loc-guardian-loc-optimizationShrinking files over the pure LOC limit: config format, extraction patterns.loc-guardian-locLOC counting with tokei: metrics, limits, reading and checking loc-guardian reports.loc-optimizationShrinking files over the pure LOC limit: config format, extraction patterns.locLOC counting with tokei: metrics, per-file limits, report formats.loc-guardian-counterCount lines of code and produce the loc-guardian LOC report with per-file limit enforcement, for all languages or one (e.g. python). The counting step of $loc-guardian-scan. Not for suggesting how to shrink over-limit files; that is $loc-guardian-optimizer.loc-guardian-initInitialize loc-guardian for this project — set the per-file pure-LOC limit and project-specific extraction rules in .claude/loc-guardian.local.md.loc-guardian-optimizerAnalyze files over the pure-LOC limit and propose concrete extractions with measured line savings; given only warning-zone (WARN) files, a lighter pass with one candidate per file. Consumes a $loc-guardian-counter report. Not for counting lines (use…loc-guardian-scanCount pure LOC, enforce per-file limits, and get measured optimization strategies for over-limit files. Optional arguments: a language (e.g. typescript) and paths. Entry point for loc-guardian in Codex.
repository explorer
xiaolai · Repositories and representative skills - Page 2
Repository-level view of 285 collected skills across 26 GitHub repositories.
common-non-native-mistakesRecurring error patterns from non-native English speakers in developer contexts: article misuse, preposition confusion, tense mismatch, 'I am agree'-style anti-patterns, and other frequent L2 slips. Use when scanning for patterns a reader can map back to…grammar-fundamentalsCore English grammar rules most likely to trip non-native developers: articles, subject-verb agreement, tense consistency, prepositions, countable vs mass nouns, comparatives. Use when reviewing grammar correctness of prose written for developer contexts…punctuation-rulesPunctuation conventions for developer prose: commas (serial, Oxford, clause-joining), semicolons, colons, hyphens vs en-dashes vs em-dashes, apostrophes, quotation marks. Use when reviewing punctuation of documentation, commit messages, or any prose where…technical-writingTechnical writing patterns for developer prose: API documentation structure, README shape, error-message wording, terminology consistency, and the active vs passive voice trade-off. Use when the text under review is documentation, a README, an API reference,…tone-calibrationPer-context tone rubrics for developer communication: commit messages, PR descriptions, code comments, API docs, emails, inline chat. Use when judging whether the register and formality of a piece of text fit its destination, not just whether it is…writing-guideMeta-skill that routes to the five focused writing skills in this plugin. Loads nothing substantive on its own — read this to decide which of grammar-fundamentals, punctuation-rules, tone-calibration, technical-writing, or common-non-native-mistakes to…
guideOrientation for the bureau plugin — the records-office model, the capture → compile → review gate, the trust tiers, the crew, and which bureau: command serves which intent. Read this FIRST before using any bureau: command, or whenever working in a repo that…recallAnswer from the bureau canon with citations and trust tiers — read dossiers as memory, honor each page's status, and never present an unverified claim as fact. Use when running bureau:query, or when the user asks what the project knows / what was decided /…scribeThe live note-taker — summarize the current session's decisions and open threads on demand or at checkpoints, and (in a bureau workspace) append them to the session's running minute. Use when running bureau:note, or when the user asks to take a note / minute…captureWrite a faithful, append-only minute for an AI session — intent, decisions, changed files, open threads, and a transcript pointer. Use when filing a session into a bureau workspace (e.g. via bureau:file-session), or when the user asks to record/minute the…
xros-runExecute an XROS methodology spec — run a CDC-style search (diverse independent routes, blocked-route state, adversarial refutation, counterexample-fed loop-until-dry), then authoritatively verify the winning candidate by running its oracle command and gating…xros-compileCompile an XROS methodology spec through an oracle-first interview. Classifies the problem into verification tier A/B/C before anything else, then fills and validates a schema-valid JSON spec.xros-reasonThe Tier-C path — structured, adversarial reasoning for a claim that has NO mechanical check. Decomposes the claim into premises and verifies the checkable ones, runs a pre-mortem, and emits dated tripwires. Never runs the CDC engine, never claims a verified…xros-sharpenOrient a newcomer in an unfamiliar field, sharpen a vague question into a falsifiable claim, then discover the currently best-available way to check it. For when the user can't yet say "how would I know if this were wrong?". First maps the field's minimal…
experience-synthesisThis skill should be used when the user asks to "learn from past sessions", "extract lessons", "find what worked", "identify patterns in my workflow", "what mistakes did I make", "what decisions were made", or wants to synthesize wisdom and actionable…memory-managementUse when auditing, extracting, pruning, or writing Claude Code memory files. Covers memory file format, MEMORY.md index conventions, staleness scoring, claim extraction heuristics, destination routing, mutation rules, and archive conventions.git-miningThis skill should be used when the user asks to "check git history", "trace code changes", "find when something was added", "correlate commits with sessions", "find hotspot files", or needs to mine git repository history for insights. Only applicable when the…jsonl-coreThis skill should be used when the user asks to "analyze conversation history", "parse JSONL files", "read past sessions", "search conversation logs", "find what happened in a session", or needs to work with Claude Code's .jsonl conversation format. It…
escalate-maxRaises effort to max for this turn. Invoke it FIRST when a mistake would be costly or a problem already resisted an attempt - security-sensitive code (authentication, authorization, cryptography, secrets, payments); destructive operations on production data;…escalate-xhighRaises effort to xhigh for this turn. Invoke it FIRST, before reading files, for genuinely hard work - a costly-to-reverse design, architecture, data-model or API decision; debugging a non-obvious cause (concurrency, caching, timing); a multi-file refactor or…reportReports how compute-ladder has been escalating effort - escalation rate, output tokens per effort tier, escalations that did not take effect, and turns that look under- or over-escalated. Use when the user asks how compute-ladder's routing is performing or…
auditIndependently audit a local change or plan with Codex, using a fresh native auditor or an explicitly selected read-only Codex process with pinned model and reasoning effort.initSet up or refresh dev-team in a local Git repository, installing seven Codex agents with explicit models and drafting a reviewed repository profile.runBuild a feature or fix with separate Codex planner, tester, coder, and auditor contexts, a repository profile, tests-first gates, and bounded correction rounds.