Development

Verify a synthetic installed IDD package when explicitly testing the packaging toolchain.

Create a draft five-block IDD Spec from selected Expectations with common Product context, confirmed boundaries and exact embedded edge cases.

Review a Spec for architectural feasibility, completeness and cross-block contradictions; preserve lifecycle and content while recording current technical findings.

Validate an implementation against every Spec Expectation, edge case, Boundary and Deliverable with actual test evidence and explicit unverified/human checks.

Claim and resolve one eligible Exploration decision, preserving unrelated staged work, human answers and truthful map completion.

Author a linked draft Intention, Expectation and five-block Spec batch from a Product and confirmed feature outcome; preserve stakeholder confirmation before saving.

Interview stakeholders and create an IDD Product definition with business purpose, audience, owner and technical context. Use when defining a product, not when implementing a Spec.

Execute one ready IDD Spec with a current clean gap-check, enforce its Boundaries, verify deliverables and produce an execution report. Use for managed Spec implementation, not general repository maintenance.

Adversarially review one or more IDD Specs for implementation ambiguity, contradictions and unowned impact-surface files before execution. Produces finding reports and gate annotations without rewriting Spec content.

Launch the Forge web UI for this project's IDD artifacts, with literal optional port/docs arguments, an observable background process and startup error reporting.

Define linked draft Intentions and Expectations together from a Product, confirming every edge case before saving the batch.

Define confirmed draft Intentions from an IDD Product, preserving purpose, priorities, dependencies and exploration lineage.

Define confirmed draft Expectations for an IDD Intention, with measurable criteria and at least two explicitly confirmed edge cases.

Review a Spec from architecture, boundary/edge and deliverable/validation perspectives with truthful parallel or sequential coverage and a consolidated report.

Chart a phase-zero Exploration map from confirmed destination and unresolved questions, preserving human decisions and factual research.

Classify terminal IDD work into a reviewable manifest, then apply explicitly approved archival with a recovery tag and reconciled ledger.

Onboards a NestJS project to the nestjs-hexagonal rulebook, CLI and hooks — creates .claude/rulebook.yaml extending the plugin rulebooks with sha256 stamps, sets the optional TypeSafe key, pins the CLI as a dev dependency, runs the first baseline check and explains what the hooks will do from then on. Use when a project starts using the plugin, when asked to "onboard this project", "enable the hooks", "create the rulebook" or "set up nestjs-hexagonal-check".

Calibrates or evaluates a semantic (Jev) rule of the nestjs-hexagonal rulebook — adds labelled golden cases, runs the calibration harness against the real model, fits thresholds, reads the report and decides whether the rule stays advisory or moves to ask; also produces the weekly pilot report from the hook logs. Use when a semantic rule misfires, when a new semantic rule is added, when asked to "calibrate a rule", "add golden cases", "raise a rule to ask" or "weekly Jev report".

Vite build tool patterns including config, plugins, HMR, env variables, proxy setup, SSR, library mode, dependency pre-bundling, and build optimization. Activate when working with vite.config.ts, Vite plugins, or Vite-based projects.

Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite this prompt", or explicitly asks to enhance prompt quality. Also triggers on Chinese equivalents: "优化prompt", "改进prompt", "怎么写prompt", "帮我优化这个指令". DO NOT TRIGGER when: user wants...

Use when you have a spec or requirements for a multi-step task, before touching code

Expert in building custom tools that solve your own problems first. The best products often start as personal tools - scratch your own itch, build for yourself, then discover others have the same itch. Covers rapid prototyping, local-first apps, CLI tools, scripts that grow into products, and the art of dogfooding. Use when: build a tool, personal tool, scratch my itch, solve my problem, CLI tool.

Guide for continuous improvement, error proofing, and standardization. Use this skill when the user wants to improve code quality, refactor, or discuss process improvements.

Specialized skill for building production-ready Discord bots. Covers Discord.js (JavaScript) and Pycord (Python), gateway intents, slash commands, interactive components, rate limiting, and sharding.