Sathvikar01/Agent-engineering-skills / agent-development-workflow
agent-development-workflow
VerifiedCoordinate the complete engineering lifecycle for substantial AI-agent or model-assisted workflow builds. Use when building, productionizing or substantially redesigning an agent, adding major tools/state/RAG/orchestration, or evaluating and hardening a whole agent system. Do not use for one bug, tiny prompt/schema/API changes, ordinary app work, simple deterministic utilities, conceptual agent explanations, or a narrow task owned by one specialist.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.7 KB |
| evals/evals.json | config | 4.3 KB |
| evals/trigger-evals.json | config | 3.4 KB |
| references/decision-and-defence.md | markdown | 1.3 KB |
references/decision-and-defence.md
View on GitHub# Material decisions and technical defence
Use for architecture, trust, quality or operational choices, not tiny edits.
| Decision | Hypothesis | Alternatives | Why chosen | Evidence | Limitation | Fallback | Status |
|---|---|---|---|---|---|---|---|
| Bounded model extraction, deterministic payment arithmetic | Document variants need interpretation | Regex-only; autonomous finance agent | Interpretation uncertain; arithmetic specified | Actual fixture/eval result or proposed experiment | Unseen layouts | Typed review-needed result | PROPOSED/VALIDATED/REJECTED/SUPERSEDED |
Do not mark proposed experiments VALIDATED. Track important AI proposals and engineer choices/tests without per-line attribution.
For “Why this architecture?”, lead with choice/boundary, then implementation, alternatives/trade-offs, observed comparisons, limits/fallback. A substantial completion defence covers what was built, boundaries, key code locations, why choices survived, test/eval versions/counts, failure modes, fallback, risks and next improvement.
Inner-loop record: planned invariant/check → diff → actual command/output → reproduced failure/root cause when present → correction → rerun/regression result → retain/revert decision. Do not manufacture a failure to fill DEBUG; if no mismatch occurred, report checks and that observation.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 471k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |