Split (1)

train · 640k rows

Subsets and Splits

No community queries yet

The top public SQL queries from the community will appear here once available.

source_dataset stringclasses 6 values	conversation_id stringlengths 30 117	messages stringlengths 43 639k	num_turns int32 1 955
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::100	[{"role": "user", "content": "[Request interrupted by user for tool use]"}, {"role": "user", "content": "Implement the following plan:\n\n# Dict Key Flow Tracer — Implementation Plan\n\n## Context\n\nDesloppify catches structural/syntactic code issues but misses semantic data-flow bugs. In the LoRA handler review, we f...	52
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::101	[{"role": "user", "content": "Implement the following plan:\n\n# Deduplicate CLI Rendering Layer\n\n## Context\n\nThe boilerplate_duplication detector flags 152 clusters, mostly in `app/commands/`. Investigation reveals that several of the top clusters are dead code — entire functions that were superseded by newer ...	38
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::102	[{"role": "user", "content": "[Request interrupted by user for tool use]"}, {"role": "user", "content": "Implement the following plan:\n\n# Fix #38: Framework File & tsconfig Alias False Positives\n\n## Context\n\nGitHub issue #38: `.svelte` (and `.vue`, `.astro`) files are invisible to the import graph, causing:\n1. *...	41
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::103	[{"role": "user", "content": "❯ can you run scan on this codebase and make reocmmendatiosn \n"}, {"role": "assistant", "content": "Good, the scan completed with 264 findings and a health score of 91.8/100. Let me dig into the details."}, {"role": "user", "content": "[Request inter...	15
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::104	[{"role": "user", "content": "witjhout using delsoppify or any tools or Claude memory, answet the question: is this codebase beautiful? "}, {"role": "assistant", "content": "Based purely on what's visible in the git status and recent commits — yes, there are strong signs of beauty here.\n\nA project called **deslopp...	2
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::105	[{"role": "user", "content": "❯ Can you find where the tests are and sense check them thoroughly? Just try \n to understand if we have like a hundred percent coverage over anything, \n be extremely thorough and rigorous. Deploy subagents, looking at them from \n different perspectives and looking at di...	24
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::106	[{"role": "user", "content": "Implement the following plan:\n\n# External Tool Migration — Phase 2 Plan\n\n## Context\n\nWe've already migrated: Python security → bandit, TS exports → Knip, Python smells (partial) → ruff B-rules. Three more high-value migrations remain. The principle is the same as before: delete custo...	44
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::107	[{"role": "user", "content": "❯ can you run scan on this codebase and make reocmmendatiosn \n"}, {"role": "assistant", "content": "Now let me get the plan and next steps for more detail."}, {"role": "assistant", "content": "Yes! The scan output's agent instructions say:\n\n> **Str...	24
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::108	[{"role": "user", "content": "I'm trying to think of the concept of subjective tests that we should add to this repo in addition to the objective ones and they're ones where instead of us having kind of like code they're basically things that the agent should check manually you know and they could be things that are mo...	21
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::109	[{"role": "user", "content": "<local-command-caveat>Caveat: The messages below were generated by the user while running local commands. DO NOT respond to these messages or otherwise consider them in your response unless the user explicitly asks you to.</local-command-caveat>"}, {"role": "user", "content": "<command-nam...	178
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::110	[{"role": "user", "content": "Implement the following plan:\n\n# Consolidate Full Plugin Code with Generic Framework\n\n## Context\n\nThe generic plugin framework (`generic.py`) now provides a rich set of tree-sitter-powered detectors (AST smells, complexity signals, god class detection, cohesion, unused imports, signa...	158
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::111	[{"role": "user", "content": "Can you look into this feedback? What's the best way to run multiple directies? RyanOnTheInside — 19:58\nstand by let me run it on somethign vibier\nwhat would be sick for this is to be able to do per module/subdirectory score, for teams with different responsibilities, and also git ignore...	52
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::112	[{"role": "user", "content": "Implement the following plan:\n\n# Merge `_shared/` into `framework/` in `desloppify/languages/`\n\n## Context\n\nThe `languages/` directory has two infrastructure directories (`_shared/` and `framework/`) alongside ~31 language plugin directories. `_shared` depends on `framework` and `fra...	92
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::113	[{"role": "user", "content": "Can you look through the latest issue and try to understand if there's a good solution to it? Be really in depth. We obviously don't have a Windows machine. But is there a way to understand this in a way that will help solve it for everyone?"}, {"role": "assistant", "content": "Let me also...	65
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::114	[{"role": "user", "content": "[Request interrupted by user for tool use]"}, {"role": "user", "content": "Implement the following plan:\n\n# Make Subjective Review a First-Class Detector+Fixer\n\n## Context\n\nDesloppify has two workflows: scan (find problems) and fix (resolve them). A `review_coverage` detector...	49
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::115	[{"role": "user", "content": "<local-command-caveat>Caveat: The messages below were generated by the user while running local commands. DO NOT respond to these messages or otherwise consider them in your response unless the user explicitly asks you to.</local-command-caveat>"}, {"role": "user", "content": "<command-nam...	106
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::116	[{"role": "user", "content": "<local-command-caveat>Caveat: The messages below were generated by the user while running local commands. DO NOT respond to these messages or otherwise consider them in your response unless the user explicitly asks you to.</local-command-caveat>"}, {"role": "user", "content": "<command-nam...	16
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::117	[{"role": "user", "content": "[Request interrupted by user for tool use]"}, {"role": "user", "content": "Implement the following plan:\n\n# Assessment-Based Review Scoring\n\n## Context\n\nReview findings currently work like other detectors: each finding is a weighted failure counted against the \"Design quality\" dime...	77
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::118	[{"role": "user", "content": "[Request interrupted by user for tool use]"}, {"role": "user", "content": "Implement the following plan:\n\n# Per-Issue Documents: Replace Monolithic Plan with Individual Work Orders\n\n## Context\n\nThe holistic review currently produces one big `holistic-plan.md` containing all findings....	72
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::119	[{"role": "user", "content": "[Request interrupted by user for tool use]"}, {"role": "user", "content": "Implement the following plan:\n\n# `desloppify issues` — State-Backed Work Queue for Review Findings\n\n## Context\n\nReview findings (subjective, from `review --import`) are already in `state[\"findings\"]` with ri...	158
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::120	[{"role": "user", "content": "see scorecard.png, the layout of it looks weird now, can you try to understand what's happening with it, the spacing feels uneven "}, {"role": "assistant", "content": "Let me look at the scorecard image and the code that generates it."}, {"role": "assistant", "content": "I can see the issu...	37
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::121	[{"role": "user", "content": "do we communicate the requirements well?"}, {"role": "assistant", "content": "Let me look at the key documentation to assess how well requirements are communicated."}, {"role": "assistant", "content": "Good question. Here's my honest assessment after reading the README, SKILL.md, and CLAUD...	9
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::122	[{"role": "user", "content": "What's our desloppify score now? How can we improve it? Run using this repo"}, {"role": "user", "content": "Base directory for this skill: /user_c042661f/Documents/desloppify/.claude/skills/desloppify\n\n# Desloppify\n\n## 1. Your Job\n\nGet strict scores as high as possible. After eve...	482
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::123	[{"role": "user", "content": "[Request interrupted by user for tool use]"}, {"role": "user", "content": "Implement the following plan:\n\n# Integrate Subjective Review into Scan Pipeline (#55, #56, #57)\n\n## Context\n\nThree related issues for the review system:\n- #55: Review is disconnected from scan — codebase ...	88
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::124	[{"role": "user", "content": "[Request interrupted by user for tool use]"}, {"role": "user", "content": "Implement the following plan:\n\n# Comprehensive Codebase Remediation Plan\n\n## Context\n\nA deep subjective analysis of the desloppify codebase identified 10 systemic issues — the kind of design-level problems tha...	200
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::125	[{"role": "user", "content": "Implement the following plan:\n\n# Beautify RuntimeContext: Remove Unnecessary Wrappers\n\n## Context\nThe old `_extra_exclusions` global was refactored into a `RuntimeContext` dataclass with `ContextVar` scoping — a solid architecture. But the refactor left behind unnecessary wrapper clas...	51
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::126	[{"role": "user", "content": "How do we fix this? ' - Global mutable state (_extra_exclusions) requiring module-level import tricks is an acknowledged wart.\n"}, {"role": "assistant", "content": "Let me look at the current state of this issue."}, {"role": "assistant", "content": "Good news — it looks like this was alr...	13
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::127	[{"role": "user", "content": "[Request interrupted by user for tool use]"}, {"role": "user", "content": "Implement the following plan:\n\n# Rework: `desloppify issues` as the Work Queue Command\n\n## Context\n\nThe first implementation created issue docs as a side effect of `review --import`. Testing it end-to-end reve...	25
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::128	[{"role": "user", "content": "can you see the prompts we give to agents based on results from scans? Can you figure out when it makes sense to nudge them towards deploying multple agents? And when to nudge them towards using fixers that we have? No code yet, just think it through"}, {"role": "assistant", "content": "Le...	14
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::129	[{"role": "user", "content": "<local-command-caveat>Caveat: The messages below were generated by the user while running local commands. DO NOT respond to these messages or otherwise consider them in your response unless the user explicitly asks you to.</local-command-caveat>"}, {"role": "user", "content": "<command-nam...	12
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::130	[{"role": "user", "content": "[Request interrupted by user for tool use]"}, {"role": "user", "content": "Implement the following plan:\n\n# Fix 6 Test Coverage Detector Issues (#42–#47)\n\n## Context\n\nAll 6 open issues (excluding #38 which has comments) target `desloppify/detectors/test_coverage.py`. They fall into t...	35
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::131	[{"role": "user", "content": "❯ can you fix the scorecard.png github issue taht was just filed? Pick X numebr of great dimensions for typescript similar to what w have for python. And then make sure that this is done ina streamlined way in the codebase"}, {"role": "assistant", "content": "Let me start by looking at the...	9
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::132	[{"role": "user", "content": "Implement the following plan:\n\n# Plan: Fix 5 Elegance Wontfix Items (Strict Score +3.3 pts)\n\n## Context\nStrict score is 90.4/100. The \"Elegance\" scorecard dimension is 83.3% strict, caused by 5 wontfix `review` findings across High/Mid/Low Elegance. Each wontfix finding costs 10% on...	100
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::133	[{"role": "user", "content": "<local-command-caveat>Caveat: The messages below were generated by the user while running local commands. DO NOT respond to these messages or otherwise consider them in your response unless the user explicitly asks you to.</local-command-caveat>"}, {"role": "user", "content": "<command-nam...	303
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::134	[{"role": "user", "content": "Implement the following plan:\n\n# Consolidate per-file/holistic dimension constants\n\n## Context\n`dimensions/file.py` and `dimensions/holistic.py` both call `load_dimensions()` on the same `dimensions.json` — producing identical data under different names. This creates two sets of const...	66
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::135	[{"role": "user", "content": "Implement the following plan:\n\n# Plan: Fix Concern Lifecycle Gaps & Consolidate Judgment Split\n\n## Context\n\nThe concerns pipeline (mechanical → subjective bridge) works end-to-end but has 6 lifecycle gaps and a design smell. Dismissals don't stick (missing `source_finding_ids`), conf...	90
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::136	[{"role": "user", "content": "Implement the following plan:\n\n# Make Generic Language Plugins Fully Functional\n\n## Context\n\nWe already have 22 generic language plugins (go, rust, ruby, swift, etc.) that run external tools and produce findings. But these findings are dead weight — they exist in state but don't ...	91
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::137	[{"role": "user", "content": "[Request interrupted by user for tool use]"}, {"role": "user", "content": "Implement the following plan:\n\n# Plan: Execution Strategy for Narrative System\n\n## Context\n\nThe narrative system tells agents what to fix (prioritized action list) but not how to approach the work. Two...	50
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::138	[{"role": "user", "content": "[Request interrupted by user for tool use]"}, {"role": "user", "content": "Implement the following plan:\n\n# Plan: Fix All E2E-Discovered Issues\n\n## Context\nSix independent E2E test agents evaluated desloppify's UX. They found 3 bugs, 3 major UX gaps, and several polish issues. This pl...	75
misterkerns/my-personal-claude-code-data	misterkerns/my-personal-claude-code-data::139	[{"role": "user", "content": "[Request interrupted by user for tool use]"}, {"role": "user", "content": "Implement the following plan:\n\n# Plan: Complete Zone Classification System\n\n## Context\n\nThe initial zone implementation (zones.py, zone stamps, scoring exclusion, TS line classifier) is working but has three g...	146