arjitj2
- 68 skills
- 0 followers
- 16 repo stars
- 3 days ago last updated
- ▌ Principle Test Behavior Not Implementation · arjitj2Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.
- ▌ Principle Migrate Callers Then Delete Legacy Apis · arjitj2Apply when introducing a new internal API while old callers still exist. Migrate callers and delete the old API in the same wave instead of preserving compatibility layers.
- ▌ Principle Separate Before Serializing Shared State · arjitj2Apply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first; serialize structurally only when one shared writer is a real invariant.
- ▌ Principle Experience First · arjitj2Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.
- ▌ Principle Model The Domain · arjitj2Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files.
- ▌ Maintain Verification Skill · arjitj2Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or "audit the verify skill".
- ▌ Principle Laziness Protocol · arjitj2Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem.
- ▌ Principle Attack The Premise · arjitj2Apply when two or more fixes that share one premise have failed the same gate. Write the premise down and test it directly before you write another fix that assumes it.
- ▌ Principle Explain The Number · arjitj2Apply before you measure, and before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.
- ▌ Principle Boundary Discipline · arjitj2Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.
- ▌ Principle Minimize Reader Load · arjitj2Apply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state in the reader's head; collapse one-caller wrappers and shrink mutable scope.
- ▌ Principle Foundational Thinking · arjitj2Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share. Get the data structures right so downstream code becomes obvious.
- ▌ Create Formal Verification Skill · arjitj2Generate a project-local skill that formally verifies the code where a bug costs the most and tests reach the least, in any language, with whichever verification tool fits. Use for /create-formal-verification-skill, "model-check this race", "prove this invariant", or when concurrency, retries, state machines, parsers, or unsafe code need more than tests.
- ▌ Principle Type System Discipline · arjitj2Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, exhaust variants, derive from authoritative schemas.
- ▌ Principle Subtract Before You Add · arjitj2Apply when sequencing an addition, refactor, or rewrite. Remove dead code, redundant validators, and stub references first, then build on the simpler base.
- ▌ Maintain Formal Verification Skill · arjitj2Bring a project's formal verification back in line with the code after the code changes: find the commits that touched verified code, update the model, harness, or properties to describe the code as it is now, rerun, and say whether each failure is drift in the verification or a bug in the code. Use for /maintain-formal-verification-skill, "is the model still true to the code", or after merges and refactors that touched verified code without rechecking it.
- ▌ Principle Exhaust The Design Space · arjitj2Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 competing prototypes and compare side by side before committing.
- ▌ Principle Guard The Context Window · arjitj2Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.
- ▌ Principle Never Block On The Human · arjitj2Apply when tempted to ask 'should I do X?' on reversible work.
- ▌ Principle Sequence Verifiable Units · arjitj2Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.
- ▌ Principle Make Operations Idempotent · arjitj2Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries. Converge to the same end state regardless of partial prior runs.
- ▌ Principle Outcome Oriented Execution · arjitj2Apply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don't preserve smooth intermediate states with throwaway compatibility code.
- ▌ Principle Encode Lessons In Structure · arjitj2Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.
- ▌ Principle Redesign From First Principles · arjitj2Apply when integrating a new requirement into an existing design.
- ▌ Blast Radius · arjitj2Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X', 'what could this break', or reviewing a small diff you don't trust.
- ▌ Setup Pstack · arjitj2Configure pstack's provider-qualified models, reasoning budget, subscription access, approved API spend, and saved backend fallbacks. Verifies only the assigned native and external model lanes before writing the override sheet. Use for /setup-pstack, "configure pstack models", "pstack budget", subscription routing, changing pstack's model choices, or the optional Codex startup-routing hook.
- ▌ Figure It Out · arjitj2Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions. Use for /figure-it-out or 'figure it out'.
- ▌ Ketchup Video · arjitj2 bundleCatch the user up like /ketchup, with a short subtitled video of slides for what happened and the waiting calls as text under it. Use for /ketchup-video.
- ▌ Show Me Your Work · arjitj2 bundleKeep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.
- ▌ Technical Writing · arjitj2Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.
- ▌ Benchmark Checklist · arjitj2Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benchmark or report a speedup or regression you measured.
- ▌ Principle Prove It Works · arjitj2Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'
- ▌ Create Verification Skill · arjitj2 bundleGenerate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.
- ▌ Principle Build The Lever · arjitj2Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.
- ▌ Principle Fix Root Causes · arjitj2Apply when debugging. Trace each symptom back to the first place the system went wrong and fix it there. A guard is a fix only when the state it handles is legitimate.
- ▌ Typescript Best Practices · arjitj2 bundleTypeScript best practices. Use when reading or editing any .ts or .tsx file.
- ▌ Verify Open Pstack · arjitj2 bundleVerify Open Pstack through installed Codex and Claude Code skills and its shipped Bun CLIs. Use for real behavior proof, routing or setup changes, orchestration bookkeeping, and release evidence.
- ▌ Automate Me · arjitj2Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via plugin-dev:skill-development + unslop, optionally pulling fresh evidence from recent transcripts.
- ▌ Interrogate · arjitj2 bundleUse for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.
