amsborse
- 44 skills
- 0 followers
- 1 hour ago last updated
- ▌ Night Consistency · amsborseConsistency loop. Select one naming, error-handling, component or theme-token inconsistency, align a bounded set with an established repository pattern, and retain it only when checks show no regression. Use for "night-consistency", "night consistency" or as /night consistency.
- ▌ Night Performance · amsborsePerformance loop. Measure one real bottleneck with repeated baseline and candidate runs, make one bounded optimisation, and retain it only when the measured gain exceeds noise and behaviour stays stable. Use for "night-performance", "night performance" or as /night performance.
- ▌ Night Dependencies · amsborseDependency loop. Review advisories and update one package or lockstep group with the project package manager, favour patch and minor releases, and keep only a tested change with a consistent lockfile. Use for "night-dependencies", "night dependencies" or as /night dependencies.
- ▌ Working Agreements · amsborseThe owner's standing rules for any coding agent, learned from their repeated instructions and corrections across coding agents. Use at the start of any coding, debugging, UI or automation task in the owner's repositories; before reporting work as done or fixed; before any commit, push, merge, deploy or paid model call; when touching secrets, git state or another agent's work; during long autonomous or overnight runs; and for any UI, visual design or animation change. A repository's AGENTS.md and the current task's explicit instructions take precedence.
- ▌ Night Accessibility · amsborseAccessibility loop. Repair one evidenced interface barrier and retain it only when violation counts fall, keyboard paths work and no new barriers appear. Use for "night-accessibility", "night accessibility" or as /night accessibility.
- ▌ Night Evolve Skills · amsborseSkill-evolution loop. Improve one catalog skill from recorded failures and repeated corrections, validate the edit, and reserve changes to the active loop or engine for human application. Use for "night-evolve-skills", "night evolve skills" or as /night evolve-skills.
- ▌ Understand Code · amsborseUnderstand and explain a codebase or one area of it — architecture, entry points, data flow, dependencies, conventions and risky spots — with file:line evidence, as a short map or a diagram. Use for "understand the architecture of this repository", "how does X work", "explain this codebase", onboarding, or before changing unfamiliar code.
- ▌ Add Interactions · amsborseAdd hover, press, drag and pointer interactions that fit the product (magnetic hover, cursor light, tilt, springs, drag) with keyboard parity, touch fallbacks and reduced motion, browser-verified. Use for "add hover interactions" or "micro-interactions".
- ▌ Automate Browser · amsborseAutomate a browser workflow — navigate, fill forms, click through flows, extract page data, take screenshots, or turn a repeated manual task into a reusable script — with the cheapest reliable browser tool available and explicit confirmation before anything outward-facing (submitting, purchasing, posting, sending). Use for "automate this browser workflow", "fill this form", "scrape this page", "click through this flow" or "make a script for this web task".
- ▌ Night Bug Hunter · amsborseBug-hunting loop. Start from a red baseline, reproduce one failure, add a failing regression test and repair its root cause, keeping the fix only when the original failure and relevant checks pass. Use for "night-bug-hunter", "night bug hunter" or as /night bugs.
- ▌ Production Ready · amsborseNever deploy, publish or change production config unless the user asked for it in this task.
- ▌ Replicate Design · amsborseReproduce how a reference feels and behaves, not its property. Never copy its images, fonts,
- ▌ Coordinate Agents · amsborse bundleSplit work across agents — delegate an isolated implementation to OpenAI Codex through codex-bridge in its own git worktree, run independent parts in parallel subagents, then review and integrate the results yourself. Includes the former /codex-frontend workflow. Use for "use Codex for this", "delegate to Codex", "split this work", "run agents in parallel" or "orchestrate agents".
- ▌ Security Audit · amsborseAudit a codebase or change for security problems — secrets, authentication and authorization, injection, XSS/CSRF/SSRF, unsafe deserialization, dependency CVEs, risky install scripts, permissions and data exposure — with a threat model sized to the system, concrete exploit scenarios, and fixes. Also reviews third-party skills, plugins and MCP servers before adoption. Read-only unless fixes are asked for. Use for "security audit", "security review", "threat model", "is this safe" or "check for secrets".
- ▌ Build Animation · amsborse bundleMotion rules are in the UI taste section of ~/agent-skills/working-agreements/AGENTS.md: one
- ▌ Improve Visuals · amsborse bundleMake an existing UI look better in rounds, judged blind on real screenshots, not on speed. Use for "improve the visuals" or "make it look better".
- ▌ Test Everything · amsborse bundlePlan, write and run tests across the stack — unit, integration, end-to-end and visual — find the gaps that matter, fix flaky tests at the cause, and report real results. Use for "test everything", "add tests", "improve test coverage", "set up e2e tests", a test strategy, or when a change needs proof beyond reading the code.
- ▌ Night Redteam · amsborseRed-team loop. Prove one exploitable trust-boundary failure only with a local failing test, then repair its root cause or record an owner decision when no safe fix fits. Use for "night-redteam", "night redteam" or as /night redteam.
- ▌ Create Visuals · amsborseOne signature visual per product acts as its brand mark: it belongs to the page, blended in
- ▌ Night Refactor · amsborseRefactoring loop. Characterise existing behaviour before simplifying one bounded area, preserve the public API, and keep the change only when tests and review show equivalent behaviour with less complexity. Use for "night-refactor", "night refactor" or as /night refactor.
- ▌ Night Research · amsborseResearch loop. Investigate one repository question with primary sources and code evidence, then return a cited markdown report with confidence levels and unknowns, without changing any files in the worktree. Use for "night-research", "night research" or as /night research.
