I-have-ADHD: A skill to stop coding agents from burying the answer
Recorded: Sept. 8, 2026, 5:08 p.m.
| Original | Summarized |
GitHub - ayghri/i-have-adhd: A skill to stop your coding agent from burying the answer. ADHD-friendly output. · GitHub Skip to content Navigation MenuSign inAppearance settingsPlatformAI CODE CREATIONGitHub CopilotWrite better code with AIGitHub Copilot appDirect agents from issue to mergeMCP RegistryIntegrate external toolsDEVELOPER WORKFLOWSActionsAutomate any workflowCodespacesInstant dev environmentsIssuesPlan and track workCode ReviewManage code changesCode QualityEnforce quality at mergeAPPLICATION SECURITYGitHub Advanced SecurityFind and fix vulnerabilitiesCode securitySecure your code as you buildSecret protectionStop leaks before they startEXPLOREWhy GitHubDocumentationBlogChangelogMarketplaceView all featuresSolutionsBY COMPANY SIZEEnterprisesSmall and medium teamsStartupsNonprofitsBY USE CASEApp ModernizationDevSecOpsDevOpsCI/CDView all use casesBY INDUSTRYHealthcareFinancial servicesManufacturingGovernmentView all industriesView all solutionsResourcesEXPLORE BY TOPICAISoftware DevelopmentDevOpsSecurityView all topicsEXPLORE BY TYPECustomer storiesEvents & webinarsEbooks & reportsBusiness insightsGitHub SkillsSUPPORT & SERVICESDocumentationCustomer supportCommunity forumTrust centerPartnersView all resourcesOpen SourceCOMMUNITYGitHub SponsorsFund open source developersPROGRAMSSecurity LabMaintainer CommunityGitHub StarsArchive ProgramREPOSITORIESTopicsTrendingCollectionsEnterpriseENTERPRISE SOLUTIONSEnterprise platformAI-powered developer platformAVAILABLE ADD-ONSGitHub Advanced SecurityEnterprise-grade security featuresCopilot for BusinessEnterprise-grade AI featuresPremium SupportEnterprise-grade 24/7 supportPricingSearch/Sign inSign upAppearance settings You signed in with another tab or window. Reload to refresh your session. Dismiss alert ayghri i-have-adhd Public
Notifications
Fork
Star Code Issues Pull requests Actions Projects Security and quality Insights
Additional navigation options
Code Issues Pull requests Actions Projects Security and quality Insights
mainBranchesTagsGo to fileCodeOpen more actions menuLatest commit History194 Commits194 CommitsFolders and filesNameNameLast commit messageLast commit date.agents/plugins.agents/plugins .claude-plugin.claude-plugin .codex-plugin.codex-plugin .cursor/skills/i-have-adhd.cursor/skills/i-have-adhd .github.github .opencode.opencode evalsevals extensionsextensions hookshooks scriptsscripts skills/i-have-adhdskills/i-have-adhd teststests .gitignore.gitignore AGENTS.mdAGENTS.md CONTRIBUTING.mdCONTRIBUTING.md GEMINI.mdGEMINI.md INSTALL.mdINSTALL.md LICENSELICENSE README.mdREADME.md gemini-extension.jsongemini-extension.json kimi.plugin.jsonkimi.plugin.json logo.pnglogo.png opencode.jsonopencode.json package.jsonpackage.json plugin.jsonplugin.json qwen-extension.jsonqwen-extension.json View all filesRepository files navigationREADMEContributingMIT licenseMore items ADHD-friendly outputs. No ADHD diagnosis needed! 🇬🇧 · Install Or 🔗 check the installation instructions. Before Great question! Let me think about this. Your auth flow has a few moving pieces: the middleware, the token verification, and the cookie handling. Looking at src/auth.ts, the verifyToken function (around lines 42-58) seems to be using an older jsonwebtoken API. One approach would be to update the package and rewrite that function. After making the change, you'd want to run the auth tests to confirm nothing breaks. By the way, you might also want to look at your dependency versions overall. Hope this helps! Let me know if you want to dig deeper. After Run npm install jsonwebtoken@latest, then edit src/auth.ts:42. Open src/auth.ts Next: paste the first failing line if any test fails. The rules Lead with the next action. Tune it Footer © 2026 GitHub, Inc. Footer navigation Terms Privacy Security Status Community Docs Contact Manage cookies Do not share my personal information You can’t perform that action at this time. |
This repository details a skill designed for coding assistants intended to mitigate the tendency of these agents to bury substantive answers in verbose or tangential commentary, aiming to produce results that are focused and actionable. The core philosophy of this skill is to enforce an ADHD-friendly output style by prioritizing action over lengthy exposition, ensuring that information is delivered directly and efficiently without unnecessary preamble or speculation. The mechanism operates by establishing specific rules for the generative model, demanding directness in response construction. These rules mandate leading with the next concrete action, structuring multi-step tasks sequentially, eliminating tangents, restating the current state after each turn, employing matter-of-fact error reporting, and enforcing brevity by capping lists. This structured approach shifts the agent's operational paradigm from discursive reasoning to direct execution planning, which is credited loosely on the basis of The Adult ADHD Tool Kit by J. Russell Ramsay and Anthony L. Rostain. The practical application involves instructing the coding agent to adopt these principles when generating responses. For instance, instead of offering general advice or lengthy thought processes regarding a technical issue, the skill forces the agent immediate execution steps. A demonstrated transformation shows that an inquiry about an authentication flow's token verification might be met with a direct recommendation to update a package and apply specific code edits, rather than a discursive analysis of potential issues. The system is designed not merely for stylistic change but to enforce a rigorous, execution-focused workflow during coding assistance. Installation involves copying the skill from the repository and following explicit installation instructions found in the repository's AGENTS.md file. Further tuning of the skill requires modifying the underlying configuration file, SKILL.md, to integrate these behavioral constraints. This customization process is further facilitated by alternative methods for deploying the skill within coding environments, such as installing it via a specific mechanism and then re-invoking the skill command to apply the new persona to the coding agent. The purpose of this tool is to enhance productivity by ensuring that AI-generated solutions are delivered in an immediately usable, highly focused format suitable for complex development tasks. |