- ▌ No Comments · arjitj2Spawn the comment-sicko subagent, fix accepted findings, and offer encodings for claimed constraints.
- ▌ Poteto Help · arjitj2 bundleGuides users through pstack setup, poteto-mode, and picking the skill, playbook, or principle for a task. Invoke `pstack:poteto-help` with a question; it does not load on its own. Not for requests to do work, even ones that name pstack.
- ▌ Poteto Mode · arjitj2 bundlepoteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.
- ▌
- ▌ Babysit · arjitj2Watch an open PR — fix failing CI, handle the straightforward review comments, and drive it to a mergeable state. Claude Code analog of Cursor's built-in /babysit. Use after opening a PR when the user wants the agent to shepherd it without re-prompting.
- ▌ Correct · arjitj2Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each time the operator corrects you. Use for /correct.
- ▌ Ketchup · arjitj2 bundleCatch the user up on what changed in this chat since their last message, in plain words and small visuals. List every item waiting on them with what they need to decide it from the reply alone. Use for /ketchup.
- ▌ Reflect · arjitj2 bundleSpawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.
- ▌ Sharpen · arjitj2 bundleSharpen a task before starting: the expert approach, what the user is really after, and the right level of specification. Use for /sharpen, /pstack:sharpen in Claude Code, or $pstack:sharpen in Codex.
- ▌ Architect · arjitj2 bundleSketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.
- ▌ Statechart · arjitj2 bundleCheck a TLA+ model of a system that moves between states, such as a product flow, a protocol, or a service, and draw it as a Mermaid statechart. The report gives the shortest path to each state that breaks a rule. Use for /statechart, /pstack:statechart in Claude Code, or $pstack:statechart in Codex, or to show a bug as a path through states.
- ▌ How · arjitj2 bundleUse for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.
- ▌ Tdd · arjitj2Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.
- ▌ Why · arjitj2 bundleUse for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
- ▌ Arena · arjitj2Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.
- ▌ Swarm · arjitj2Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.
- ▌ Teach · arjitj2Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.
- ▌ Recall · arjitj2Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief. Use for 'recall my work on X', 'catch me up', 'what have I been working on', 'where did I leave off', before starting or resuming work.
- ▌ Swiftui Design Principles 2 · arjitj2 bundleDesign principles for building polished, native-feeling SwiftUI apps and widgets. Use this skill when creating or modifying SwiftUI views, iOS widgets (WidgetKit), or any native Apple UI. Ensures proper spacing, typography, colors, and widget implementations that look and feel like quality apps rather than AI-generated slop.
- ▌ Deslop · arjitj2Use when the user asks to deslop, clean up, de-slop, harden, simplify, deduplicate, or improve code quality across an existing codebase, especially when the work spans unused code, circular dependencies, weak types, legacy paths, defensive fallbacks, and AI-generated clutter.
- ▌ Creating Skills · arjitj2Use when creating a new skill, adding a skill to the user's setup, or the user says "make this a skill". All personal skills live in the arjit-skills monorepo and are symlinked into place.
- ▌ Frontend Slides · arjitj2 bundleCreate stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
- ▌ Adding A Project · arjitj2Use when adding a new project to the user's personal site and resume, or when the user says to make something "live". Covers updating both arjit-me and arjit-resume, compiling the PDF, and pushing.
- ▌ IOS Simulator Testing · arjitj2End-to-end iOS simulator testing using blitz-iphone MCP and XcodeBuildMCP. Use this skill when testing an iOS app on the simulator — building, launching, interacting with the UI, and verifying state. Covers which MCP to use and when, gesture mechanics, and interaction patterns learned from real test runs.
- ▌ Address Copilot Review · arjitj2Handle GitHub Copilot PR review comments end-to-end. Use when the user asks to read Copilot's review on a pull request, decide which comments to act on, implement appropriate fixes, push follow-up commits, reply on each review thread with either the fix or the rationale for not changing code, and resolve threads that are fully addressed.
- ▌ Create Public Facing Pr · arjitj2Use when creating, publishing, or updating a public-facing GitHub pull request that should read cleanly for maintainers and users. Guides branch hygiene, staging, validation, commit wording, PR title/body, pushing, and final verification without exposing agent workflow details.
- ▌ Resolve Merge Conflicts · arjitj2Resolve PR merge conflicts end-to-end by identifying the base branch, merging it locally, fixing conflicted files carefully, validating the result, and pushing the updated branch. Use when the user asks to look at merge conflicts on a PR, resolve them, and push the branch.
- ▌ Squash Merge Dependabot Fixes · arjitj2Squash-merge already-assessed Dependabot PRs one by one, handling merge conflicts carefully, waiting for fresh CI after Dependabot rebases, checking security alerts, and recording the outcome.
- ▌ Swiftui Design Principles · arjitj2 bundleDesign principles for building polished, native-feeling SwiftUI apps and widgets. Use this skill when creating or modifying SwiftUI views, iOS widgets (WidgetKit), or any native Apple UI. Ensures proper spacing, typography, colors, and widget implementations that look and feel like quality apps rather than AI-generated slop.