software-factory-skills

Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.

Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.

Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via plugin-dev:skill-development + unslop, optionally pulling fresh evidence from recent transcripts.

Watch an open PR — fix failing CI, handle the straightforward review comments, and drive it to a mergeable state. Claude Code analog of Cursor's built-in /babysit. Use after opening a PR when the user wants the agent to shepherd it without re-prompting. Use this skill when the user asks for babysit or the task clearly matches this workflow.

Captures before/after screenshots of web pages or elements for visual comparison. Use when user says "take before and after", "screenshot comparison", "visual diff", "PR screenshots", "compare old and new", or needs to document UI changes. Accepts two URLs (file://, http://, https://) or two image paths.

Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X', 'what could this break', reviewing a small diff you don't trust, or a brief that asserts something about existing code ('make X public', 'X already handles Y') before you design against that assertion.

Restate the last message in plain human language, with no jargon. Use for /bro or when asked to say it plainly.

Use when multiple workflows duplicate the same operational logic, when deciding what belongs in actions vs shared services, or when refactoring repeated operational blocks across domain flows. Use when adding new features that share mechanics with existing ones.

Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", "make a driver skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.

Remove AI-generated code slop and clean up code style Use this skill when the user asks for deslop or the task clearly matches this workflow.

Records visual proof while testing UI behavior — the agent tests the app hands-on via computer use while a screen recording with structured test/assertion annotations captures the session — then posts the video and a results summary to the requested destination. Use when changed runtime behavior needs observable verification, including headless environments (scripted screenshots and probes) and non-UI changes (measured numbers, output pairs).

Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions via show-me-your-work. Use for /figure-it-out, 'figure it out', a large migration, or when no narrower playbook applies.

Find failing PR checks, inspect logs or external check links, and apply focused fixes Use this skill when the user asks for fix ci or the task clearly matches this workflow.

Resolve merge conflicts non-interactively, validate build and tests, and finalize conflict resolution Use this skill when the user asks for fix merge conflicts or the task clearly matches this workflow.

Fetch and summarize review comments from the active pull request Use this skill when the user asks for get pr comments or the task clearly matches this workflow.

Address Greptile feedback on a PR, MR, or shelved changelist through bounded review and fix cycles. Use when the task includes a Greptile review loop. Supports the alternate @greptile-apps trigger for large PRs.

Run the greploop workflow with the @greptile-apps trigger when the normal trigger refuses a large PR. Requires the greploop skill installed alongside this entrypoint.

Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.

Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or "audit the verify skill".

Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".

Use this skill when executing software work governed by Mission Control or a similar software factory. Preserve Mission, WorkOrder, Task, Attempt, evidence, pull-request, and release lineage while keeping authority and approval boundaries explicit.

Use this skill when starting a feature, fix, or documentation change that will edit a Git repository. Isolate edits in a new worktree unless the harness already assigned one to the same task. Read-only reviews and investigations do not need a worktree.

Spawn the comment-sicko subagent, fix accepted findings, and offer encodings for claimed constraints. Use this skill when the user asks for no comments or the task clearly matches this workflow.

poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.

Apply when two or more fixes that share one premise have failed the same gate. Take a census of which actors hold the imbalance before the next fix, then question the premise instead of writing another fix that assumes it.

Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.

Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun. Use this skill when the user asks for principle build the lever or the task clearly matches this workflow.

Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.

Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 competing prototypes and compare side by side before committing.

Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.

Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.

Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share. Get the data structures right so downstream code becomes obvious. Use this skill when the user asks for principle foundational thinking or the task clearly matches this workflow.

Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.

Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem.

Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries. Converge to the same end state regardless of partial prior runs.

Apply when introducing a new internal API while old callers still exist. Migrate callers and delete the old API in the same wave instead of preserving compatibility layers.

Apply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state in the reader's head; collapse one-caller wrappers and shrink mutable scope.

Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files. Encode the domain in a structure instead of scattered conditionals.

Apply when tempted to ask about a low-risk, reversible implementation detail inside the authorized scope. Proceed and present the result, but preserve product-owner decisions, approval policy, and external-write boundaries.

Apply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don't preserve smooth intermediate states with throwaway compatibility code. Use this skill when the user asks for principle outcome oriented execution or the task clearly matches this workflow.

Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.' Use this skill when the user asks for principle prove it works or the task clearly matches this workflow.

Apply when integrating a new requirement into an existing design. Redesign as if the requirement had been a foundational assumption from day one, instead of bolting it on.

Apply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first; serialize structurally only when one shared writer is a real invariant.

Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer. Use this skill when the user asks for principle sequence verifiable units or the task clearly matches this workflow.

Apply when sequencing an addition, refactor, or rewrite. Remove dead code, redundant validators, and stub references first, then build on the simpler base.

Apply when you write, change, or keep a test. Call the code the way its users do and assert the result they observe against a literal expected value. If the test would still pass when every imported function returns undefined, rewrite the assertion or delete the test.

Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, refuse to lie to the compiler, exhaust variants, derive from authoritative schemas.

Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief. Use for 'recall my work on X', 'catch me up', 'what have I been working on', 'where did I leave off', before starting or resuming work, and before telling the user that something was never recorded.

Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.