executing-plans
Use when you have a written implementation plan to execute
using-lsp-tools
Use when mcp-language-server tools are available and you need semantic code intelligence. Triggers: 'find definition', 'find references', 'who calls this', 'rename symbol', 'type hierarchy', 'go to definition', 'where is this used', 'where is this defined', 'what type is this'. Provides navigation, refactoring, and type analysis via LSP.
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
test-driven-development
Use when user explicitly requests test-driven development, says 'TDD', 'write tests first', 'red green refactor', 'test-first', or 'start with the test'. Also invoked as a sub-skill by implementing-features and executing-plans for each implementation task. NOT a replacement for implementing-features for full feature work.
writing-plans
Use when you have a spec, design doc, or requirements and need a detailed step-by-step implementation plan before coding. Triggers: 'write a plan', 'create implementation plan', 'plan this out', 'break this down into steps', 'convert design to tasks', 'implementation order'. Produces TDD-structured task sequences with file paths, code, and verification steps. Usually invoked by implementing-features Phase 3.
using-skills
Use when starting any conversation to initialize skill matching, or when unsure which skill applies to a request. Handles skill routing, rationalization prevention, and session initialization. Primarily loaded via session init, not by direct user request.
finding-dead-code
>
using-git-worktrees
Use when starting feature work that needs isolation from current workspace, setting up parallel development tracks, or before executing implementation plans. Triggers: 'worktree', 'separate branch', 'isolate this work', 'don't mess up current work', 'work on two things at once', 'parallel workstreams', 'sandboxed workspace'.
autonomous-roundtable
Meta-orchestrator for Forged autonomous development: decompose projects into features, execute through DISCOVER→DESIGN→PLAN→IMPLEMENT→COMPLETE, convene roundtables, coordinate skills.
optimizing-instructions
|
auditing-green-mirage
Use when auditing whether tests genuinely catch failures, or when user expresses doubt about test quality. Triggers: 'are these tests real', 'do tests catch bugs', 'tests pass but I don't trust them', 'test quality audit', 'green mirage', 'shallow tests', 'tests always pass suspiciously', 'would this test fail if code was broken'. Forensic analysis of assertions, mock usage, and code path coverage.
deep-research
>
dehallucination
Verify claims, references, and assertions are grounded in reality. Triggers: 'does this actually exist', 'is this real', 'did you hallucinate', 'verify these references', 'check if this is fabricated', 'reality check', 'ground truth'. Invoked as quality gate by roundtable feedback, Forge workflow, and after deep-research verification.
designing-workflows
Use when designing systems with explicit states, transitions, or multi-step flows. Triggers: \"design a workflow\", \"state machine\", \"approval flow\", \"pipeline stages\", \"what states does X have\", \"how does X transition\", or when implementing-features Phase 2.1 detects workflow patterns.
assembling-context
Prepare tiered context packages for subagents and manage token budgets. Triggered by 'prepare context for', 'assemble context', 'token budget', or invoked by implementing-features Phase 3.5/4.2.
distilling-prs
Use when reviewing PRs to triage, categorize, or summarize changes requiring human attention. Triggers: 'summarize this PR', 'what changed in PR #X', 'triage PR', 'which files need review', 'PR overview', 'categorize changes', or pasting a PR URL. Uses heuristic pattern matching to classify changes by review priority. For deep code analysis, use advanced-code-review instead.
documenting-tools
Use when writing MCP tools, API endpoints, CLI commands, or any function that an LLM will invoke. Also use when LLMs misuse tools due to poor descriptions. Triggers: 'document this tool', 'write tool docs', 'MCP tool', 'tool description quality', 'model keeps calling this wrong', 'improve tool description'. For human-facing API docs, standard documentation practices apply instead.
merging-worktrees
Use when merging parallel worktrees back together after parallel implementation, combining parallel development tracks, or unifying branches from dispatched parallel agents. Triggers: 'merge worktrees', 'combine parallel branches', 'integrate parallel work', 'all tracks complete', 'bring everything together'.
managing-artifacts
Use when generating documents, reports, plans, audits, or when asked where to save files. Triggers on "save report", "write plan", "where should I put", "project-encoded path"
isolated-testing
|
enforcing-code-quality
|
fractal-thinking
|
advanced-code-review
Use when performing thorough multi-phase code review with historical context tracking and verification. Triggers: 'thorough review', 'deep review', 'review this branch in detail', 'full code review with report'. 5-phase process: strategic planning, context analysis, deep review, verification, report generation. More heavyweight than code-review; produces detailed artifacts. For quick review, use code-review instead.
analyzing-domains
|
generating-diagrams
Use when generating flowcharts, diagrams, dependency graphs, or visual representations of processes, relationships, architecture, or state machines. Triggers: 'diagram this', 'flowchart', 'visualize', 'dependency graph', 'ER diagram', 'state machine diagram', 'class diagram', 'sequence diagram', 'map the relationships', 'draw the architecture', 'how does X connect to Y'. NOT for: simple bullet point explanations, runtime monitoring, or text-only documentation.
analyzing-skill-usage
Analyze session transcripts to extract skill invocation patterns, score invocations, and produce comparative metrics for skill improvement decisions.
reflexion
|
resolving-merge-conflicts
Use when git merge or rebase fails with conflicts, you see 'unmerged paths' or conflict markers (<<<<<<< =======), or need help resolving conflicted files
creating-issues-and-pull-requests
Use when creating GitHub pull requests or issues with template compliance. Triggers: 'create a PR', 'open a pull request', 'file an issue', 'create issue', or invoked as delegate from finishing-a-development-branch Option 2. Discovers project templates, populates them from branch context, and creates via reliable gh CLI patterns.
code-review
Use when reviewing code. Triggers: 'review my code', 'check my work', 'look over this', 'review PR #X', 'PR comments to address', 'reviewer said', 'address feedback', 'self-review before PR', 'audit this code'. Modes: --self (pre-PR self-review), --feedback (process received review comments), --give (review someone else's code/PR), --audit (deep single-pass analysis). For heavyweight multi-phase analysis, use advanced-code-review instead.
gathering-requirements
Use when eliciting or clarifying feature requirements, defining scope, identifying constraints, or capturing user needs. Triggers: 'what are the requirements', 'define the requirements', 'scope this feature', 'user stories', 'acceptance criteria', 'what should this do', 'what problem are we solving', 'what are the constraints'. Also invoked by implementing-features during DISCOVER stage and by the Forged workflow.
project-encyclopedia
[DEPRECATED] <ONBOARD> Use on first session in a project, or when user asks for codebase overview. Creates persistent glossary, architecture maps, and decision records to solve agent amnesia.
polish-repo
Use when improving project discoverability, attracting users/contributors, or presenting open source work. Triggers: 'write a README', 'improve README', 'get more users', 'get more contributors', 'add badges', 'create a logo', 'set up issue templates', 'audit this project', 'project presence', 'make this discoverable', 'why isn't anyone using this', 'prepare for launch', 'repo presentation', 'open source marketing', 'attract contributors', 'project storefront'. Also triggers on: naming a project, writing taglines, GitHub metadata, community infrastructure, signs of life.
deckset-presentation-expert
Expert assistant for creating Deckset presentations with markdown. Helps with slide formatting, headings, lists, images, videos, presenter notes, build steps, themes, and configuration. Use when working with .md presentation files, or when user mentions Deckset, creating slides, presentations, or decks.
react-native-component-generator
Generates React Native components with platform-specific code, TypeScript support, and mobile-first patterns. Use when user asks to "create React Native component", "generate RN component", "scaffold mobile component", or "create cross-platform component".
property-based-test-generator
Generates property-based tests using Hypothesis (Python), fast-check (JavaScript/TypeScript), or QuickCheck (Haskell). Use when user asks to "generate property tests", "create hypothesis tests", "add property-based testing", or "generate fast-check tests".
visual-regression-test-setup
Sets up visual regression testing using Percy, Chromatic, or Playwright to catch unintended UI changes through screenshot comparison. Use when user asks to "setup visual testing", "add screenshot tests", "prevent visual bugs", or "setup Percy/Chromatic".
database-query-optimizer
Analyzes and optimizes database queries for PostgreSQL, MySQL, MongoDB with EXPLAIN plans, index suggestions, and N+1 query detection. Use when user asks to "optimize query", "analyze EXPLAIN plan", "fix slow queries", or "suggest database indexes".
bundle-analyzer
Analyzes JavaScript bundle sizes, identifies large dependencies, and suggests optimizations for webpack, vite, rollup. Use when user asks to "analyze bundle", "optimize bundle size", "reduce bundle", "webpack analysis", or "tree shaking".
translation-key-extractor
Extracts hardcoded strings from code and converts them to translation keys for i18n. Use when user asks to "extract translations", "find hardcoded strings", "internationalize code", "setup i18n", or "create translation files".
i18n-setup-wizard
Sets up complete internationalization infrastructure for React, Vue, Next.js, or vanilla JS with framework config, translation files, and language switching. Use when user asks to "setup i18n", "add translations", "multi-language support", or "internationalization setup".
lighthouse-ci-integrator
Integrates Lighthouse CI for automated performance testing, Core Web Vitals tracking, and regression detection in CI/CD pipelines. Use when user asks to "setup Lighthouse CI", "add performance testing", "monitor Core Web Vitals", or "prevent performance regressions".
dependency-vulnerability-scanner
Scans dependencies for known vulnerabilities (npm audit, pip-audit, etc.), generates reports, and suggests fixes. Use when user asks to "check vulnerabilities", "security scan", "audit dependencies", "check CVEs", or "vulnerable packages".
pii-detector
Detects Personally Identifiable Information (PII) in code, logs, databases, and files for GDPR/CCPA compliance. Use when user asks to "detect PII", "find sensitive data", "scan for personal information", "check GDPR compliance", or "find SSN/credit cards".
image-optimizer
Optimizes images for web performance by converting to modern formats, compressing, and generating responsive sizes. Use when user asks to "optimize images", "compress images", "convert to webp", or mentions image performance.
security-header-generator
Generates security HTTP headers (CSP, HSTS, CORS, etc.) for web applications to prevent common attacks. Use when user asks to "add security headers", "setup CSP", "configure CORS", "secure headers", or "HSTS setup".
vue-component-generator
Generates Vue 3 components using Composition API, TypeScript, proper props definition, and best practices. Use when creating Vue components or building Vue UI.
testing-framework-helper
Generates comprehensive test suites with unit tests, integration tests, and E2E tests for various frameworks (Jest, Pytest, Vitest, etc.). Use when writing tests.
react-component-generator
Generates React components with TypeScript, hooks, and best practices. Use when user asks to "create React component", "generate component", or "scaffold component".
nextjs-page-generator
Generates Next.js 13+ pages with App Router, Server Components, Client Components, API routes, and proper data fetching. Use when building Next.js applications.
Page 1247 of 1607 · 80320 results
