SamyakJhaveri
- 123 skills
- 0 followers
- 5 days ago last updated
- ▌ Pstack · samyakjhaveri bundlePick a pstack method before a task: a bug or failing test, code you have not read, a multi-file or batch change, writing or changing tests, an API or shared-state change, a measured number, a review, a hard multi-part job, or calling work done.
- ▌ Catchup · samyakjhaveri bundleFast 30s session bootstrap briefing. Use when resuming work after any break, at the start of a fresh session, or when unsure of current project state. Reports git status, recent commits, environment state, memory-index staleness, pending tasks, and red flags. NOT for deep code exploration or planning - it only reports state, it does not change it.
- ▌ Hypothesis Tree · samyakjhaveriStructured hypothesis tree manager for multi-step investigations. Use when a "why does X fail" question branches into sub-hypotheses, when an investigation spans several sessions and the reasoning must survive between them, or when falsifiable claims need tracking with linked evidence and dates. Maintains one markdown file with add, update, review, and prune subcommands, each gated on verifying that the cited evidence file actually exists and actually says what the claim says. NOT for a single-session bug hunt, a question answerable by one command, or as a general note-taking file.
- ▌ To Questionnaire · samyakjhaveri bundleTurn a decision you can't fully answer into a questionnaire for someone else to fill in.
- ▌ Writing For Agents · samyakjhaveri bundleWriting documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
- ▌ Setup Matt Pocock Skills · samyakjhaveri bundleConfigure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
- ▌ Resolving Merge Conflicts · samyakjhaveri bundleUse when you need to resolve an in-progress git merge/rebase conflict.
- ▌ Fable Prompting · samyakjhaveriWhich Claude Fable 5.1 guide sections you can act on from a session, and which Claude Code already injects. Use before writing a Fable prompt or plan.
- ▌ Vet Skill · samyakjhaveriSecurity-scan an external skill or bundle before installing it. Use whenever adopting a skill, plugin, or agent from a third-party GitHub repo or marketplace, before enabling it or copying it into the project. Wraps NVIDIA SkillSpector for a static scan and applies a pass/review/reject threshold. NOT for scanning your own authored skills as a quality check (use /code-review), and NOT a runtime sandbox - it inspects, it does not contain.
- ▌ Audit · samyakjhaveriCheckpoint on a plan or a piece of work - blind review, each finding reproduced before any fix, an independent second design, a short evidence-tagged report, then the updated work. Manual-only; an agent told to run it reads this file by path.
- ▌ Brief · samyakjhaveriTurn a raw request (often a transcribed voice note) into a brief: four lines and three fields, echoed back for correction, then handed to the ticket contract for a Track B ticket. Use when you type /brief or start a ticket from a request. Manual only. NOT for writing the ticket body itself (docs/factory/CONTRACT.md) or breaking a large request into several tickets (Track C).
- ▌ Sync To Hub · samyakjhaveri bundlePromote project-side `.claude/` improvements (skills, agents, hooks, rules) into the sam-cc-setup plugin in the hub repo. Sync is project -> hub, ADDITIVE ONLY. Each new or changed file is offered with a 3-way prompt (sync now / defer / never) so trial-only experiments do not pollute the curated hub. Use after a session in which you used or refined a tool worth keeping across future projects. NOT for mid-session use, uncommitted project work, or deleting anything from the hub (edit the hub directly for that).
- ▌ Run Spec · samyakjhaveriBuild a spec whose tickets form a task graph as one branch and one PR, in Loam or DistBench: plan a schedule from the blocking edges and the files each ticket touches, run parallel workers in their own worktrees, merge each into one integration branch, then run one full check and one review. Use when Samyak types it with a spec issue, a ticket list or a ticket file. Not for a single ticket: give it to one worker. Not for queued tickets run unattended: use bin/factory next.
- ▌ Wizard · samyakjhaveri bundleGenerate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
- ▌ To Spec · samyakjhaveri bundleTurn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.
- ▌ Ask Matt · samyakjhaveri bundleAsk which skill or flow fits your situation. A router over the skills in this repo.
