anton-abyzov/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.

This repository also configures its own agents. See what specweave tells them →

166Stars on the repository
28Mods indexed here, across every type
todayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

sw-do

01

anton-abyzov/specweave

Skill Claude Code

Work a SpecWeave increment task by task - claim, implement inside its Files, test, commit, done with evidence - alone, unattended or in lanes, then close. Use for "implement", "continue", "auto".

not rated 166 +1 changed 2d ago A SkillSpector: pass 46 tokens original MIT

sw-handoff

02

anton-abyzov/specweave

Skill Claude Code

Hand work to another tool, account or machine and pick it up there, in two words. Use when the user says "hand off", "hand off all", "out of tokens", "switching accounts", "pick up" or "continue".

not rated 166 +1 changed 2d ago A SkillSpector: pass 51 tokens original MIT

sw-increment

03

anton-abyzov/specweave

Skill Claude Code

Plan work as a SpecWeave increment - one spec.md with Problem, Scope, numbered ACs, Approach and Tasks - before writing code. Use for "plan a feature", "new increment", "let's build X".

not rated 166 +1 changed 2d ago A SkillSpector: pass 46 tokens original MIT

sw-review

04

anton-abyzov/specweave

Skill Claude Code

Adversarial review of an increment before it ships, by a fresh context or another model family; every finding cites path:line and is re-verified. Use for "review", "qa", "critique this".

not rated 166 +1 changed 4d ago A SkillSpector: pass 45 tokens original MIT

sw-jev

05

anton-abyzov/specweave

Skill Claude Code

Use Jev or optional OpenAI Decisions for bounded routing, shell-command risk, text screening and failure triage. Use for "jev", "system one", or "classify this".

not rated 166 +1 changed 13d ago C 38 tokens original MIT

sw-auto

06

anton-abyzov/specweave

Skill Claude CodeCodex

Run a SpecWeave increment unattended until every task is done, then verify and close - the Unattended section of sw-do. Use for "auto mode", "run until done".

not rated 166 +1 changed 4d ago A 38 tokens original MIT

sw-done

07

anton-abyzov/specweave

Skill Claude Code

Close a SpecWeave increment - every task done or skipped, specweave verify green, a fresh-context review, then specweave complete. Use for "close it", "we are done", "finish up".

not rated 166 +1 changed 4d ago A 45 tokens original MIT

sw-project

08

anton-abyzov/specweave

Skill Claude Code

Keep a project's goal, decisions, work items, artifacts and briefs portable across AI tools and accounts. Use for project coordination, "project brief", "what is this project about".

not rated 166 +1 today A 36 tokens original MIT

sw-sync

09

anton-abyzov/specweave

Skill Claude Code

Sync SpecWeave increments with GitHub, Jira or Azure DevOps - push progress, pull or import issues, check token and health, run setup. Use for "sync", "push to GitHub", "import issues".

not rated 166 +1 today A 46 tokens original MIT

sw-glossary

10

anton-abyzov/specweave

Skill Claude Code

Build the shared language - interview the user term by term and write GLOSSARY.md with what each term means in the business, the data, the code and the UI. Use for "glossary", "ubiquitous language".

not rated 166 +1 today A 49 tokens copy · 95% MIT

sw-grill-me

11

anton-abyzov/specweave

Skill Claude Code

Interview the user relentlessly, in rounds, until every decision in a plan is settled; facts are your job, decisions are theirs. Use for "grill me", "interview me", "stress-test this plan".

not rated 166 +1 today A 44 tokens copy · 97% MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: