research-brief
Generate a concise research brief with uncertainty and citations.
tailscale
Troubleshoot Tailscale connectivity or access internal services via Tailscale hostnames.
technicals-regime
Summarize trend, volatility, and liquidity regime from TA time series.
pr-process
Prepare commits and pull requests for this repo following the PR template and Conventional Commits.
github-issue
Create GitHub issues in this repo using the Codex issue template and the gh CLI. Use when the user asks to file/open/create a GitHub issue, track work, or request a Codex implementation run via .github/ISSUE_TEMPLATE/codex-task.md.
ansible
Create, update, or run Ansible playbooks and inventory in this repo for multi-node changes (ansible/). Use for node bootstrap, package installs, or cluster-wide config updates.
kubernetes
Use for kubectl, CNPG, and kustomize/helm operations in this repo, including rollouts and cluster debugging.
market-context
Build a normalized market-context JSON bundle for a single symbol and timestamp.
news-sentiment
Extract structured, source-attributed sentiment context for one symbol.
deployment
Build, push, and deploy services via GitOps in this repo. Use when updating images, manifests, or rolling out changes with Argo CD.
fundamentals
Produce normalized fundamentals factors and deltas for one symbol.
github
Work with GitHub in this repo: PR creation, CI checks, and gh CLI operations.
gitops
GitOps workflows for this repo: edit Argo CD/Kubernetes/infra manifests in version control, validate changes, and rely on Argo CD to sync. Use when tasks touch argocd/, kubernetes/, tofu/, ansible/, or deployment/runbook changes, or when asked to roll out services via GitOps.
memories
Save and retrieve memories or embeddings via the repo helpers or API. Use when working with embedding config or memory storage.
repo-map
Navigate this repo quickly to find the correct app, package, or service, and identify the right files for changes.
deepwork-bar
Add, remove, or list written-bar criteria for the active deepwork session
Team Management
This skill should be used when the user asks to "manage teams", "create a team", "create a task", "assign a task", "send a message to an agent", "list teams", "check tasks", "broadcast to team", "read inbox", "update task status", or any team/task/agent/message management operation.
deepwork
Run a deepwork session: research/design convergence (default) or plan execution (--mode execute). Design mode spawns a 5-archetype oppositional team and delivers an approved plan. Execute mode drives faithful implementation of an approved plan via role-asymmetric agents.
deepwork-wiki
Synthesize the deepwork wiki — rewrites Overview, Session Index, and Cross-refs in ${CLAUDE_PROJECT_DIR:-$(pwd -P)}/.claude/deepwork/DEEPWORK_WIKI.md from archived sessions. Preserves the # Log section verbatim (hook owns it).
deepwork-teardown
End an active deepwork session — graceful per-teammate shutdown, archives state, and restores settings. CLI auto-cleans team dirs at session end. Works for both mid-flight abort and post-HALT cleanup.
deepwork-status
View deepwork session status — phase, team, bar verdicts, proposals, guardrails
deepwork-reconcile
Rebuild state.json from events.jsonl — full replay with hash-chain validation
deepwork-recap
Karpathy-style recap of deepwork history — reads DEEPWORK_WIKI.md Overview and the last 3 log entries, outputs 30-50 plain-text words
deepwork-guardrail
Add, remove, replace, or list hard guardrails for the active deepwork session
deepwork-execute-status
View execute-mode session status — phase, plan_hash, drift, change_log, test results, 3-dimension verdict table, rollback log, discoveries
deepwork-execute-amend
Lightweight single-gate amendment for execute mode — spawns MICRO-TEAM (CRITIC + 1 specialist) for re-verdict without full deepwork re-run
deepwork-drift-sweep
Enumerate ALL workstreams in the current deepwork session and diff each artifact against its source-of-truth. Produces drift-report.vN.md listing potential drift items across every workstream, not only those flagged by the drift agent.
typescript-workflow
TypeScript/JavaScript project workflow guidelines using Bun package manager. Triggers on `.ts`, `.tsx`, `bun`, `package.json`, TypeScript. Covers bun run, bun install, bun add, tsconfig.json patterns, ESM/CommonJS modules, type safety, Biome formatting, naming conventions (PascalCase, camelCase, UPPER_SNAKE_CASE), project structure, error handling, environment variables, async patterns, and code quality tools. Activate when working with TypeScript files (.ts, .tsx), JavaScript files (.js, .jsx), Bun projects, tsconfig.json, package.json, bun.lock, or Bun-specific tooling.