- ▌ Grilling · samyakjhaveri bundleGrill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
- ▌ Research · samyakjhaveri bundleInvestigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
- ▌
- ▌
- ▌ Wayfinder · samyakjhaveri bundlePlan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
- ▌ To Tickets · samyakjhaveri bundleBreak a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker).
- ▌ Code Review · samyakjhaveri bundleReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
- ▌ Codebase Design · samyakjhaveri bundleShared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
- ▌ Diagnosing Bugs · samyakjhaveri bundleDiagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
- ▌ Domain Modeling · samyakjhaveri bundleBuild and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a CONTEXT.md, or recording or editing an ADR.
- ▌ Tech Selection · samyakjhaveriStructured trade-off analysis for choosing a library, tool, framework, or component during planning. Use when a plan or design must pick between 2+ candidate technologies, or when the user asks "which X should we use". Produces a bounded decision record: candidates compared on the actual task, assumptions ranked by an importance-by-evidence grid, and a tradeoff-per-option table. For a full measured bake-off, hands over to the experiment-loop skill. NOT for reviewing an already-written plan (use /plan-review) or open-ended ideation (use the local brainstorming skill in this plugin).
- ▌ Worktree Status · samyakjhaveriReport which git worktrees, branches, and PRs are done or ready to merge. Use when asking what's ready to merge, which worktrees or branches are done, or the status of worktrees, branches, and PRs across the repo. Fetches remote refs, then reports deterministically. NOT a session bootstrap (use /catchup) or a pipeline gate (use /validate); never edits worktrees.
- ▌ Plan Review · samyakjhaveriRun the merged blind plan review (correctness checklist + elegance gate in one agent) on a plan, spec, or design doc before execution. Accepts the artifact path as the argument. Use in a fresh session on a plan authored earlier, or before executing any non-trivial or hard-to-reverse plan. NOT for reviewing shipped code or diffs (use /code-review), or reviews where the author's rationale must be weighed (this flow deliberately withholds it).
- ▌ Surprise Me · samyakjhaveriFind a better route to a named goal than the current plan - ranked ideas the judge can verify, from independent lenses, with the cheapest one run as proof. For research questions, hypotheses, experiment designs, engineering designs and plans. Manual-only; an agent told to run it reads this file by path.
- ▌ Research Gap · samyakjhaveri bundlePick research questions or check a research gap, ending in one cheap validation: blind proposer seats, a merge with support counts, logged paper searches, and the closest papers read into a quote-checked reading log. Use for research questions, a gap, novelty or 'first to' claim, prior work for one claim, or logging a paper. Manual only.
- ▌ Factory Watch · samyakjhaveriRead the factory's status once and report a run that stopped, a PR that opened, or a failing precondition. Use when you type /factory-watch for one read. Manual only, so a /loop fire cannot run it: to watch on a loop, type the plain prompt `/loop 30m run bin/factory status (bin/runner 'bin/factory status' off the runner) and report only a run that stopped, a new pr-opened, or a new precondition FAIL since the last check`. Not for starting, stopping or merging a run: use bin/factory itself.
- ▌ Authoring Context Docs · samyakjhaveriSizing and anatomy rules for the two routing layers - the root CLAUDE.md (L0) and a subdirectory CONTEXT.md (L1). Use when authoring or refactoring the root CLAUDE.md, when it is over budget, when deciding whether content belongs in CLAUDE.md vs a rule file vs a skill, or when hand-writing a CONTEXT.md. To *generate* a CONTEXT.md from scratch, use /scaffold-context instead - it operationalizes Part 2 of this skill. NOT for: writing the project's architecture, design, or API documentation; authoring a skill body; or editing an existing CONTEXT.md whose shape is already settled.
- ▌
- ▌ Verify Loam · samyakjhaveri bundleProve a Loam change in a real rendered project: copier-render this checkout, then drive headless and interactive Claude Code sessions, stubbed Codex runs and copier updates in the render and capture hook, memory, deny-rule, update and check evidence. Use before shipping any seed, hook, settings or copier.yml change.
