Updated 2d ago
by Cynnamoroll
factory-stack
Agentic skills for Factory's Droids
22 GitHub stars (22)
+22 in 6 days
| Period | New stars |
|---|---|
| Nov 17 | +3 |
- 25 skills (25 skills found in its SKILL.md files)
- 2 forks (2 forks)
- 2d ago last update (Last updated 2d ago)
Install
Skills CLI
npx skills add Cynnamoroll/factory-stack
Asks which skills and agents to install. Just one: npx skills add Cynnamoroll/factory-stack --skill add-guardrail — add -g for every project.
Claude Code
git clone https://github.com/Cynnamoroll/factory-stackcp -r "factory-stack/plugins/factory-stack/skills/add-guardrail" ~/.claude/skills/
Copies the add-guardrail skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add Cynnamoroll/factory-stack
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.
-
add-guardrail
Block repeated mistakes with types, lint, CI, hooks, or permission rules, with AGENTS.md last. Use after a correction recurs or to mine past sessions with droid search; not for opening /hooks or editing permissionRules by hand.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ add-guardrail/ SKILL.md -
adversarial-review
Attack a risky diff with parallel read-only reviewers and verify every finding. Use before merging; use /review for routine review, simplify for reuse, quality, and efficiency, or check-blast-radius for fallout outside the diff.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ adversarial-review/ SKILL.md -
build-feature
Design in Spec mode, build, and verify with prove-it-works. Use for features, prototypes, and visual parity; use Spec mode alone for plans, or refactoring-playbook for large refactors, migrations, and dependency upgrades.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ build-feature/ SKILL.md -
check-blast-radius
Find breakage outside the diff and prove it with a repro or test. Use for fallout beyond changed lines; use adversarial-review to attack the diff itself or /review for routine review.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ check-blast-radius/ SKILL.md -
create-tla-model
Model stateful flows, protocols, and state machines in TLA+. Use for new formal models of behavior tests rarely cover; use tla-check to re-check models or maintain-tla-model after code changes.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ create-tla-model/ SKILL.md -
create-verify-skill
Create a missing project verify-<app> skill using agent-browser for web apps or tuistory for terminal apps. Use maintain-verify-skill for drift, /create-skill for generic skills, or agent-browser or tuistory for a one-time drive.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ create-verify-skill/ SKILL.md -
dev-workflow
Set session autonomy, reply, comment, and fan-out rules at the start of coding. Use AGENTS.md for repository conventions and a task-specific skill for workflows such as fixing bugs or shipping PRs.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ dev-workflow/ SKILL.md -
engineering-principles
Apply named principles to coding or review decisions, such as fix root causes or explain the number. Read only relevant files; use AGENTS.md for repository rules, prove-it-works or vet-measurement for verification procedures.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ engineering-principles/ SKILL.md -
explain-how
Explain current code with file references and explorer subagents. Use for unfamiliar code or how-it-works questions; use explain-why for history or rationale, or a bare explorer Task for quick lookups.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ explain-how/ SKILL.md -
explain-why
Explain code rationale from git, PRs, issues, and connected MCP sources with citations. Use for design rationale, regressions, and postmortems; use explain-how for current behavior or droid search for session history.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ explain-why/ SKILL.md -
fix-bug
Reproduce a defect, fix its root cause, and verify the repro with prove-it-works. Use for defect reports; use Normal mode for direct fixes needing no repro-first loop, or tune-perf for performance regressions.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ fix-bug/ SKILL.md -
maintain-tla-model
Update TLA+ models after changes to covered code, then run tla-check. Use create-tla-model for first models or tla-check to check unchanged models.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ maintain-tla-model/ SKILL.md -
maintain-verify-skill
Refresh a drifted project verify-<app> skill after feature changes. Use create-verify-skill for the first skill, or agent-browser or tuistory for a one-time drive.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ maintain-verify-skill/ SKILL.md -
prove-it-works
Verify fixes, features, and refactors in the running system using verify-<app>, otherwise agent-browser or tuistory, plus tests. Use before finishing; use /review or adversarial-review for diffs, or simplify for reuse, quality, and efficiency.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ prove-it-works/ SKILL.md -
race-worktrees
Race independent droid exec candidates in separate worktrees and combine their strongest parts. Use for competing designs; use Missions for multiple features or Spec mode for one plan.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ race-worktrees/ SKILL.md -
session-recap
Recap changes, files, decisions, and pending user calls since the last message or across past sessions. Use when returning to work; use droid search, droid resume, or session-navigation to find, list, or resume sessions.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ session-recap/ SKILL.md -
sharpen-prompt
Deepen a vague or broad prompt without expanding scope before Spec mode or a Mission. Use Spec mode directly once the request is sharp.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ sharpen-prompt/ SKILL.md -
ship-pr
Verify each PR in an isolated worktree, run simplify, and open it with gh. Use for completed work ready for review; use bare gh pr create if those passes are unnecessary, or watch-pr for an open PR.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ ship-pr/ SKILL.md -
test-first
Write a failing behavior test, make it pass, then refactor. Use for TDD, regression tests, or bugs with obvious repros; use eval-runs or eval-hillclimb for skill or prompt evals.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ test-first/ SKILL.md -
tighten-prose
Cut filler, hedging, and stock phrasing while applying technical-writing rules. Use for READMEs, docs, PRs, commits, and comments; use simplify for code reuse, quality, and efficiency.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ tighten-prose/ SKILL.md -
tla-check
Check existing TLA+ models with TLC, render states, and report violations. Use to verify models or run the checker; use create-tla-model or maintain-tla-model for edits, or eval-runs or eval-hillclimb for skill or prompt evals.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ tla-check/ SKILL.md -
tune-perf
Measure, run vet-measurement, change one thing, and remeasure slowdowns, performance regressions, or metric climbs. Use fix-bug for correctness or vet-measurement for numbers alone; not for unmeasured refactors.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ tune-perf/ SKILL.md -
unattended-run
Run unattended work with Loop, a decision log, and resumable wip: commits. Use when the user hands off and steps away; use Missions for multiple features or Automations for scheduled jobs.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ unattended-run/ SKILL.md -
vet-measurement
Vet a decision-driving measurement's limiter, tuning, limits, errors, repeatability, and relevance, including within tune-perf. Use before trusting, reporting, or acting; use eval-runs or eval-hillclimb for skill or prompt evals, or tune-perf to change performance.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ vet-measurement/ SKILL.md -
watch-pr
Watch an open PR to green, triage bot and human comments, and fix CI. Use /install-code-review to set up automated review or follow-up-on-pr for a one-time merge-ready pass.
plugins/factory-stack/ on GitHub (opens in a new tab)skills/ watch-pr/ 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.