Development
Plugin
specweave
Spec-first AI development: describe a feature → AI creates spec + plan + tasks, builds autonomously, syncs to GitHub/JIRA. Domain-expert skills for PM, Architect, Frontend, QA learn your patterns permanently. Claude Code, Codex, Cursor, Copilot & more.
Plugin Signal92/100Strong
maintained100
capable100
documented100
adopted47
Install on Claude Code
> /plugin marketplace add anton-abyzov/specweave> /plugin install sw@specweave
Stats
158
Stars
21
Forks
Active
Maintenance
TypeScript
Language
MIT
License
8h ago
Last commit
9mo ago
Created
Repo: anton-abyzov/specweave
In this plugin
- commands
- abandon
- ado-cleanup-duplicates
- ado-clone
- ado-close
- ado-create
- ado-import-areas
- ado-import-projects
- ado-pull
- ado-push
- ado-reconcile
- ado-status
- ado-sync
- analytics
- archive
- auto-status
- cancel-auto
- diagrams-generate
- discrepancies
- discrepancy-to-increment
- docs-build
- docs-generate
- docs-health
- docs-init
- docs-organize
- docs-validate
- docs-view
- docs
- doctor
- fix-duplicates
- framework
- github-cleanup-duplicates
- github-clone
- github-close
- github-create
- github-pull
- github-push
- github-reconcile
- github-status
- github-sync
- github-update-user-story
- handoff
- import-external
- jira-cleanup-duplicates
- jira-close
- jira-create
- jira-import-boards
- jira-import-projects-full
- jira-import-projects
- jira-pull
- jira-push
- jira-reconcile
- jira-status
- jira-sync
- jobs
- living-docs
- lsp
- next
- progress
- qa
- reconcile
- reflect
- release-align
- release-init
- release-npm
- release-platform
- release-rc
- restore
- save
- state
- sync-setup
- sync-status
- team-status
- update-instructions
- skills
- ado-mapper
- ado-multi-project
- ado-resource-validator
- ado-sync
- analytics
- architect
- auto
- brainstorm
- close-all
- code-reviewer
- debug
- diagrams
- do
- done
- e2e
- get
- github-issue-standard
- github-multi-project
- github-sync
- grill
- handoff
- help
- image
- import
- increment
- jira-mapper
- jira-resource-validator
- jira-sync
- judge-llm
- multi-project
- npm
- plan
- pm
- pr-review
- pr
- progress-sync
- release-expert
- remotion
- skill-gen
- skill-refine
- sync-docs
- tdd-cycle
- tdd-green
- tdd-red
- tdd-refactor
- team-build
- team-lead
- team-merge
- umbrella
- validate
- video
- agents
What's inside
Skill(51 skills)
/ado-mapperBidirectional conversion between SpecWeave increments and Azure DevOps work items. Use when exporting increments to ADO epics, importing ADO epics as increments, or resolving sync conflicts. Handles Epic/Feature/User Story/Task hierarchy mapping./ado-multi-project[DEPRECATED] Use `sw:multi-project --tool ado` instead. Organizes specs and tasks across multiple Azure DevOps projects. This skill will be removed in SpecWeave v1.3.0./ado-resource-validatorValidates Azure DevOps projects, area paths, and teams exist with auto-creation of missing resources. Use when setting up ADO integration, configuring .env variables, or troubleshooting missing project errors. Supports project-per-team, area-path-based, and team-based strategies./ado-sync[DEPRECATED] Help and guidance for Azure DevOps synchronization with SpecWeave increments. Use when asking how to set up ADO sync, configure credentials, or troubleshoot integration issues. For actual syncing, use sw-ado:push or sw-ado:pull command./analyticsAnalytics and metrics for SpecWeave usage — token consumption, cache efficiency, agent spawn counts./architectSystem architect for scalable technical designs and ADRs. Use for system architecture, microservices, database design, trade-off analysis, component diagrams, tech selection.
- /auto
- /brainstorm
- /close-all
- /code-reviewer
- /debug
- /diagrams
- /do
- /done
- /e2e
- /get
- /github-issue-standard
- /github-multi-project
- /github-sync
- /grill
- /handoff
- /help
- /image
- /import
- /increment
- /jira-mapper
- /jira-resource-validator
- /jira-sync
- /judge-llm
- /multi-project
- /npm
- /plan
- /pm
- /pr-review
- /pr
- /progress-sync
- /release-expert
- /remotion
- /skill-gen
- /skill-refine
- /sync-docs
- /tdd-cycle
- /tdd-green
- /tdd-red
- /tdd-refactor
- /team-build
- /team-lead
- /team-merge
- /umbrella
- /validate
- /video
Agent(20 agents)
sw-architectSystem Architect for writing plan.md with architecture decisions and component design. Use for increment technical planning during sw:increment orchestration.sw-closerIncrement closer that runs the full sw:done closure pipeline (code-review, simplify, grill, judge-llm, PM validation, sync) in a fresh context. Use when closing increments after task completion to avoid context overflow.sw-plannerTest-Aware Planner for generating tasks.md with BDD test plans. Reads spec.md and plan.md to produce implementation tasks with Given/When/Then scenarios. Use during sw:increment orchestration.sw-pmProduct Manager for writing spec.md with user stories and acceptance criteria. Use for increment specification creation during sw:increment orchestration.reviewer-commentsYou are the COMMENT ACCURACY REVIEWER agent.reviewer-silent-failuresYou are the SILENT FAILURES REVIEWER agent.
Command(73 commands)
/abandonAbandon an incomplete increment (requirements changed, obsolete)/ado-cleanup-duplicatesClean up duplicate Azure DevOps work items for a Feature. Finds work items with duplicate titles and closes all except the first created item./ado-cloneClone Azure DevOps repositories to local workspace. Use after init if cloning was skipped, or to add repos later./ado-closeClose Azure DevOps work item when increment complete/ado-createCreate Azure DevOps work item from SpecWeave increment/ado-import-areasImport Azure DevOps area paths from a project and map them to SpecWeave projects. Creates 2-level directory structure with area path-based organization.
- /ado-import-projects
- /ado-pull
- /ado-push
- /ado-reconcile
- /ado-status
- /ado-sync
- /analytics
- /archive
- /auto-status
- /cancel-auto
- /diagrams-generate
- /discrepancies
- /discrepancy-to-increment
- /docs-build
- /docs-generate
- /docs-health
- /docs-init
- /docs-organize
- /docs-validate
- /docs-view
- /docs
- /doctor
- /fix-duplicates
- /framework
- /github-cleanup-duplicates
- /github-clone
- /github-close
- /github-create
- /github-pull
- /github-push
- /github-reconcile
- /github-status
- /github-sync
- /github-update-user-story
- /handoff
- /import-external
- /jira-cleanup-duplicates
- /jira-close
- /jira-create
- /jira-import-boards
- /jira-import-projects-full
- /jira-import-projects
- /jira-pull
- /jira-push
- /jira-reconcile
- /jira-status
- /jira-sync
- /jobs
- /living-docs
- /lsp
- /next
- /progress
- /qa
- /reconcile
- /reflect
- /release-align
- /release-init
- /release-npm
- /release-platform
- /release-rc
- /restore
- /save
- /state
- /sync-setup
- /sync-status
- /team-status
- /update-instructions
README
The Problem
36.82% of AI skills have security flaws (Snyk ToxicSkills). In May 2025, 170 out of 1,645 vibe-coded apps had security vulnerabilities exposing personal data. No specs. No tests. No review. Just vibes.
Every alternative is an instruction layer — Cursor Rules, Copilot Instructions, Windsurf Rules, CLAUDE.md. They tell the AI how to write code but never what to build, never how to test it, and never when it's done.
SpecWeave is a spec-first development layer. Configuration, not prompting. Enforced, not hoped for.
The Solution
You: "Build a checkout flow with Stripe"
↓
spec.md → plan.md → tasks.md ← you review the plan
↓
Autonomous execution for hours ← AI builds, tests, fixes
↓
Quality gates (Grill + Judge-LLM) ← code reviewed automatically
↓
Synced to GitHub/JIRA/ADO ← closed, documented, shipped
Every feature starts as a specification — user stories, acceptance criteria, architecture decisions — before a single line of code is written. TDD enforces correctness. Quality gates catch what tests miss.
Built With SpecWeave
12 production projects shipped in 3 months. 5 in the App Store.
| App | Platform | What It Does |
|---|---|---|
| EasyChamp | Web (GCP) | Enterprise sports league management. 20+ microservices, ML video analytics. 4 years in production. |
| SketchMate | App Store | AI drawing game — multi-model evaluation judges player art semantically. |
| Lulla | App Store | Baby sleep app with Apple Watch. ML cry classification (tired/hungry/pain). |
| Football 2026 | App Store + Web | World Cup 2026 companion. AI travel planner, live tickets, team stats. |
| SkillUp Football | App Store | Coaches monetize training via Stripe. Instagram-like feed, scheduling. |
| BizZone | App Store | Student & business events with AI-powered news generation. |
| EduFeed | Web | NotebookLM meets Zoom. Upload videos, get quizzes, flashcards, live rooms. |
| JobWeave | Web | AI-powered job search. Smart matching, resume optimization. |
| SpecWeave | npm | The framework itself. 600+ increments, 538+ releases. |
| SpecWeave Umbrella | GitHub | Multi-repo orchestration workspace for all repositories. |
| vskill | npm | Package manager for AI skills. Security scanning, 49 platforms. |
| verified-skill.com | Web | Skill marketplace & studio. 105K+ verified skills, eval system. |
Browse increments on GitHub — full transparency.
Quick Start
npm install -g specweave # Node.js 20.12.0+
cd your-project
specweave init .
# Then in Claude Code, Cursor, Copilot, or any AI tool:
# "Build me a user authentication system"
How It Compares
| Capability | Cursor Rules | Copilot Instructions | Windsurf | Cline | Vibe Coding | SpecWeave |
|---|---|---|---|---|---|---|
| Structured specs (spec + plan + tasks) | — | — | — | — | — | Yes |
| Quality gates (Grill + Judge-LLM + 130 rules) | — | — | — | — | — | Yes |
| Autonomous execution (hours, unattended) | — | — | — | — | — | Yes |
| Multi-agent teams (parallel, contract-first) | — | — | — | — | — | Yes |
| External sync (GitHub / JIRA / ADO) | — | — | — | — | — | Yes |
| TDD enforcement (strict red-green-refactor) | — | — | — | — | — | Yes |
| LSP code intelligence (198x faster) | — | — | — | — | — | Yes |
| Self-improving skills (learns from corrections) | — | — | — | — | — | Yes |
Cursor tells AI "use Tailwind." SpecWeave tells AI "build a checkout flow with 5 acceptance criteria, test it, review it, sync to JIRA, and close."
Key Features
Spec-First Planning — Every feature starts as spec.md + plan.md + tasks.md. Configuration, not prompting.
TDD Enforcement — Strict red-green-refactor. Tasks cannot close without passing tests. Coverage targets enforced.
Agent Swarms — Run parallel agents across iTerm/tmux panes. Team lead splits work, each agent owns an increment.
┌──────────────────┬──────────────────┬──────────────────┐
│ Agent 1 (auth) │ Agent 2 (payments)│ Agent 3 (catalog)│
│ sw:auto │ sw:auto │ sw:auto │
│ ████████░░ 80% │ ██████░░░░ 60% │ ████░░░░░░ 40% │
└──────────────────┴──────────────────┴──────────────────┘
LSP Code Intelligence — 198x faster than grep, 0 false positives. Semantic references, definitions, and types.
100+ Skills — PM, Architect, QA, Security, DevOps, Frontend, Backend, Mobile, ML. Every skill is customizable via skill-memories without forking.
External Sync — GitHub Issues, JIRA, Azure DevOps — bidirectional, real-time. Close an increment, external tools update automatically.
Enterprise Ready — Compliance audit trails (SOC 2, HIPAA, FDA). Brownfield analysis. Multi-repo coordination. Multi-environment deployment.