- ▌ Review Changes · amsborse bundleA report the owner can read without opening the code: the interface as pictures, everything else
- ▌ Run Autonomous · amsborseRun a long or multi-step task autonomously — overnight, while the user is away, or until a list of milestones is done — with an isolated branch or worktree, a ledger of progress and decisions, bounded retries, and an evidence-backed report. Includes the nightly-evolution routine (one draft PR of improvements per night). Never pushes, merges or deploys unless asked. Use for "run this task autonomously overnight", "keep going until done", "work on this while I sleep" or "run nightly evolution".
- ▌ Audit Design · amsborse bundleAn audit reports; it does not fix. Change code only when the user asks for fixes, then hand
- ▌ Night Visual · amsborseVisual loop. Improve one evidenced interface issue, compare real screenshots in both themes and configured viewports, and retain the change only when visual review and runtime checks support it. Use for "night-visual", "night visual" or as /night visual.
- ▌ Build Feature · amsborse bundleBuild a feature end to end — ground it in the code, write a short brief, implement, test, verify on the real target and review. Scales from a small change (just do it and verify) to a large feature (spec first, worktree, parallel workers). Use when asked to build, add or implement a feature, "build this end to end", or "write a spec/brief" for one (the former /spec).
- ▌ Manage Skills · amsborseManage this skill catalog — find which skill fits a request, create or update a skill, vet and adopt a third-party skill, reinstall or repair skill discovery for any agent, and learn new rules from past agent conversations (history-learning). Use for "which skill should I use", "add a skill", "update my skills", "install skills", "learn from my history" or when a skill seems missing or broken.
- ▌ Night Improve · amsborseImprovement loop. Rank small repository improvements by evidence, make the best bounded change, and keep it only when checks prove the intended benefit without regressions. Use for "night-improve", "night improve" or as /night improve.
- ▌ Experience · amsborseOne entry point to make a web product look, feel and perform better. Audits first, then runs the fewest creative skills that fit. Use for "/experience" or "take this site to the next level".
- ▌ Night Docs · amsborseDocumentation loop. Find one mismatch between repository instructions and actual code, correct it with precise examples, and retain the edit only when the documented commands and claims are verified locally. Use for "night-docs", "night docs" or as /night docs.
- ▌ Night Ideas · amsborseIdea loop. Rank product and engineering opportunities from repository evidence with explicit priority scores, returning actionable proposals and follow-ups without writing files. Use for "night-ideas", "night ideas" or as /night ideas.
- ▌ Night Tests · amsborseTest-coverage loop. Each iteration finds the riskiest untested behavior, adds one focused test in the project's own style, proves it would catch a break, and keeps it only if the suite stays green. Use for "night-tests", "add tests overnight", "grow coverage in a loop" or as /night tests.
- ▌ Review Code · amsborseReview a diff, branch, commit or PR for real bugs, performance problems, needless complexity and missing tests, and verify every finding before reporting it. By default the review is an independent read-only pass by OpenAI Codex through codex-bridge (the former /codex-review); without the bridge it is a careful self-review. Use for "review this", "code review", "second opinion", "have Codex check it", or before calling a large change done.
- ▌
- ▌ History Learning · amsborse bundleLearn durable preferences, corrections, decisions and working patterns from historical coding-agent conversations (Claude Code, Codex, Cursor, OpenCode, Antigravity, Kiro, Qwen) and turn them into reviewed, evidence-backed skill updates. Use when asked to learn from past conversations or chat history, mine repeated corrections or preferences, update skills from experience, run incremental history learning, or audit what has been learned. Read-only over history, consent-gated per source, redacts before any model sees text, and never publishes or overwrites skills on its own.
- ▌ Revamp UI · amsborse bundleThe bar is the UI taste section of ~/agent-skills/working-agreements/AGENTS.md, with details and
- ▌ Verify · amsborseVerify a change where the user actually looks at it (local browser, Vercel/production URL, LG TV, Windows desktop app, Chrome extension) and report pass/fail with real evidence. Use when the user runs /verify, says something is "still broken" / "I still see the old one", or before claiming a UI or runtime fix is done.
- ▌ Fix Bug · amsborseFind and fix a bug — reproduce it on the real target, find the root cause, write a failing regression test, fix, and confirm the fix where the user saw the bug. Use for errors, crashes, failing tests or CI, wrong behavior, "this is broken", "still broken" or "I still see the old one".
- ▌ Improve · amsborseAudit a project or area for improvements, rank them, implement the safe ones and verify them in one pass, then list the rest as numbered options. Also covers behavior-preserving refactors and measured performance work. Use when the user runs /improve [area], asks "what can be improved" (and would otherwise follow up with "implement all"), or asks to refactor, clean up or speed something up.
- ▌
- ▌ Build UI · amsborseNew UI should look like it was always part of the product. Extend what exists: the project's
- ▌ Night QA · amsborseUser-flow QA loop. Exercise one main journey end to end, capture reproducible breaks, and add one regression-backed repair or a precise bug-hunter follow-up, with runtime evidence for every claim. Use for "night-qa", "night qa" or as /night qa.
- ▌ Ship · amsborseShip finished work end to end once the user asks for it — run the checks, compare failures with a baseline on main, merge, push, deploy and health-check when the repo has a deploy step, then clean up this session's branches, worktrees and servers and report the commit. Use for "ship it", "merge and push", "merge, push and deploy", "merge to main and clean up" or "push everything and delete the branches". Not for deciding whether something is ready (production-ready) or for unasked releases.
- ▌ Night · amsborse bundleRun autonomous, verified improvement loops on a repository overnight or while away. It plans by priority, works on an isolated run branch, delegates each iteration to an agent, verifies and keeps or reverts every change, survives crashes through a watchdog, and writes an evidence-only morning report. Never pushes, merges or deploys. Use for "/night", "/night auto", "/night tests", "run loops overnight", "night status", "night report" or "stop the night run".