BryceEWatson

gemini-image

Generate and edit images with Google's Gemini models (Nano Banana / Gemini 3 Pro Image / 3.1 Flash Image) from a zero-dependency Python CLI. Use whenever the user wants to create, generate, edit, restyle, or compose an image with Gemini / Google AI; produce listing photos, mockups, banners, icons, or marketing visuals via Gemini; or attach reference images for image-to-image editing. Also handles text/conversation/model-listing — it is the maintained successor to the older `gemini-client` plugin. Triggers: "generate an image with Gemini", "use Google AI to make a picture", "Gemini image", "nano banana", "edit this image with Gemini", "Imagen".

global-review-loop

Mine ALL of your local Claude history across EVERY project (both corpora — Claude Code CLI and Cowork local-agent-mode) for operator friction that recurs across MULTIPLE projects, then propose GLOBAL ~/.claude leverage (a CLAUDE.md rule, a new/edited global skill, a memory, or a settings hook) to fix it — each proposal reconciled against what already ships globally, self-validated by an adversarial /review-loop --mode claim loop, and recorded in a cross-run ledger so nothing is re-proposed, dismissed-twice, or shipped on its own say-so. DISTINCT FROM: signal-scan (one repo → that repo's .claude/ config), command-retro (Command's own logs → Command's queue), and transcript-analysis (ONE project, Cowork-only, proposes that project's CLAUDE.md candidates). This skill is the GLOBAL, cross-project layer: it only surfaces friction proven to recur across >=N DISTINCT projects (counted by cwd-PATH attribution only) and only ever proposes changes to ~/.claude. Invoke as /global-review-loop. Triggers: "what global rule

pattern-retrospective

Apply rigorous pattern-retrospective analysis to Claude transcripts. Triggers on writing studies, blog posts, handoff docs, retrospectives, specs, or improvement proposals that draw conclusions from past Claude sessions — phrasings like "handoff to X", "lessons from session Y", "pattern Z over time", "spec for X", "improvements to X", "audit my use of W" all match. Enforces target-system audit BEFORE specifying its requirements, streaming JSONL parsing (never load whole files), 5-tuple extraction with provenance tags, self-falsification of every cited claim including system-state claims, Bayesian confidence smoothing, and correlation-not-causation discipline. Designed to prevent the credulous-handoff failure mode where ~60% of proposed requirements turn out to already exist in the target system.

Code & Development Listed

review-loop

Dispatches a multi-agent review team over the work in this session, runs an execution-grounded check (lint/test/build), validates findings through a falsifier stage, addresses load-bearing issues, and re-reviews until clean or budget hits. On the terminal verdict, always records a commit-pinned verdict comment on the branch's open PR (if one exists), so the review leaves a trail. Invoked manually as /review-loop or automatically by the Stop hook after real work outside plan mode. Use `--mode claim` to review a non-code analytical conclusion (a research finding or comparison verdict) by sending reviewers back to its primary sources to falsify it.

session-pickup

Start a continued Claude Code session by safely rehydrating from a prior session's handoff — the inverse of session-end. Finds the latest handoff in .claude/handoffs/, reads it + the docs it points to (tiered, not everything), RECONCILES it against current git/file state to catch anything that drifted since it was written, rebuilds the todo list + the settled constraints + open verification debts, then presents where you are + the immediate next action and confirms before acting. Invoke at the start of a session that continues prior work.

transcript-analysis

Analyze Cowork session transcripts for recurring narrative patterns — repeated instructions, planning loops, failure patterns, decision re-litigation, and knowledge re-establishment. Produces a structured report with CLAUDE.md candidates, unresolved loops, and pattern frequency data. Use this skill when the user wants to review what keeps repeating across sessions, extract lessons from past work, audit their collaboration patterns, or identify rules that should be encoded permanently. Triggers on: transcript analysis, session analysis, narrative analysis, what keeps repeating, review our sessions, cowork analysis, pattern analysis, what should go in CLAUDE.md, extract lessons, session retrospective, retro, session patterns.

weekly-work-log

Build and refresh the brycewatson.com "Weekly Work Log" report page (/report, archived under /log) for the last completed week. Discovers the week's work from session-end handoffs + git, distils it into honest public-voice items, re-derives and verifies every number, and (unattended, every Sunday night) opens a review PR. Never publishes unattended.

chat-arch-thrash-detect

Calibration-gated PostToolUse hook that watches the rolling window of tool calls in a Claude Code session and emits a stderr nudge when it detects an Edit-thrash, Read-loop, Test-loop, or Tool-flail pattern. NOT a user-invokable skill — the directory exists to host the hook script + install/uninstall machinery alongside the rest of the chat-arch skill family. Gated behind `CHATARCH_THRASH_DETECT=1` for the 4-week calibration window (plan §Phase 4 #8).

chat-history-search

Exhaustive search across ALL of your local Claude chat history — Cowork (Claude Desktop local-agent-mode) AND Claude Code CLI — to find user prompts, recover past conversations, inventory how often a pattern was used, or audit prior work. Knows every log location, every JSONL line shape, and the false-positive gotchas (task-notification wrappers, TodoWrite items, tool_result content, audit-log duplicates) that trip up naive grep. Use when the user asks to find all uses of X, when they last said Y, inventory prompts about Z, recover a conversation, or audit their sessions across projects.

seo-index-validation

Validate whether a DEPLOYED site is being crawled and indexed correctly, and diagnose plus fix why pages are not indexed. Use when a Google Search Console alert email arrives ("New reason preventing your pages from being indexed", "Not found (404)", "Page with redirect", "Discovered / currently not indexed", "Crawled / currently not indexed", "Soft 404"), when checking index health after a deploy, migration, or domain change, when a page will not appear in Google, or to confirm a prior indexing fix actually cleared in Search Console. It probes live HTTP (status codes, redirects, soft-404, canonical tags, sitemap) with curl, reads the GSC report via the browser, fixes at the correct layer (CDN or host setting, _redirects, a 404 page) under confirmation-gating, then schedules a lagged re-check. NOT for keyword research, content optimization, or backlinks. Triggers include "Search Console", "GSC", "not indexed", "404 in Search Console", "page with redirect", "soft 404", "validate indexing", "validate SEO", "why

session-handoff

Alias of `session-end` (this skill was renamed). Ending / closing out a session — and handing it off when work is mid-flight — now lives in session-end; "handoff" is its mid-flight mode. Invoking this just routes to session-end so old muscle memory ("/session-handoff") keeps working.