Dashboard — Built-in web dashboard for increment progress, analytics, cost tracking, and multi-project monitoring.
Skills Ecosystem
SpecWeave skills are published and verified at verified-skill.com. The vskill package manager provides:
- Security scanning — 52 attack patterns, SHA-256 pinning, blocklist API
- 49 agent platforms — one install deploys to Claude Code, Cursor, Copilot, Windsurf, and 45 more
- Skill evals — unit tests, A/B comparisons, cross-model testing. Skills tested like programs.
- Visual Skill Studio —
vskill eval servefor benchmarks, comparisons, and history
npx vskill install remotion-best-practices # Install from registry
npx vskill eval run my-skill # Run eval suite
Core Commands
| You say | SpecWeave runs |
|---|---|
| "Build me X" | sw:increment → spec + plan + tasks |
| "Go ahead" | sw:auto → autonomous execution |
| "Ship it" | sw:done → quality gates + close |
| "Split into teams" | sw:team-lead → parallel agents |
| "Review the code" | sw:code-reviewer → 6 parallel reviewers |
Upgrading to v1.1.0 (Opus 4.7 Alignment)
SpecWeave v1.1.0 aligns the framework with Claude Opus 4.7 best practices.
P0 Fixes (required if using judge-llm or team-lead)
-
Remove fixed extended thinking:
sw:judge-llmno longer passesthinking.budget_tokens. Adaptive prompt hints replace it. No user action needed — the CLI handles this automatically. -
Team-lead spawn heuristic:
sw:team-leadnow only spawns agents whendomains ≥ 3ORtasks ≥ 15OR--parallelis set. Previously it always spawned agents. -
State markers removed:
skill-chain-*.jsonandinterview-*.jsonstate files are no longer written.pretooluse-guard.tsuses TaskGet-based state with filesystem fallback.
Config Migration
Run the migration script to add new config keys with defaults:
specweave migrate-config-0669
Deprecations
See full list in CHANGELOG.md. Key migrations:
/sw:tdd-red→/sw:tdd-cycle --phase red/sw:github-sync→/sw-github:sync-spec/sw:team-build→/sw:team-lead --preset <name>
Full migration guide: .specweave/docs/internal/specs/opus-47-migration.md
Documentation
spec-weave.com — guides, reference, and enterprise docs.
Community
Discord · YouTube · GitHub Issues
License
File tree
anton-abyzov/specweaveView on GitHub
.claude-plugin/
marketplace.json
README.md
.env.example
.gitattributes
.github/
actions/
setup-and-build/
action.yml
CLAUDE_WORKFLOW_FIX_PROMPT.md
CONTRIBUTING.md
dependabot.yml
ISSUE_TEMPLATE/
bug-report.yml
config.yml
feature-request.yml
PULL_REQUEST_TEMPLATE.md
workflows/
_disabled/
kafka-plugin-ci.yml
bot-pr-guardian.yml
ci-autofix.yml
claude-code-review.yml
claude.yml
config-validation.yml
dependabot-auto-merge.yml
dependabot-autofix.yml
deploy-docs.yml
docs-build.yml
dora-metrics.yml
e2e-smoke-test.yml
process-lifecycle-tests.yml
release.yml
skill-lint.yml
test-autofix.yml
test.yml
validate-platforms.yml
version-alignment.yml
.gitignore
.mermaidrc.json
.npmignore
AGENTS.md
bin/
specweave.js
CHANGELOG.md
CLAUDE.md
CODE_OF_CONDUCT.md
docs-site/
.env.example
.gitignore
ALGOLIA-DOCSEARCH-SETUP.md
blog/
_template.md
2025-10-26-introducing-specweave.md
2026-01-04-seo-best-practices.md
2026-02-21-toxicskills-why-your-ai-agent-skills-need-verification.md
authors.yml
tags.yml
DEPLOYMENT.md
docs/
docs-site/
ALGOLIA-DOCSEARCH-SETUP.md
_page-template.md
academy/
fundamentals/
ai-development-fundamentals.md
backend-fundamentals.md
enterprise-app-development.md
frontend-fundamentals.md
iac-fundamentals.md
index.md
ml-fundamentals.md
security-fundamentals.md
software-engineering-roles.md
testing-fundamentals.md
index.md
specweave-essentials/
01-getting-started.md
02-three-file-structure.md
03-your-first-increment.md
04-the-next-command.md
05-quality-gates.md
06-tdd-workflow.md
07-external-tools.md
08-ai-model-selection.md
09-troubleshooting.md
10-advanced-patterns.md
11-vibe-coding-problem.md
12-init-deep-dive.md
13-increment-lifecycle.md
14-github-integration.md
15-jira-integration.md
16-ado-integration.md
index.md
talks/
index.md
skills-plugins-marketplaces.md
videos/
index.md
opencode-web-calculator.mdx
api/
index.md
commands/
abandon.md
auto-status.md
auto.md
cancel-auto.md
do.md
help.md
jobs.md
overview.md
pause.md
reflect.md
resume.md
save.md
skill-refine.md
status-management.md
status.md
enterprise/
azure-devops-migration.md
case-study-migration.md
github-migration.md
index.md
jira-migration.md
knowledge-transfer-migration.md
monolith-to-microservices.md
multi-environment-deployment.md
release-management.md
examples/
index.md
faq.md
getting-started/
first-increment.md
index.md
installation.md
glossary/
index-by-category.md
overview.md
README.md
terms/
ac-id.md
architect-agent.md
bidirectional-sync.md
increments.md
intelligent-living-docs-sync.md
intelligent-model-selection.md
living-docs.md
metadata-json.md
plan-md.md
pm-agent.md
profile-based-sync.md
project-detection.md
project-specific-tasks.md
qa-lead-agent.md
quality-gate.md
role-orchestrator.md
skills-vs-agents.md
spec-md.md
strategic-init.md
tasks-md.md
guides/
ado-multi-project-migration.md
agent-security-best-practices.md
agent-skills-extensibility-analysis.md
agent-teams-and-swarms.md
ai-coding-benchmarks.md
analytics-dashboard.md
autonomous-execution.md
backlog-management.md
best-practices.md
bidirectional-linking.md
brainstorming.md
command-reference-by-priority.md
compliance-standards.md
core-concepts/
background-jobs.md
deterministic-llm-hybrid.md
living-documentation.md
skills-first-architecture.md
what-is-an-increment.md
who-benefits-from-living-docs.md
cross-tool-handoff.md
dashboard/
activity.md
agents.md
config.md
errors.md
hooks.md
marketplace.md
notifications.md
plugins.md
services.md
sync.md
deep-interview-mode.md
deployment-platforms.md
external-tool-sync.md
github-action-setup.md
github-integration.md
hierarchy-mapping.md
increment-status-reference.md
integrations/
external-tools-overview.md
issue-trackers.md
lazy-plugin-loading.md
life-automation.md
lsp-integration.md
meta-capability.md
migration-v024.md
migration-v031-project-fields.md
mobile/
react-native-setup-guide.md
model-selection.md
multi-project-setup.md
multi-project-sync-architecture.md
multilingual-guide.md
openclaw-agent-setup.md
plugin-management.md
project-specific-tasks.md
repository-selection.md
scheduling-and-planning.md
spec-bidirectional-sync.md
spec-commit-sync.md
specs-organization-guide.md
specweave-learning-journey.md
specweave-vs-speckit.md
status-sync-guide.md
status-sync-migration.md
strategic-init.md
sync-configuration.md
sync-strategies.md
troubleshooting/
common-errors.md
emergency-recovery.md
index.md
umbrella-sync-routing.md
why-verified-skill-matters.md
youtube-scripts/
youtube-script-skills-security-crisis.md
youtube-script-why-skills-matter.md
youtube-tutorial-script-v1.md
youtube-tutorial-script-v2.md
youtube-tutorial-script-v3.md
integrations/
generic-ai-tools.md
metrics.md
overview/
