Updated today
by anton-abyzov
specweave
Open-source spec CLI: the spec, tasks and proof of done live in git, so any AI coding agent (Claude Code, Codex, Cursor, Copilot) can pick up where another stopped. Powers SpecWithCode: specwithcode.com
170 GitHub stars (170)
+7 in 30 days
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | −1 |
| Oct 7 | +1 |
| Oct 8 | 0 |
| Oct 9 | 0 |
| Oct 10 | 0 |
| Oct 11 | +1 |
| Oct 12 | 0 |
| Oct 13 | 0 |
| Oct 14 | 0 |
| Oct 15 | 0 |
| Oct 16 | 0 |
| Oct 17 | 0 |
| Oct 18 | 0 |
| Oct 19 | +1 |
| Oct 20 | 0 |
| Oct 21 | 0 |
| Oct 22 | 0 |
| Oct 23 | +1 |
| Oct 24 | 0 |
| Oct 25 | 0 |
| Oct 26 | 0 |
| Oct 27 | +2 |
| Oct 28 | 0 |
| Oct 29 | −1 |
| Oct 30 | +2 |
| Oct 31 | 0 |
| Nov 1 | 0 |
| Nov 2 | 0 |
| Nov 3 | 0 |
| Nov 4 | 0 |
| Nov 5 | 0 |
- 22 skills (22 skills found in its SKILL.md files)
- 20 forks (20 forks)
- Today last update (Last updated today)
Install
Skills CLI
npx skills add anton-abyzov/specweave
Asks which skills and agents to install. Just one: npx skills add anton-abyzov/specweave --skill sw-auto — add -g for every project.
Claude Code
git clone https://github.com/anton-abyzov/specweavecp -r "specweave/skills/sw-auto" ~/.claude/skills/
Copies the sw-auto skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add anton-abyzov/specweave
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
sw-auto
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".
skills/sw-auto/ on GitHub (opens in a new tab)SKILL.md -
sw-do
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", "next task".
skills/sw-do/ on GitHub (opens in a new tab)SKILL.md -
sw-done
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".
skills/sw-done/ on GitHub (opens in a new tab)SKILL.md -
sw-glossary
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".
skills/sw-glossary/ on GitHub (opens in a new tab)SKILL.md -
sw-grill-me
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".
skills/sw-grill-me/ on GitHub (opens in a new tab)SKILL.md -
sw-handoff
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" or "pick up".
skills/sw-handoff/ on GitHub (opens in a new tab)SKILL.md -
sw-increment
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".
skills/sw-increment/ on GitHub (opens in a new tab)SKILL.md -
sw-jev
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".
skills/sw-jev/ on GitHub (opens in a new tab)SKILL.md -
sw-project
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".
skills/sw-project/ on GitHub (opens in a new tab)SKILL.md -
sw-review
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".
skills/sw-review/ on GitHub (opens in a new tab)SKILL.md -
sw-sync
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".
skills/sw-sync/ on GitHub (opens in a new tab)SKILL.md -
glossary
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".
plugins/specweave/ on GitHub (opens in a new tab)skills-optional/ glossary/ SKILL.md -
jev
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".
plugins/specweave/ on GitHub (opens in a new tab)skills-optional/ jev/ SKILL.md -
project
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".
plugins/specweave/ on GitHub (opens in a new tab)skills-optional/ project/ SKILL.md -
sync
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".
plugins/specweave/ on GitHub (opens in a new tab)skills-optional/ sync/ SKILL.md -
auto
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".
plugins/specweave/ on GitHub (opens in a new tab)skills/ auto/ SKILL.md -
do
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", "next task".
plugins/specweave/ on GitHub (opens in a new tab)skills/ do/ SKILL.md -
done
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".
plugins/specweave/ on GitHub (opens in a new tab)skills/ done/ SKILL.md -
grill-me
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".
plugins/specweave/ on GitHub (opens in a new tab)skills/ grill-me/ SKILL.md -
handoff
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" or "pick up".
plugins/specweave/ on GitHub (opens in a new tab)skills/ handoff/ SKILL.md -
increment
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".
plugins/specweave/ on GitHub (opens in a new tab)skills/ increment/ SKILL.md -
review
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".
plugins/specweave/ on GitHub (opens in a new tab)skills/ review/ SKILL.md
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries.
-
ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod…
-
cavemanby JuliusBrussee 🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
-
OpenMontageby calesthio World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge…
-
oh-my-openagentby code-yeongyu OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.
-
obsidian-skillsby kepano Agent skills for Obsidian. Teach your agent to use Obsidian CLI and open formats including Markdown, Bases, JSON Canvas.