- ▌ Test Driven Development · samyakjhaveri bundleGuides implementing features and bug fixes test-first, enforcing the red-green-refactor cycle with mandatory failure verification.
- ▌ Understand Anything · samyakjhaveriAnalyzes a codebase with multiple agents and builds an interactive React knowledge graph dashboard for onboarding and visual architecture exploration.
- ▌ Dispatching Parallel Agents · samyakjhaveriDelegates independent debugging tasks to parallel agents with isolated context, preserving the main session for coordination.
- ▌ Subagent Driven Development · samyakjhaveri bundleExecutes implementation plans by dispatching a fresh subagent per task and running two-stage reviews for spec compliance and code quality.
- ▌ Finishing A Development Branch · samyakjhaveriGuides completing development work by verifying tests, presenting structured options for merging, creating a pull request, keeping, or discarding a branch, and cleaning up worktrees.
- ▌ Verification Before Completion · samyakjhaveriEnforces running verification commands and confirming output before claiming work is complete, fixed, or passing, ensuring evidence precedes any success claims.
- ▌ Render Gate · samyakjhaveriRuns a test-driven rendering loop for Copier templates, writing E2E assertions first and iterating until every flavor renders cleanly before committing.
- ▌ Create Skill · samyakjhaveri bundleGuides the creation of well-structured Claude Code skills and slash commands, covering skill types, scope, frontmatter settings, and file organization.
- ▌ Multi Review · samyakjhaveriRuns a structured code review using four parallel subagents covering style, correctness, security, and performance, then synthesizes findings by severity and gives an approve/needs-changes recommendation.
- ▌ Eval Grader · samyakjhaveriGrades and classifies evaluation batch results, applying exclusions, diagnosing failure modes, computing pass rates, and generating summary tables for papers.
- ▌ Paper Write · samyakjhaveri bundleDrafts a LaTeX paper section by section from an outline, with venue-specific templates and citation management.
- ▌ Template Sync · samyakjhaveriSync Claude Code assets between a project and its project-template buffer, with subcommands for status, diff, pull, promote, trial, and sync-from-buffer. Promotion is always opt-in and never automatic.
- ▌ Augment Test · samyakjhaveriRuns a data augmentation pipeline on a given input and reports pass/fail per transform, diagnosing failures against known issues.
- ▌ Critique Swarm · samyakjhaveriLaunches four parallel adversarial review agents covering security, scope, fidelity, and test gaps, then synthesizes findings into a ranked verdict for plans or feature branches.
- ▌ Grill With Docs · samyakjhaveri bundleStress-tests a plan against the project's domain model and documented decisions, sharpening terminology and updating DOMAIN.md and ADRs inline as decisions crystallize.
- ▌ Citation Audit · samyakjhaveriVerifies every bibliographic entry in a paper for existence, metadata accuracy, and contextual support using web/DBLP/arXiv lookups, flagging hallucinated authors, wrong years, fabricated venues, and misattributed citations.
- ▌ Grill Research · samyakjhaveriInterrogates research plans before evals or published claims, forcing explicit null hypotheses, confound checks, and data verification across four review waves.
- ▌ Overnight Eval · samyakjhaveriLaunches long-running evaluation batches in isolated tmux sessions with pre-flight verification, monitoring, and post-flight analysis for unattended runs.
- ▌ Scaffold Context · samyakjhaveriGenerates a CONTEXT.md routing file for a specified project subdirectory, following the canonical anatomy and ensuring it meets size and content constraints.
- ▌ Session Critique · samyakjhaveri bundleRuns an adversarial, decision-aware review of all session work before committing, checking decision adherence and code maintainability, and applies only user-authorized fixes.
- ▌ Paper Review Sim · samyakjhaveriSimulates a NeurIPS/SC/ICSE-style peer review with five reviewer personas (HPC, ML, Stats, Reproducibility, Devil's Advocate) that verify every claim against actual result data before submission.
- ▌ Plan Review Invoke · samyakjhaveriReviews a plan from a prior session by extracting the canonical reference prompt from seed/plan-reviewer-design.md and invoking the plan-reviewer agent with it, surfacing the verdict without auto-applying changes.
- ▌ Hpc Code Reviewer · samyakjhaveriReviews CUDA, OpenMP, and OpenCL code for parallel correctness, covering data races, memory model violations, synchronization bugs, numerical precision issues, and API-specific pitfalls.
- ▌ Interpret Results · samyakjhaveriAnalyzes evaluation results by requiring a stated hypothesis before examining data, then compares expectations to actual result files to prevent post-hoc rationalization.
- ▌ Paper Claim Audit · samyakjhaveriVerifies that every number, comparison, and scope claim in a research paper matches raw result files, using a fresh cross-model reviewer with no prior context to prevent confirmation bias.
- ▌ Cuda Omp Translator · samyakjhaveriReference guide for evaluating LLM-generated translations between CUDA and OpenMP, covering memory model mapping, kernel launch patterns, shared memory, atomics, and common failure modes.
- ▌ Navigate · samyakjhaveriRecommends the best skill, agent, or command for a given task by classifying intent and scanning available tools.
- ▌ Auto Paper Improvement Loop · samyakjhaveriIteratively improves a compiled LaTeX paper through two rounds of external LLM review, fix implementation, and recompilation.
- ▌ Improve Codebase Architecture · samyakjhaveri bundleFinds architectural friction in a codebase and proposes deep-module refactors to improve testability and AI-navigability, informed by the domain glossary and ADRs.
- ▌ Model Route · samyakjhaveriRecommends the optimal Claude model tier (Opus, Sonnet, or Haiku) for a given task by analyzing reasoning depth, blast radius, domain expertise, output length, and correctness cost, and suggests parallelization opportunities.
- ▌ Reflect · samyakjhaveriGenerates a structured post-task reflection capturing surprises, patterns, prompt improvements, and gotchas, writing it to a markdown file without modifying project rules.
- ▌ Unknowns · samyakjhaveri bundleSurface and clarify unknowns before prompting, log deviations during implementation, and verify understanding after, using HTML artifacts that pair prompts with outputs.
- ▌ Tdd · samyakjhaveri bundleGuides test-driven development with a red-green-refactor loop, emphasizing behavior-focused tests and vertical slicing over horizontal test writing.
- ▌ Decision Matrix · samyakjhaveriGuides users through structured decision-making with weighted scoring, criteria analysis, and clear recommendations, including quick and interview modes.
- ▌ Prompt Improver · samyakjhaveriResearches conversation and code context to generate 1-6 targeted clarifying questions when a prompt is vague, then executes the original request.
- ▌ Sam Handoff · samyakjhaveriWrites or updates a HANDOFF.md file in the project root to capture goal, progress, and next steps for a fresh agent to continue in-progress work.
- ▌ To Prd · samyakjhaveriSynthesizes the current conversation and codebase context into a structured PRD and publishes it to the project issue tracker with a triage label.
- ▌ Triage · samyakjhaveri bundleTriage issues through a state machine driven by triage roles, including gathering context, recommending actions, and applying outcomes.
- ▌ Codex Review · samyakjhaveriRuns the current git diff through the Codex CLI for an independent, read-only second-opinion review, then triages findings back into the session for Claude to apply fixes.
- ▌ Council · samyakjhaveriRuns a structured multi-agent deliberation: four specialist agents write independent position papers, two cross-examiners debate them, and the orchestrator synthesizes a final recommendation with implementation plan and risk register.
- ▌ Sop Writer · samyakjhaveriTurns a process description into a complete Standard Operating Procedure document with numbered steps, decision points, checklists, and troubleshooting guidance.
- ▌ Nature Skills · samyakjhaveriProvides nine skills for Nature-journal-family academic publishing, covering figure creation, prose polishing, manuscript writing, citation formatting, data availability statements, paper reading, reviewer responses, paper-to-PPT conversion, and academic search via an MCP server.
- ▌ Diagnose · samyakjhaveriRuns a disciplined debugging loop for hard bugs and performance regressions, covering reproduction, hypothesis testing, instrumentation, fixing, and regression testing.