ai-revolution-context.md
claude-code-architecture.md
claude-code-basics.md
dogfooding.md
features.md
introduction.md
no-docs-needed.md
philosophy.md
plugins-ecosystem.md
skills-as-structured-expertise.md
why-specweave.md
reference/
changelog.md
command-decision-tree.md
commands.md
configuration.md
cost-tracking.md
index.md
metadata-reference.md
skills.md
use-case-guide.md
skills/
extensible/
extensible-skills-standard.md
extensible-skills.md
index.md
self-improving-skills.md
skill-development-guidelines.md
skill-generation.md
fundamentals.md
index.md
installation.md
skill-contradiction-resolution.md
skill-discovery-evaluation.md
skill-studio.md
verified/
index.md
secure-skill-factory-standard.md
skills-ecosystem-security.md
verified-skills.md
vskill-cli.md
why-skills-matter.md
workflows/
brownfield.md
deployment.md
design.md
greenfield.md
hotfix.md
implementation.md
overview.md
planning.md
research.md
validation.md
docusaurus.config.internal.ts
docusaurus.config.ts
drafts/
social-media-programmable-skills-v2.md
e2e/
hero.spec.ts
installation-upgrading.spec.ts
FAVICON-UPDATE.md
GITHUB-PAGES-DEPLOY.md
legacy/
MESSAGE_TO_USER.md
NVM_GLOBAL_PACKAGES_SOLUTION.md
package-lock.json
package.json
playwright.config.ts
README.md
remotion/
components/
BigText.tsx
index.ts
NumberTicker.tsx
SectionTitle.tsx
TerminalFrame.tsx
TypewriterText.tsx
index.ts
lib/
fonts.ts
theme.ts
Root.tsx
scenes/
Scene1Problem.tsx
Scene2Scanner.tsx
Scene3ThreeTiers.tsx
Scene4InstallFlow.tsx
Scene5ShipSafely.tsx
SpecWeaveHero.tsx
youtube/
constants.ts
scenes/
AgentSwarm.tsx
AppShowcaseGrid.tsx
AutoModeCycle.tsx
ColdOpenTypewriter.tsx
CommitTimelapse.tsx
CTASteps.tsx
IncrementFlow.tsx
LayerDiagram.tsx
QualityGates.tsx
SocialGrowthChart.tsx
StatsCounter.tsx
YouTubeRoot.tsx
scripts/
generate-hero-images-free.js
generate-hero-images.js
generate-trading-only.js
LOGO-FIX-INSTRUCTIONS.md
README.md
sync-docs.sh
SETUP-COMPLETE.md
sidebars.internal.ts
sidebars.ts
src/
__mocks__/
docusaurus-layout.tsx
docusaurus-link.tsx
docusaurus-useBaseUrl.ts
__tests__/
docusaurus-config.test.ts
link-checker.test.ts
remotion-theme.test.ts
sidebars.test.ts
smoke.test.ts
components/
Accordion/
Accordion.module.css
index.tsx
animation/
AnimateOnScroll/
AnimateOnScroll.module.css
AnimateOnScroll.test.tsx
index.tsx
CountUp/
CountUp.test.tsx
index.tsx
WordAnimation/
index.tsx
WordAnimation.module.css
WordAnimation.test.tsx
Callouts/
Callouts.module.css
index.tsx
CardGroup/
CardGroup.module.css
index.tsx
cards/
ContentCard/
__tests__/
ContentCard.test.tsx
ContentCard.module.css
index.tsx
FeatureCard/
... 1600 moreShowing a partial view of a very large repo.
FAQ
specweave is a Claude Code plugin with 51 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes ado-mapper, ado-multi-project, ado-resource-validator. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is specweave?
- Spec-first AI development: describe a feature → AI creates spec + plan + tasks, builds autonomously, syncs to GitHub/JIRA. Domain-expert skills for PM, Architect, Frontend, QA learn your patterns permanently. Claude Code, Codex, Cursor, Copilot & more.
- How do I install specweave?
- Run these in Claude Code: /plugin marketplace add anton-abyzov/specweave then /plugin install sw@specweave. Then prompt normally.
- Does specweave auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is specweave free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.