arjunprabhulal/agent-skills / skills/agent-lifecycle/agent-scoping
agent-scoping
VerifiedTurns a vague agent idea into a reviewable agent spec — the jobs it does, the boundaries it must not cross, and the criteria that decide whether it works. Use this whenever the user talks about building an agent, an assistant, a bot, or an automation, even if they only describe the idea informally and never ask for a spec — a request like "build an agent that handles X" with no written scope is exactly the trigger. Also use it when an existing agent's purpose has drifted and needs restating. Don't use it for choosing tools, models, or architecture, or for writing eval cases, though it produces the raw material for both.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 5.6 KB |
| references/agent-spec-template.md | markdown | 2.4 KB |
| references/scoping-questions.md | markdown | 3.5 KB |
references/agent-spec-template.md
View on GitHub# Agent Spec: <name>
**Status:** draft | in review | approved
**Owner:** <who decides scope disputes>
**Last updated:** <YYYY-MM-DD>
## 1. One-paragraph summary
What this agent does, for whom, and what it replaces. If a new engineer reads only this
paragraph, they should be able to describe the agent correctly.
## 2. Users
| User | Context they are in | What they have already |
| --- | --- | --- |
| | | |
Note anything about the user that changes the design: expertise, urgency, whether they can
verify the agent's output, whether they are technical.
## 3. Jobs
For each job the agent is responsible for:
### Job 1: <phrased from the user's side>
- **Trigger:** what starts it
- **Input:** what the user provides
- **Done means:** the observable end state
- **Frequency:** rough volume, if known
Repeat for each job. Three to seven is the healthy range.
## 4. Boundaries
### Not yet
Plausibly in scope, deliberately deferred. Note what would need to change to pull it in.
- <item> — deferred because <reason>
### Never
Out of bounds by design. Note why, since these are the ones people will challenge.
- <item> — excluded because <reason>
## 5. Success criteria
| # | Criterion | Target | How measured | Judge |
| --- | --- | --- | --- | --- |
| 1 | | | | |
Include at minimum: task success rate, acceptable failure mode, latency/cost if constrained,
and escalation path.
## 6. Failure handling
- **When the agent cannot complete a job:** what it should do instead
- **When it is uncertain:** ask, guess and flag, or stop
- **Escalation path:** who or what receives the handoff
## 7. Worst plausible outcome
The most damaging thing this agent could realistically do, and what prevents it. This
section feeds directly into the permission model in `agent-hardening`.
## 8. Constraints
Anything fixed before design starts: data residency, existing systems it must use, budget,
deadline, compliance requirements, approved model providers.
## 9. Open assumptions
Everything written above that has not been confirmed by the owner. Keep this section alive —
move items out as they are settled rather than deleting the heading.
| Assumption | Impact if wrong | Confirmed by |
| --- | --- | --- |
| | | |
## 10. Out of this document
Deliberately decided in a later phase, so nobody mistakes silence here for an omission:
architecture and tool surface (`agent-design`), eval cases (`agent-evaluation`), rollout plan
(`agent-deployment`).
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 |