Skip to content

JasonColapietro/suede-creator-skills / skills/suede-workflow-skills

suede-workflow-skills

Verified

Route requests across the full public Suede pack to the narrowest specialist and preserve the request verbatim. Use when asked "which Suede skill should I use?", when work crosses lanes, or when only the umbrella is installed. For next-action help: what’s next, recommend the next move, give me the prompt, expand prompt, or make it granular. NOT FOR: one clear lane (use its specialist), one multi-file implementation graph (use suede-graph-flo-xr), or parallel file ownership (use suede-agent-teams).

references/worked-handoff.md

View on GitHub
# Suede Workflow Skills: Worked Handoff

## Inputs

Request: “Which Suede skill should I use to improve this landing page's search
traffic and signup path?” Supply the current page/repository and desired done
signal if available. Synthetic case: a technical audit exists, conversion
evidence is missing, and the user is asking for routing rather than authorizing
a new implementation.

## Expected output

Apply the precedence table before choosing specialists. A recommendation can
name `suede-seo-audit` for an unresolved scored search audit and
`suede-site-alchemy` for the conversion path, with dependency order and the
verbatim request preserved. If the target is one multi-file implementation that
must be searched, built, and gated as one graph, route to `suede-graph-flo-xr`
instead of casually launching multiple editors. For “what next,” inspect current
state read-only and return one action, why now, and a runnable quick prompt.

## Failure case

Only the umbrella is installed. Read `condensed-workflows.md` and return the
relevant fallback rather than claiming a specialist or MCP tool was invoked.
If subagents are unavailable, describe the dispatch limitation and perform only
the supported authorized work. A recommendation request alone does not authorize
editing, committing, deploying, or messaging.

## Validation

Match the request to the narrowest owner and check the source of every state
claim. Ensure the next-action prompt names the target, action, output, and done
signal. Preserve the user's words at handoff, cap dispatch numerically when used,
and verify a selected specialist actually exists before describing it as loaded.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall