Skip to content

porada/domfiles / skills/refine-agent-workflow

refine-agent-workflow

Verified

Recommend focused improvements to agent instructions and workflows.

FileKindSize
README.mdmarkdown653 B
SKILL.mdskill md2.9 KB
references/guidance-recovery.mdmarkdown1.4 KB
references/refine-agent-workflow.mdmarkdown6.9 KB

references/guidance-recovery.md

View on GitHub
# Guidance Recovery

Determine whether the affected guidance is required. A missing local target, a malformed destination, an HTTP response reporting the resource as missing or permanently unavailable, or a verified conflict with current behavior indicates defective guidance. Access restrictions, authentication problems, network failures, and HTTP server errors alone don’t establish a defect. Report verified defects with evidence and recommend updating the skill.

When required guidance is defective, use a complete available fallback or verify a replacement against authoritative evidence. Don’t substitute an unverified location. Ask before changing an explicitly selected version or another material task assumption. Problems with optional or supporting guidance don’t stop the workflow.

For retrieval failures that don’t establish a defect, correct a demonstrated path or invocation mistake, make bounded retries, or use an equivalent method. Keep the target, authorized effects, authentication, and disclosure boundaries unchanged. Use the supported grant or correction process for access restrictions.

When recovery cannot proceed, report the affected resource, attempted methods, failure evidence including the exact error when available, and smallest corrective action. Continue only independent authorized work. A procedural waiver doesn’t supply missing evidence or establish that an omitted or failed step succeeded.
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated 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: 322kUpdated Claude CodeCodexVerifiedInstall