- ▌ Zoom Out · samyakjhaveriProvides a higher-level map of relevant modules and callers using the project's domain glossary when you're unfamiliar with a code area.
- ▌ UI UX Pro Max · samyakjhaveriGenerates opinionated design systems with curated color palettes, font pairings, UI styles, product-type rules, and UX guidelines across multiple tech stacks.
- ▌ Prototype · samyakjhaveri bundleBuilds a throwaway prototype to answer a design question, choosing between a runnable terminal app for logic/state questions or multiple UI variations switchable from one route.
- ▌ To Issues · samyakjhaveriBreaks a plan, spec, or PRD into independently-grabbable issues using tracer-bullet vertical slices, then publishes them to the project issue tracker.
- ▌ Gpt Researcher · samyakjhaveriConducts autonomous multi-source research using a planner/executor architecture and an MCP server, with tools for deep research, quick search, report writing, and source retrieval.
- ▌ Self Healing · samyakjhaveri bundleContinuously improves Claude's effectiveness by recognizing patterns, saving memory, creating skills, and refining project knowledge. Use when Claude notices repeated workflows, encounters a problem it solved before, wants to save something for future sessions, needs to create a reusable skill, or when the user asks.
- ▌ Brainstorming · samyakjhaveri bundleGuides collaborative dialogue to turn ideas into approved designs and specs before any implementation begins.
- ▌ Writing Plans · samyakjhaveri bundleTurns a spec or requirements into a detailed, bite-sized implementation plan with exact file paths, code, and test steps for engineers with no codebase context.
- ▌ Storm Research · samyakjhaveriRuns Stanford's STORM pipeline to produce Wikipedia-quality research articles with citations, using Claude models and a search engine API.
- ▌ Weekly Review · samyakjhaveriRuns an interactive weekly review session to assess accomplishments against stated goals, identify missed items, and plan the next week with a structured report and accountability question.
- ▌ Codex Plan Review · samyakjhaveriRuns a plan file through the Codex CLI as an independent adversarial reviewer, then folds accepted findings back into the plan. Read-only sandbox; Codex never edits.
- ▌ Writing Skills · samyakjhaveri bundleUse when creating new skills, editing existing skills, or verifying skills work before deployment.
- ▌ Bootstrap Cc Setup · samyakjhaveri bundleBootstraps the always-loaded rules layer for a new repository: writes a CLAUDE.md skeleton and a workflow.md model-notes rule, and optionally installs a native git pre-commit hook. Skips repos already rendered by the Loam Copier template.
- ▌ Executing Plans · samyakjhaveriLoads an implementation plan, reviews it critically, executes each task with verification, and reports completion, stopping to ask for help when blocked.
- ▌ Workflow Mapper · samyakjhaveriTurns messy business process descriptions into structured workflows, classifies each step for automation potential using a GREEN/YELLOW/RED framework, and produces a prioritized automation roadmap with time savings estimates.
- ▌ Using Superpowers · samyakjhaveri bundleRoutes conversations to relevant skills from the library, prioritizing process-oriented skills and user instructions.
- ▌ Process Optimizer · samyakjhaveriAnalyzes workflows to identify inefficiencies, bottlenecks, and optimization opportunities, providing a structured report with recommendations for eliminating, resequencing, parallelizing, and automating steps.
- ▌ Academic Research · samyakjhaveriRuns a multi-agent academic research pipeline covering systematic review, LaTeX paper writing, peer review, and end-to-end orchestration with integrity gates.
- ▌ Code Review Graph · samyakjhaveriScopes code-review blast radius and detects architectural hotspots using Tree-sitter AST analysis and GraphRAG, with an MCP server for graph-based analysis.
- ▌ Using Git Worktrees · samyakjhaveriCreates isolated git worktrees with smart directory selection and safety verification for feature work.
- ▌ Systematic Debugging · samyakjhaveri bundleGuides a structured root-cause investigation before any fix, covering reproduction, evidence gathering, hypothesis testing, and implementation with failing tests.
- ▌ Receiving Code Review · samyakjhaveriGuides technical verification of code review feedback before implementation, emphasizing reasoned pushback over performative agreement.