claude

stenswf

Sten Software Workflow bundle. Issue lifecycle (plan → ship → review → apply, with PRD-mode capstone, plus ship-light single-session lite path), PRD inception (grill-me → prd-from-grill-me → prd-to-issues). Refactor-focused skills (plan-reviewer, test-file-compaction, etc.) now live in the sibling stenswr plugin.

1 on GitHubby StEnv0.27.0MITupdated 29 days ago
/

Plugin stenswf from marketplace sten-agent-skills in stevenengland/sten-agent-skills. Commands read from the repo's manifest — 28 days ago.

What it installs

Skills (27)

  • apply-loop

    Verify every open PR review thread regardless of author, fix and resolve the valid ones, leave disputed ones open with a reason, and converge on approval.

  • apply

    Apply a review — slice-mode (interactive per-suggestion) or PRD-mode (themed cleanup PR from local `<prd-review>` findings, mirrored onto the PR).

  • architecture

    Guide architectural decision-making for new projects, large refactors, or design-pattern selection.

  • bootstrap

    One-shot repo setup for stenswf planning/shipping.

  • brevity

    Plain-English brevity for internal reasoning and dialogue, preserving full prose in code, commits, PRs, plans, and reviews.

  • clean-code

    Apply clean code principles for readability, simplicity, and ease of change when writing, reviewing, or refactoring code.

  • codebase-design

    Shared deep-module vocabulary and principles for designing or improving a module's interface, finding deepening opportunities, placing seams, and making code testable and AI-navigable.

  • deliberate-peer

    Take up the peer deliberation at the given path, research the codebase and history deeply, and argue until you can accept a complete proposal or reject it by clause.

  • deliberate

    Work a blocking tension out with a peer agent in another harness until it accepts a complete proposal, then record the outcome as a decision.

  • grill-me

    Interview the user relentlessly about a plan or design until every branch of the decision tree is resolved ("grill me").

  • improve-codebase-architecture

    Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

  • lint-escape

    Tiered escape protocol for lint and type errors that cannot be resolved with clean code alone.

  • plan-light

    Lightweight planning for a well-scoped slice issue — `plan-light.md` plus a 5-field JSON identity card consumable by `ship-light`.

  • plan

    Plan a slice issue end-to-end, producing a per-task fragment tree and dispatch manifest under `.stenswf/<issue>/`.

  • prd-from-grill-me

    Create a PRD through user interview, codebase exploration, and module design, then submit as an issue.

  • prd-to-issues

    Break a PRD into independently-grabbable issues using tracer-bullet vertical slices.

  • review-loop

    Run the review engine over a live PR's new commits, post findings as fingerprinted resolvable threads, and approve on convergence.

  • review

    Review changes against an issue, slice, or PRD.

  • ship-light

    Implement a single well-scoped slice issue end-to-end in one session — branch, TDD, commit, PR, CI green.

  • ship

    Implement a slice issue by dispatching one subagent per local task fragment (TDD + clean code), run a refactor pass, file a PR, monitor CI to green, and archive the local plan on merge.

  • show-me

    Help the user understand the current topic visually with concise diagrams, code-shape sketches, and focused HTML artifacts.

  • slice-e2e

    One-shot lite pipeline dispatching `plan-light` then `ship-light` in separate subagent sessions for context separation.

  • tdd

    Test-driven development with a red-green-refactor loop for features, bug fixes, or integration tests.

  • thermo-nuclear-code-quality-review

    Run an extremely strict code-level maintainability review for giant files, spaghetti-condition growth and missed simplifications, used for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit or especially harsh maintainability review.

  • triage-issue

    Triage a raw GitHub bug-report issue into REJECT or a stenswf-shaped bug-brief plus slice without a quick-fix lane.

  • visual-pr

    Create or update a pull request description that explains why the change exists and shows its shape with show-me-style visual outlines.

  • wayfinder

    Chart a too-big-for-one-session idea as a shared map of investigation tickets on the issue tracker, resolved one at a time until the way to a PRD is clear.

View source on GitHub

More from stevenengland/sten-agent-skills

All 3 plugins →

Agentic Python codebase analysis suite. Measures complexity, hunts real bugs via Hypothesis PBT, proposes deep-module architecture RFCs, and generates a dependency-safe refactor plan.

6 skills

1

stenswr

claude

StEn Software Refactor bundle. Orthogonal, language-agnostic refactor skills across four phases: understand (comprehension-to-taste), discover (functional-bug-hunting, security-bug-hunting), critique (plan-reviewer), test hygiene (test-file-compaction lossless, test-file-refactor lossy).

6 skills

1

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

ecc

claudecodex

Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses

200 skills · 98 commands · 71 agents · 1 MCP server · hooks

affaan-m/ECC 302,088

agent-skills

claudecodex

Production-grade engineering skills covering every phase of software development: spec, plan, build, verify, review, and ship.

25 skills · 4 agents

addyosmani/agent-skills 116,782

Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data

9 skills · 9 commands · 11 agents · 1 MCP server

ruvnet/ruflo 81,589

azure

claude

Transform Claude into an Azure expert. This plugin integrates the Azure MCP server and specialized Azure skills to move beyond generic advice. It enables Claude to perform real-world tasks: listing resources, validating deployments, diagnosing infrastructure issues, and optimizing costs across 50+ Azure services.

44 skills · 1 MCP server

anthropics/claude-plugins-official 47,076

Maintain stenswf?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins3 plugins