely from over-restrictive policy changes with a one-rule-at-a-time rollback and canary-proof workflow.
Recover fast from oversized prompt failures using a staged workflow, compact context rules, and a copy/paste rescue prompt.
Fix the common "I could do this yesterday" loop by checking session surface, policy drift, and approval-state mismatches.
Use a side-by-side canary test to prove context mismatch fast and recover with exact-error evidence instead of guesswork.
Use a quick liveness + execution isolation flow to confirm runtime issues and recover safely without guessing.
Fix execution-mismatch trust breaks with a simple “done + evidence + verification” workflow and escalation packet.
A practical recovery checklist for common 502 failures, plus a clean support packet you can paste into #help.
A deterministic setup-time recovery flow that separates local noise from real host/runtime health failures.
A beginner-friendly 4-minute flow to isolate repeated setup-time reply errors and escalate with clean evidence.
Fix unauthorized login loops fast by resetting stale dashboard token state and re-pairing with the correct active gateway token.
Fix dashboard access failures by matching exact browser origin, updating allowedOrigins, and restarting gateway cleanly.
Fix node-connect failures caused by stale pairing state, token mismatch, or local-vs-remote URL confusion.
A quick isolation flow for blank dashboard pages caused by browser session, extension, VPN/proxy, or network-path issues.
Stop over-chatty behavior in Discord with clear response gates, silence rules, and a copy/paste group-chat policy block.
A focused recovery checklist for when “/” commands don't appear, including role permissions, channel overrides, and known-good tests.
A practical fix for guild/channel ID mixups and hidden channel permission overrides that make bots look "broken."
Use a clean-room channel test to isolate send-permission, thread/forum, and integration restriction issues in minutes.
Fix the high-friction typing-then-silent loop with a fast channel-policy isolation flow and known-good recovery steps.
Stop double-reply loops by isolating trigger paths, policy overlaps, and stale runtime config with a clean-room test.
Recover quickly when Discord UI goes blank during onboarding with a client-state reset flow and canary retest.
Fix the common “works in DM/channel, silent in thread” failure by checking archived/locked state and thread-level permissions first.
Force clean bullet-point output in chat apps with a strict format contract, canary test, and anti-regression workflow.
Fix silent/partial reply failures by switching to chunked output and file-first fallbacks instead of one giant message.
Diagnose Discord pin-action failures fast and use a reliable manual-handoff fallback when moderation actions are blocked.
A plain-English fix for the common confusion where DM works but server channels feel like a different agent.
Fix the “it forgot everything” confusion when switching between dashboard chat, Discord DMs, and server channels.
A fast identity/workspace verification flow for when your bot name, memory, or settings suddenly look wrong.
A fast path-first workflow to find missing outputs, verify actual write location, and stop "saved but can’t find it" loops.
A proof-first workflow to classify file mismatch fast (local ahead, remote ahead, or wrong context) before overwriting work.
Fix write-failure loops quickly with a path-proof workflow, tiny canary test, and evidence-first completion checks.
Stop duplicate-file chaos with deterministic naming, find-before-create rules, and a simple cleanup protocol.
Contain damage fast, recover safely with proof, and add guardrails to prevent destructive delete incidents.
Break repeated clarifying-question loops with a compact requirement block, strict ask policy, and evidence-first completion rules.
Stop language drift with a hard language lock, fresh-context reset, and output-format checks that keep replies consistent.
Fix Desktop/Documents visibility confusion with a deterministic workspace path check, upload flow, and quote-proof verification.
Use a single source-of-truth file workflow to prevent duplicates, enforce naming rules, and keep project folders clean.
Fix Discord DM privacy settings so Whambulance can open your support flow and your ticket doesn’t get stuck.
Fix repetitive heartbeat behavior with clean checklist design, non-repetition rules, and lightweight state tracking.
A practical recovery guide for heartbeat file path mistakes, stale instructions, repeated loops, and noisy check-ins.
Fix heartbeat-reply leakage in normal chat by separating maintenance polls from user-facing conversation behavior.
Fix timezone drift that causes wrong-day replies, off-schedule reminders, and confusing time-based behavior.
A practical 5-minute diagnosis flow for missing/late reminders, timezone mismatches, and wrong delivery context.
Stop “it stopped when I closed chat” confusion with a simple background-work model: explicit schedule + explicit destination.
Fix scheduler trust issues by choosing the right automation mode for exact reminders vs flexible background checks.
Fix weekday reminder misses by validating cron expression, timezone, delivery destination, and canary test proof.
A deterministic 5-minute checklist to separate real scheduler issues from timezone, delivery, and session-target drift.
A plain-English guide to the most common confusion: skills are behavior packs, not native software installs.
Recover quickly from broken model settings, invalid fallback IDs, and “all models failed” loops with a safe rollback workflow.
Fix model-switch 500 loops with a deterministic isolate→retest→restart flow and a support-ready evidence packet.
Stop unnecessary setup loops with a no-install recovery prompt, assumption check, and safer decision flow.
Fix security-restriction clone loops with a read-only canary test, context checks, and an evidence-first workflow.
Fix the common “needs CLI” confusion with a connector/auth check, tiny write test, and clean escalation packet.
Break the connected-but-unavailable loop with a fast account/scope/session check and a tiny canary test.
Fix connected-but-upload-failed loops with account/folder lock, canary upload proof, and one-variable-at-a-time recovery.
Fix connected-but-read-only Google Docs loops with a tiny canary write, permission checks, and an evidence-first recovery flow.
Fix Gmail connector send failures with a proof-first canary workflow and a clean loop-break escalation path.
A deterministic path to isolate attachment path/type/size failures without reconnect loops.
Fix sender-identity mismatch with a one-email canary proof flow for account and alias correctness.
A proof-first workflow to isolate deliverability issues, folder filtering, and sender-identity mismatch before reconnect retries.
Break connected-but-empty calendar loops with account/calendar proof, timezone checks, and a tiny canary read.
Fix connected-but-no-write loops with one canary create + read-back proof before scaling to real scheduling.
A deterministic edit-proof workflow for wrong-event edits, timezone drift, and stale Calendar display confusion.
Understand read-only web access vs browser automation, diagnose capability limits fast, and use a clean human+agent handoff.
A practical split-lane workflow: agent-led planning + human/API-backed publishing, without login-loop frustration.
A capability-safe Canva workflow: agent creates strategy + copy + design blueprint, human runs final in-editor actions.
A practical API-first workflow for drafting and publishing WordPress posts without browser-login failure loops.
A practical workflow for Midjourney: agent-led prompt strategy + manual generation steps, with a fast canary test and loop-break rules.
Diagnose private/login-gated URLs, anti-bot blocks, and safe workarounds when your browser can see pages the agent cannot.
Fix empty or low-signal search results with a canary query, constraint isolation flow, and a support-ready evidence packet.
Resolve "missing Brave key" confusion quickly with a canary-search workflow and a clean evidence-first escalation path.
A practical fix for “Dropbox MCP required” errors, with connector/auth checks, smoke test prompt, and escalation packet.
Fix connector "installed but unavailable" loops with a fast auth/session reset flow, smoke test prompt, and clean escalation packet.
Pre-built SOUL.md files for every use case — personal assistant, copywriter, fitness coach, real estate agent, and 48 more. Copy, paste, go. Free forever.
15+ ready-to-use skills: human writing, market research, daily briefings, email management, SEO, journaling, and more. Install in one command.
AI divorce mediation, robotics builds, kids curriculum, best setup tips, recurring support issues, and this week's helper shoutouts.