{
  "markdown": "# lchase\n\nLawrence Chase's Claude Code marketplace: code review and diagram tools for Claude Code\nand other coding agents.\n\n```\n/plugin marketplace add lchase/skills\n/plugin install smart-review@lchase\n/plugin install tldraw@lchase\n```\n\nEach plugin is independent; install only what you want. `@lchase` is the marketplace name\n(from `.claude-plugin/marketplace.json`), not the GitHub slug.\n\n### Updating\n\nNew versions ship whenever the `version` string in a plugin's manifest changes. Claude Code\n**refreshes marketplaces in the background by default**, so you normally pick up updates\nwithout doing anything. To pull them right now:\n\n```\n/plugin marketplace update lchase      # refresh this marketplace's manifest\n/plugin update smart-review@lchase     # apply a pending update to one plugin\n/plugin update tldraw@lchase\n```\n\n`/plugin marketplace update` (no name) refreshes every marketplace. From a shell:\n`claude plugin marketplace update lchase` and `claude plugin update <plugin>@lchase`.\n\n### Reinstalling\n\nIf a plugin gets into a bad state (stale cached script, half-applied update), do a clean\nreinstall:\n\n```\n/plugin uninstall tldraw\n/plugin marketplace update lchase\n/plugin install tldraw@lchase\n```\n\nNuclear option, re-register the whole marketplace:\n\n```\n/plugin marketplace remove lchase\n/plugin marketplace add lchase/skills\n/plugin install smart-review@lchase\n/plugin install tldraw@lchase\n```\n\n### Migrating from the old layout\n\nBefore this repo became a multi-plugin marketplace it published one plugin from the repo\nroot under a marketplace named `chase`. If you installed it back then, clear the old\nregistration first:\n\n```\n/plugin uninstall smart-review\n/plugin uninstall tldraw            # only if you installed the short-lived tldraw@chase\n/plugin marketplace remove chase\n/plugin marketplace add lchase/skills\n/plugin install smart-review@lchase\n/plugin install tldraw@lchase\n```\n\nThe tldraw skill's command also changed: `/tldraw:tldraw` → **`/tldraw:diagram`**.\n\n| Plugin | What it does | Skills / commands | Harnesses |\n|---|---|---|---|\n| [**smart-review**](plugins/smart-review/) | Ensemble code review: six specialized lenses over a diff, merged into one deduplicated, severity-ranked verdict | `/smart-review:{review,min,max,add-pr-review,review-pr-comments}` + auto-trigger | Claude Code, Cursor, Codex, Gemini CLI, any AGENTS.md agent |\n| [**tldraw**](plugins/tldraw/) | Natural-language description → editable tldraw document (`.tldr`) + rendered PNG/SVG | `/tldraw:diagram` + auto-trigger | Claude Code only (needs Node + `npx`) |\n\n---\n\n## smart-review\n\n*An ensemble code review: several specialized lenses, one merged verdict, not another pile\nof comments.*\n\nMost code review, human or AI, is one reviewer making a single pass and leaving a list of\ncomments. This runs six specialized lenses instead (spec-conformance, correctness,\nsecurity, performance, design, and tests), then merges the results into one verdict:\nduplicates collapsed, findings that several lenses independently raise weighted up,\nconflicting advice reconciled, severity rolled up, structural problems first, nits capped.\nThe merge is the point. An ensemble without it is just louder, and a longer checklist\nhanded to one reviewer only dilutes its attention and repeats its own misses.\n\nTwo modes: a fast single pass (`min`) for tight loops, and an orchestrated ensemble (`max`)\nfor pre-merge review. Auto-routing picks between them by change size and sensitivity.\n\nThe skill lives in [`plugins/smart-review/skills/smart-review/`](plugins/smart-review/skills/smart-review/)\nas harness-neutral markdown. Each harness gets a thin manifest pointing at that same\ndirectory, so no skill content is copied or forked.\n\n| Harness | Install | `min` | `max` | Slash commands / auto-trigger |\n|---|---|---|---|---|\n| Claude Code | `/plugin marketplace add lchase/skills` then `/plugin install smart-review@lchase` | ✅ | ✅ isolated parallel subagents | ✅ |\n| Cursor | point Cursor at `plugins/smart-review/.cursor-plugin/` | ✅ | ✅ sequential ensemble | via session-start hook |\n| Codex | `plugins/smart-review/.codex-plugin/` manifest | ✅ | ✅ sequential ensemble | no |\n| Gemini CLI | `gemini extensions install https://github.com/lchase/skills` (reads root `gemini-extension.json`) | ✅ | ✅ sequential ensemble | via `GEMINI.md` |\n| Any AGENTS.md agent | reads root [`AGENTS.md`](AGENTS.md) | ✅ | ✅ sequential ensemble | no |\n\n`max`'s isolated parallel subagents (and optional cross-model routing) are a Claude Code\ncapability. Elsewhere `max` runs the same spec-gate + six lenses + merge as a disciplined\nsequential walk. Design and internals: [`plugins/smart-review/SMART-REVIEW.md`](plugins/smart-review/SMART-REVIEW.md).\n\n**Claude Code slash commands:**\n\n- `/smart-review:review`: auto (routes to min or max by size + sensitivity)\n- `/smart-review:min`: fast single-pass review\n- `/smart-review:max`: orchestrated ensemble review\n- `/smart-review:add-pr-review <PR number or URL>`: reviews a GitHub PR and, after you confirm what to publish, posts the findings as PR comments\n- `/smart-review:review-pr-comments <PR number or URL>`: triages a PR's existing unresolved review comments, fixes or explains each after your approval, replies, and resolves the thread\n\nThe skill also triggers automatically when you ask Claude to review a diff, PR, or branch.\n\n---\n\n## tldraw\n\nTurn a described diagram (flowchart, architecture / system diagram, process map, decision\ntree, state machine) into two artifacts: an **editable `.tldr` document** (opens at\ntldraw.com or in the tldraw editor) and a **rendered PNG/SVG** for docs and PRs.\n\nClaude writes a `{nodes, edges}` spec from your description; a bundled Node script does a\nsimple layered auto-layout, emits the `.tldr`, and renders images by loading it into a\nheadless-Chromium tldraw instance via [`@kitschpatrol/tldraw-cli`](https://github.com/kitschpatrol/tldraw-cli)\n(first run downloads Chromium, ~1 min, cached).\n\n```\n/plugin install tldraw@lchase\n```\n\nClaude Code only. Skill: `/tldraw:diagram` (also auto-triggers on \"draw this diagram\",\n\"diagram this flow\", \"make a tldraw of…\"). Details:\n[`plugins/tldraw/skills/diagram/SKILL.md`](plugins/tldraw/skills/diagram/SKILL.md).\n\n---\n\n## Repo layout\n\n```\n.claude-plugin/marketplace.json   # the \"lchase\" marketplace: 2 plugin entries\nAGENTS.md                         # repo-level agent pointer (→ smart-review)\ngemini-extension.json + GEMINI.md # Gemini CLI installs the repo as an extension (→ smart-review)\n\nplugins/smart-review/             # plugin 1, multi-harness code review\n  .claude-plugin/plugin.json\n  skills/smart-review/            # the harness-neutral core (SKILL.md + references/)\n  agents/ commands/ hooks/        # Claude Code packaging\n  .cursor-plugin/ .codex-plugin/  # thin per-harness manifests\n  scripts/                        # validate-adapters.sh, bump-version.sh\n  evals/                          # dev-only eval kit (not shipped to installers)\n  SMART-REVIEW.md                 # design writeup\n\nplugins/tldraw/                   # plugin 2, Claude Code only\n  .claude-plugin/plugin.json\n  skills/diagram/                 # SKILL.md + scripts/build-tldr.mjs + references/\n```\n\n## Developing\n\n```\nclaude plugin validate .                                # marketplace + both plugins\n./plugins/smart-review/scripts/validate-adapters.sh      # smart-review's per-harness manifests\n```\n\n**Releasing:** users only get an update when a plugin's `version` string changes, so bump\nit on every user-facing change and push to `main`.\n\n- smart-review: version is pinned across all its manifests; bump them together with\n  `./plugins/smart-review/scripts/bump-version.sh <version>`.\n- tldraw: versions independently; edit `plugins/tldraw/.claude-plugin/plugin.json`.\n\nOnce pushed, installed clients pick it up on their next background marketplace refresh, or\nimmediately with `/plugin marketplace update lchase`.\n",
  "bytes": 7930,
  "sha": "e77688d7d94f835ca64ca18d54f98846d3406f2819dbf2a84b36b29ed90aaeda",
  "repo_slug": "lchase/skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_lchase_skills_e605440d/readme"
}