claude-skills

Convene the 18-member Council of High Intelligence — simulate multi-persona deliberation from Aristotle, Feynman, Torvalds, Taleb, Kahneman, and 13 others, then synthesize into ONE verdict. Use when facing hard decisions, design tradeoffs, strategy questions, or when you want diverse adversarial perspectives on a problem. Trigger on "/council", "ask the council", "what would the council say", "multi-perspective analysis". Supports --quick (fast), --duo (dialectic pair), --triad <domain>, --full (all 18), --members a,b,c.

Finds viable product, business, or project ideas in any domain by generating candidates, rigorously validating each against real competitors and market data, and killing weak ideas with documented reasons. Two modes — fast batch generate-and-kill (default), or `--deep` DFS that branches a single space into opportunity tuples with codex cross-attack, mandatory steelman, and a VC-gauntlet fundability gate. Use when the user asks to brainstorm ideas, find market gaps, identify business opportunities, figure out what to build, come up with side project ideas, find underserved niches, or (with --deep) "find the real opportunities in X", "exhaustively explore X", "keep digging until you exhaust X". Works for SaaS, open source, MCP servers, apps, tools, APIs, or any product category.

Stress-test a startup/product proposal like a top-tier VC partner meeting — reality-checked against real market data, with an independent codex devil's-advocate bear case — then iterate hardened rewrites to a GO / CONDITIONAL-GO / NO-GO verdict. Use when the user says "vc review", "is this fundable", "would a VC fund this", "tear apart my startup idea", "pitch critique", "investor lens", "gauntlet this", "red-team my startup", "poke holes in my idea". Also the fundability gate invoked by opportunity-dfs §8.

The single entry point for ALL design and specification work. Use when designing, specifying, architecting, writing a spec, RFC, design doc, or drafting a design for any system, feature, product, protocol, game, or workflow. Trigger phrases include "design this", "architect this", "design spec", "design review", "write a spec", "technical spec", "RFC", "API design", "data model", and "implementation spec". Default mode: adversarial stress-testing with parallel critics. Use `--spec` for lightweight single-session spec document generation without critics.

Use when researching, investigating, or exploring a topic systematically with orthogonal multi-dimensional coverage and source-quality tiers. Trigger phrases include "research this deeply", "deep research on", "investigate this topic thoroughly", "explore this topic", "systematic research", "multi-dimensional research", "comprehensive research", "cover all angles of", "thorough research on", "deep dive into (research)", "exhaustive research". Spawns parallel agents across WHO/WHAT/HOW/WHERE/WHEN/WHY/LIMITS with risk-stratified spot-checking. Bounded by a user-controlled round budget with honest coverage reporting on what was and wasn't covered.

Use when the user says "autopilot", "build this", "make it", "ship it", "just do it", "do it", "implement this", or gives a vague idea, spec, task list, or bug fix and expects autonomous execution. Handles decomposition, agent coordination, and verification automatically. "build me end to end", "go from idea to code", "do everything", "run this autonomously". Follows the Spec-Driven Development workflow: specify → clarify → plan → tasks → analyze → implement.

Use before touching code for any multi-step task — features, refactors, migrations, architectural decisions, bug fixes, or any work that needs to be broken into verifiable steps. Trigger phrases include "write a plan", "implementation plan", "plan this", "plan the work", "break this down", "how should I approach this", "make a plan", "design the approach", "before I code this", "I need a plan", "write up the plan", "spec to plan", "requirements to plan". Produces SDD-compatible plan.md, research.md, data-model.md, contracts/, and tasks.md via a Planner → Architect → Critic consensus loop.

DEPRECATED — use `deep-design --spec` instead. Turns a conversation, idea, or discussion into an SDD-compatible spec.md. Use when the user asks to write a spec, technical spec, design doc, RFC, API design, data model, spec this out, turn this into a spec, write up the design, document this, implementation spec, spec for this feature.

Use when reviewing, auditing, QAing, critiquing, verifying, or assessing any artifact — a spec, code change, diff, PR, research report, skill, prompt, or document. Also use for pre-completion verification ("verify this works", "prove this is done", "evidence before claiming complete"). Trigger phrases include "review this", "audit this", "QA this", "find issues", "find defects", "critique this", "check this for problems", "what's wrong with this", "evaluate this", "run QA", "review the diff", "review the PR", "review my code", "deep QA", "defect audit", "code review", "assess this", "verify this works", "verify before completing", "prove this is done", "is this actually working". The single skill for all quality assurance — adversarial review, pre-completion verification, and evidence gathering. Cross-model critic lanes (GPT/Gemini via OpenAI-compatible endpoint) are enabled by default for blind-spot diversity; disable with --no-cross-model.

Session retrospective that scans the current conversation for agent failures, user corrections, and alignment gaps, then proposes patches to CLAUDE.md or skills. Use when: after a difficult session, after repeated corrections, to improve agent behavior, to analyze what went wrong, to close the learning loop after autopilot/fix-pr. Trigger phrases: "retrospect", "what went wrong", "session retro", "learn from this", "what should we improve", "session review", "capture learnings", "post-mortem this session".

Search across all installed skills (user + plugin) by keyword to discover relevant skills whose descriptions may have been truncated from the main listing. Use when the user references a skill by partial/fuzzy name, asks "is there a skill for X?", or when the main skill listing seems incomplete. Trigger phrases include "find a skill", "is there a skill for", "search skills", "what skill does X", "find skill", "skill search", "look for a skill", "any skill that handles".

Renders interactive charts in the browser using Chart.js. Use when the user wants to visualize data, plot numbers, draw a bar chart, line chart, pie chart, doughnut chart, radar chart, graph metrics, compare benchmarks, show a cost curve, or display a time series. Always renders live in browser — never as a static image.

The single entry point for ALL debugging — bugs, test failures, CI failures, Metaflow run failures, Jenkins build failures, or any unexpected behavior. Trigger phrases include "debug this", "why is this failing", "find the bug", "fix the bug", "root cause", "what's wrong with", "this is broken", "diagnose", "troubleshoot", "investigate this failure", "the test is failing", "this used to work", "why doesn't this work", "where's the bug", "CI failed", "PR is red", "why did my flow fail", "build failed", "Jenkins failure". Composes specialized sub-skills internally (debug-pr for CI, debug-run for Metaflow, debug-jenkins for builds) — the agent always enters through deep-debug, never routes to sub-skills directly.

Renders interactive diagrams in the browser using Cytoscape.js. Use when the user asks to visualize, diagram, draw, render, or show a graph, flowchart, dependency tree, roadmap, architecture diagram, or any node-and-edge structure. Always renders live in browser — never as a static image.

The single loop skill for ALL recurring and drive-to-completion work. Subsumes the built-in loop (periodic polling), ralph (iterative completion with verification), and loop-until-done (PRD-driven execution). Durable Temporal-backed — survives session crashes. Trigger phrases include "loop", "loop until done", "keep trying", "fix until", "until X passes", "check every N minutes", "keep checking", "poll for", "don't stop until", "ralph", "persist until done", "sagaflow loop", "durable loop".

Turns bullet points, research, or structured content into a browser-based Reveal.js slide deck. Use when the user asks to create slides, a presentation, a deck, a slideshow, or says "present this", "turn this into slides", "make a deck", or mentions keynote, powerpoint, or reveal.

Renders interactive sortable, filterable tables in the browser using pure vanilla HTML/CSS/JS — no external dependencies. Use when the user wants to compare alternatives, show a feature matrix, display structured data, create a comparison table, render a sortable table, show options side-by-side, or visualize rows and columns of data. Always renders live in browser — never as static text.

Use when coordinating multiple agents on a staged pipeline — plan → PRD → exec → verify → fix — via a durable Temporal-backed workflow that survives session crashes. Trigger phrases include "team temporal", "sagaflow team", "durable team", "temporal-backed agent team". File-based state, independent critic/verifier gates, two-stage review on every source modification, honest termination labels. Fire-and-forget while you do other work.

Renders interactive Gantt-style project timelines and roadmaps in the browser using vis-timeline. Use when the user mentions timeline, gantt, roadmap, project plan, phases, milestones, schedule, sprints, quarters, or asks when things happen or to show a schedule. Writes /tmp/timeline.html and opens it via Chrome DevTools MCP.

Use when the user asks to monitor, health-check, watch, or check status of services, pipelines, code, teams, builds, deployments, or CI. Also triggers for "is X healthy", "check on Y", "watch Z". Runs one-shot or recurring, parameterized by data source.

Fans out 4 parallel prompt-clash defend agents at staggered time budgets (1min, 2min, 3min, 4min), then ensembles/synthesizes the best elements of each into a single hardened prompt. Use when the user wants the strongest possible defense prompt and has ~5 minutes. Trigger phrases include "prompt clash ensemble", "ensemble defense", "fan out prompt clash", "best defense possible", "ensemble prompt", "multi-budget defense".

All-in-one prompt engineering competition toolkit — attack generation, defense hardening, real-time analysis, and pattern reference for AI security tournaments like Clash of Prompts. Use when preparing for or competing in prompt engineering competitions, red-teaming LLMs, hardening system prompts, analyzing prompt injection techniques, or practicing timed prompt challenges. Trigger phrases include "prompt clash", "prompt competition", "prompt tournament", "red team this prompt", "harden this prompt", "attack this prompt", "defend this prompt", "prompt injection", "prompt security", "clash of prompts", "prompt challenge", "prompt battle".

Crash-recovery test for the sagaflow generic interpreter. Multiple sequential tool calls with a sleep in the middle.

Smoke test for the sagaflow generic interpreter. Writes a greeting to report.md and ends turn. Use only for testing the interpreter round-trip.

Review a PR against the top 20 Tier 2 LLM-enforceable best practices from 35 seminal software engineering books (Code Complete, Clean Code, A Philosophy of Software Design, Refactoring, Release It!, Designing Data-Intensive Applications, etc.). Produces a structured PR comment with four dimension scores (0-5 each), specific violations with line numbers, and an APPROVE / REQUEST_CHANGES / BLOCK decision. Auto-invoke when the user asks to: - "review PR", "canon review", "best practices review", "engineering standards review" - "score this PR", "check this PR against best practices" - Asks about code quality, module design, reliability patterns, or maintainability of a PR Do NOT invoke for: general code questions not tied to a specific PR, or requests for quick/lightweight review (use /review instead). Keywords: canon, best practices, PR review, score, dimensions, code quality, module design, reliability, maintainability, SRP, DRY, guard clauses, deep modules, idempotency, circuit breaker.

Durable Temporal-backed build workflow that survives session crashes. Use when building, scaffolding, or implementing a spec via sagaflow.

Architecture-level design review evaluating 15 Tier 2 best practices drawn from DDD (Evans), POEAA (Fowler), Release It! (Nygard), DDIA (Kleppmann), Team Topologies (Skelton/Pais), How Buildings Learn (Brand), and Systemantics (Gall). Auto-invoke when a PR touches: - Service definitions, infrastructure code, API boundaries, or database schemas - Files matching **/architecture*, **/design*, **/api/*, **/schema*, **/migrations/* - Any directory named services/, infrastructure/, platform/, domain/, core/ Also invoke when the user says: - "design review", "architecture review", "review the design", "check the architecture" - "does this follow DDD", "bounded context check", "SOLID review" - "is this evolvable", "check coupling", "resilience review" Keywords: architecture, design, bounded context, DDD, SOLID, resilience, circuit breaker, bulkhead, shearing layers, cohesion, coupling, ADR, API versioning, Team Topologies, cognitive load, Gall's Law, consistency model, backpressure.

Use when creating, reading, editing, or producing Word documents (.docx) — including reports, memos, letters, templates with TOCs, headings, page numbers, or letterheads; extracting or reorganizing .docx content; find-and-replace; inserting/replacing images; accepting, rejecting, or authoring tracked changes and redlines; adding comments; validating docx structure; fixing 'invalid docx' or content-type / schema errors; converting .doc→.docx. Do NOT use for PDFs, spreadsheets, Google Docs, or coding tasks unrelated to Word documents.

Use when creating, reading, editing, or producing Word documents (.docx) — including reports, memos, letters, templates with TOCs, headings, page numbers, or letterheads; extracting or reorganizing .docx content; find-and-replace; inserting/replacing images; accepting, rejecting, or authoring tracked changes and redlines; adding comments; validating docx structure; fixing 'invalid docx' or content-type / schema errors; converting .doc→.docx. Do NOT use for PDFs, spreadsheets, Google Docs, or coding tasks unrelated to Word documents.

Systematically diagnoses why a test is flaky by running multi-run experiments, isolation tests, ordering permutations, and timing analysis. Use when the user says a test is flaky, intermittent, non-deterministic, randomly failing, passes sometimes, or asks to debug test flakiness.

Context compactor — prunes old sagaflow runs, archives stale memory files, compacts MEMORY.md indexes, compresses aimee journals. Like Squad's `squad nap` but for our Claude Code setup.

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

Use when creating, editing, scaffolding, designing, reviewing, improving, or refactoring a Claude Code skill, slash command, subagent, or agent capability. Also use when extracting a repeatable workflow from the current session into a reusable skill. Trigger phrases include "create skill", "build skill", "scaffold skill", "edit skill", "write skill", "design skill", "improve skill", "fix skill", "review skill", "audit skill", "refactor skill", "new slash command", "new subagent", "turn this workflow into a skill", "turn this into a skill", "extract skill from session", "skillify this", "save this workflow as a skill", "add a skill", "authoring skills", "writing skills".

Use when the user asks "what models are available", "list models", "show models", or wants to see which LLM models are accessible via claude-code-router.

Use when the user asks to run a task on a specific model, compare model outputs, or says 'run this on GPT/Gemini/Sonnet'. Routes tasks to any model via claude-code-router. Usage: /ccr-run [model] <task>

Use when checking CI/CD health, Jenkins build failures, flaky tests, build success rates, or generating a CI health report. Trigger phrases: CI health, build failures, jenkins report, flaky tests, build health, are builds passing, CI status.

Use when checking code quality trends, tech debt accumulation, TODO/FIXME growth, test coverage ratios, PR size distribution, or generating a code quality report. Trigger phrases: code quality, code trends, tech debt trends, quality report.