typescript-testing
TypeScript/JavaScript testing practices with Bun's test runner. Activate when working with bun test, .test.ts, .test.js, .spec.ts, .spec.js, testing TypeScript/JavaScript, bunfig.toml, testing configuration, or test-related tasks in Bun projects.
testing-workflow
Testing workflow patterns and quality standards. Activate when working with tests, test files, test directories, code quality tools, coverage reports, or testing tasks. Includes zero-warnings policy, targeted testing during development, mocking patterns, and best practices across languages.
sql-workflow
SQL workflow guidelines. Activate when working with SQL files (.sql), database queries, migrations, or SQLFluff.
web-projects
Guidelines for web development projects using JavaScript/TypeScript frameworks. Activate when working with web projects, package.json, npm/yarn/pnpm, React, Next.js, Vue, Angular, Svelte, or other web frameworks, frontend components, or Node.js applications.
flask-workflow
Flask framework workflow guidelines. Activate when working with Flask projects, flask run, or Flask-specific patterns.
shell-workflow
Shell script workflow guidelines. Activate when working with shell scripts (.sh), bash scripts, or shell-specific tooling like shellcheck, shfmt.
structured-analysis
Apply structured analytical frameworks to any artifact (prompts, systems, documents, code). 12 frameworks in 3 tiers: Core (4 universal), Auto-Invoke (specialized), On-Demand (advanced). Includes adversarial-review for finding blind spots and post-plan validation workflow.
code-documentation
Guidelines for self-explanatory code and meaningful documentation. Activate when working with comments, docstrings, documentation, code clarity, API documentation, JSDoc, or discussing code commenting strategies. Guides on why over what, anti-patterns, decision frameworks, and language-specific examples.
go-workflow
Go project workflow guidelines. Activate when working with Go files (.go), go.mod, Go modules, golang, or Go-specific tooling.
ansible-workflow
Ansible automation workflow guidelines. Activate when working with Ansible playbooks, ansible-playbook, inventory files (.yml, .ini), or Ansible-specific patterns.
least-astonishment
Principle of Least Astonishment (POLA) - ensure code changes behave as users and developers expect. Activate when making code changes, refactoring, modifying APIs, renaming functions/variables, changing file structure, or reviewing proposed implementations. Guides predictable, convention-following changes.
ignore-files-workflow
Ignore file management for .gitignore, .dockerignore, and .specstory directories. Includes synchronization, alphabetical ordering, organization, best practices, and testing guidelines. Activate when working with .gitignore, .dockerignore, .specstory files, or managing version control and Docker build context.
session-context-management
Maintain "just enough" context across work sessions using CURRENT.md, STATUS.md, and LESSONS.md files. Activate when tasks take >15 minutes, touch 3+ files, interruptions likely, or scope uncertain. Includes /snapshot and /pickup commands for saving and resuming work. ADHD-friendly, token-efficient approach.
rust-workflow
Rust project workflow guidelines. Activate when working with Rust files (.rs), Cargo.toml, Cargo.lock, or Rust-specific tooling.
ruleset-optimization
Guidelines for optimizing Claude rulesets and instruction files (CLAUDE.md, settings.json) using context efficiency principles. Includes strategies for skill extraction, progressive disclosure, token savings calculation, and deduplication. Manually invoke when optimizing rulesets, reducing context size, extracting content to skills, or improving ruleset organization.
ruby-workflow
Ruby project workflow guidelines. Activate when working with Ruby files (.rb), Gemfile, bundler, or Ruby-specific tooling.
react-workflow
React framework workflow guidelines. Activate when working with React components (.jsx, .tsx), React hooks (useState, useEffect), or React-specific patterns.
rails-workflow
Ruby on Rails framework workflow guidelines. Activate when working with Rails projects, Gemfile with rails, rake tasks, or Rails-specific patterns.
python-workflow
Python project workflow guidelines. Triggers: .py, pyproject.toml, uv, pip, pytest, Python. Covers package management, virtual environments, code style, type safety, testing, configuration, CQRS patterns, and Python-specific development tasks.
python-testing
Python-specific testing practices with pytest, fixtures, mocking, async testing, coverage configuration, and uv execution rules. Activate when working with pytest files, conftest.py, test directories, pyproject.toml testing configuration, or Python test-related tasks.
ptc-orchestration
Activate when user needs multi-URL scraping, browser automation pipelines, or efficient tool orchestration to reduce API round-trips and context usage.
nextjs-workflow
Next.js framework workflow guidelines. Activate when working with Next.js projects, next.config, app router, or Next.js-specific patterns.
Page 1153 of 1711 · 85517 results
