specwright
Spec-driven development workflow for Claude Code. Maps each acceptance criterion to implementation and test evidence, and runs build, test, security and semantic quality gates with captured output.
23 skills10
@obsidian-owl- 10Stars earned
- 1Plugin
- 23Skills
- 9Agents
- 18Commands
Plugins
1@obsidian-owlSkills
23gate-build
Runs configured build and test commands in tiered order. Captures output as evidence per tier. Returns PASS, FAIL, WARN, or SKIP…
@obsidian-owlgate-security
Detects leaked secrets, injection patterns, and sensitive data exposure across changed files. Uses real tooling when configured,…
@obsidian-owlgate-semantic
Tiered semantic analysis of changed code (rg → ast-grep → OpenGrep). Detects error-path bugs structural gates miss. Findings…
@obsidian-owlgate-spec
Maps every acceptance criterion from the spec to implementation evidence and test evidence. Criteria without evidence fail. The…
@obsidian-owlgate-tests
Audits test quality — assertion strength, boundary coverage, mock discipline, error path testing. Delegates to the tester agent…
@obsidian-owlgate-wiring
Detects unused exports, orphaned files, architecture layer violations, and circular dependencies across changed files. Delegates…
@obsidian-owlsw-adopt
Explicitly adopt an existing work into the current worktree after validating live ownership, stale sessions, and branch…
@obsidian-owlsw-audit
Periodic codebase health check. Analyzes architecture, complexity, consistency, and debt across the full codebase. Produces…
@obsidian-owlsw-build
TDD implementation of one work unit. Delegates test writing to the tester agent and implementation to the executor agent. Commits…
@obsidian-owlsw-debug
Investigation-first debugging workflow. Scopes the problem, delegates root cause analysis, produces a diagnosis report, and…
@obsidian-owlsw-design
Autonomous solution architecture. Researches the codebase, designs a solution, challenges it adversarially, and produces design…
@obsidian-owlsw-doctor
Specwright health check. Validates shared config, anchor docs, workflow and session state, commands, gates, and hooks. May…
@obsidian-owlAgents
9eval-analyzer
AgentYou are an analysis agent for the Specwright eval framework. Your job is to surface patterns and anomalies in benchmark data from…
@obsidian-owleval-grader
AgentYou are a grading agent for the Specwright eval framework. Your job is to evaluate a piece of content against a rubric and return…
@obsidian-owlspecwright-architect
AgentStrategic architecture advisor. Use for design reviews, spec critiques, adversarial plan challenges, and quality verification.…
@obsidian-owlspecwright-build-fixer
AgentFixes build and test failures with minimal changes. Gets the build green quickly without architectural changes or refactoring.
@obsidian-owlspecwright-executor
AgentFocused task executor for TDD implementation. Builds exactly one work unit at a time. Receives failing tests, writes minimal code…
@obsidian-owlspecwright-integration…
AgentIntegration test engineer for non-unit tiers. Writes integration tests, contract tests, and end-to-end tests that exercise real…
@obsidian-owlspecwright-researcher
AgentDocumentation and reference researcher. Fetches official docs, verifies technical information, and summarizes findings. READ-ONLY.
@obsidian-owlspecwright-reviewer
AgentCode quality and spec compliance reviewer. Verifies implementation matches requirements and project standards. Read-only for…
@obsidian-owlspecwright-tester
AgentAdversarial test engineer. Writes tests that are genuinely hard to pass. Thinks like an attacker hunting for weak…
@obsidian-owlCommands
18sw-adopt
CommandExplicitly adopt an existing work into the current worktree.
@obsidian-owlsw-audit
CommandPeriodic codebase health check for systemic technical debt.
@obsidian-owlsw-build
CommandTDD implementation of one work unit. If branch-head freshness blocks and policy is rebase or merge, recover in-stage; manual is…
@obsidian-owlsw-debug
CommandInvestigation-first debugging. Scope, investigate, diagnose, then fix/log/defer.
@obsidian-owlsw-design
CommandInteractive solution architecture with adversarial critique and assumption surfacing.
@obsidian-owlsw-doctor
CommandRead-only installation health check with repair hints.
@obsidian-owlsw-eval
CommandRun Specwright eval suite. Spawns subagents to run skills in fixture workdirs, then grades results.
@obsidian-owlsw-guard
CommandDetect stack and configure deterministic guardrails.
@obsidian-owlsw-init
CommandProject setup. Creates constitution and charter. Configures gates.
@obsidian-owlsw-learn
CommandPost-ship capture of patterns and learnings.
@obsidian-owlsw-pivot
CommandResearch-backed rebaselining for planning, building, or verifying work. Preserves completed and shipped scope while revising…
@obsidian-owlsw-plan
CommandDecompose design into work units with testable specs.
@obsidian-owlIs this you? Claim your profilePut a plugin at the top of Plugins, from $9