Part of the Overpowered skill suite. Create and activate the smallest temporary capability needed to close a real execution gap during a task, then measure whether it helped and discard or nominate it for reuse. Use only when installed skills, available tools, existing context, knowledge retrieval, and Academy candidates cannot reliably perform a material part of the objective; supports temporary skills, context instructions such as AGENTS.md fragments, and runtime tools when the harness can load them dynamically.
Coding
using-overpowered
Try itPart of the Overpowered skill suite. Route knowledge-work and enterprise-automation tasks through the smallest relevant combination of Overpowered skills, and invoke gear-up only when a material execution capability is genuinely missing. Use when multiple suite skills may apply or when starting a non-trivial task involving organizational knowledge, conflicting evidence, evolving artifacts, business rules, process automation, risky side effects, verifiable completion, or an uncovered capability gap.
What it does
Part of the Overpowered skill suite. Route knowledge-work and enterprise-automation tasks through the smallest relevant combination of Overpowered skills, and invoke gear-up only when a material execution capability is genuinely missing. Use when multiple suite skills may apply or when starting a non-trivial task involving organizational knowledge, conflicting evidence, evolving artifacts, business rules, process automation, risky side effects, verifiable completion, or an uncovered capability gap.
The skill document
Using Overpowered
Purpose
Apply the smallest set of Overpowered working methods that materially improves the task. Select process/knowledge skills before implementation mechanics; never load the suite by default and never create a new capability merely because creation is possible.
Routing protocol
Before substantial action, scan these conditions:
| Condition | Use |
|---|---|
| Material organization-specific/current/historical knowledge is missing | know-enough |
| Prior cases may help | find-precedent |
| Answer lives in structured files | ask-the-data |
| Sources materially disagree | reconcile |
| Versions/snapshots must be compared | what-changed |
| Plan depends on hidden premises | assumption-audit |
| Rules/process have likely non-happy paths | find-the-exceptions |
| Human process should become executable automation | automate-this |
| Human authority/risk boundary must be designed | human-gates |
| Side effects are broad/irreversible/costly | dry-run |
| Material claims need traceability | evidence-first |
| Work is about to be declared complete | completion-audit |
| Work must survive a context/harness boundary | checkpoint |
| A material execution gap remains after reuse/knowledge/Academy checks | gear-up |
| A qualified/proven workflow should become a durable portable skill | skillify |
Priority rules
- Understand before automating. If a process is underspecified, use
find-the-exceptionsbeforeautomate-thisfinalizes the design. - Know before guessing. Use
know-enoughwhen retrieval can resolve a material uncertainty. - Authority before analogy. Current authoritative knowledge outranks precedent for normative questions.
- Conflict before synthesis. Reconcile material disagreement before producing a single “truth.”
- Reuse before creation. Installed skills/tools, generic runtime capabilities, and relevant Academy candidates outrank
gear-upgeneration. - Create only for a proven capability gap. Missing knowledge, convenience, token pressure, or a long prompt are not capability gaps.
- Simulation before risky side effects. Use
dry-runwhen a preview meaningfully reduces risk. - Evidence before completion. Use
completion-auditbefore strong done/fixed/migrated/reconciled claims.
Do not over-compose
Do not invoke the whole suite. Typical chains are 1–4 skills. gear-up is a last-mile fallback, not a default member of a chain.
Examples:
contract clause
→ know-enough → find-precedent → human-gates
policy revision
→ what-changed → know-enough
business process automation
→ find-the-exceptions → automate-this → dry-run
data question
→ ask-the-data → completion-audit only if a strong completion claim matters
missing deterministic operation during a real task
→ reuse/search → gear-up → validate/use → Academy candidate only if valuable
Interaction rule
If a skill can discover a fact from tools or artifacts, do not ask the user for that fact. Ask humans for intent, decisions, unavailable tacit knowledge, authority, or approval required by risk policy.
Adaptive capability rule
Before gear-up, be able to state all of the following in one short block:
Material objective at risk: ...
Why existing capabilities are insufficient: ...
Why this is not a knowledge gap: ...
Academy reuse result: ...
Smallest missing capability: ...
Observable value test: ...
If that block cannot be completed credibly, do not generate a new capability.
Stop condition
Stop routing once the active skill set and existing runtime capabilities cover the material failure modes of the current task. Then execute. If a proven execution gap remains, route once through gear-up; do not continue meta-analysis or capability generation after the task can proceed reliably.
Related skills
Part of the Overpowered skill suite. Generalize and package a qualified or otherwise proven repeatable workflow into a portable Agent Skill with concise instructions, progressive disclosure, trigger-focused metadata, gotchas, and evals. Use after real execution evidence exists—especially for a Skill Academy capability ready to graduate; do not use as the hot-generation mechanism during a task or merely to save a conversation.
Part of the Overpowered skill suite. Transform a described human/business process into an executable automation design by separating deterministic steps, agentic reasoning, existing systems, and human gates; define triggers, data, decisions, exceptions, controls, and verification. Use when the goal is to automate a process, not merely understand it or interview the user about it.
Part of the Overpowered skill suite. Create a durable, self-contained state package so a fresh agent, session, or different harness can resume non-trivial work without the original chat history. Use for long-running work, context resets, handoffs, or pauses; not for simple finished tasks.
Route ambiguous agent work to the right skill, command style, and effort level. Use when a task mentions skills, agents, workflows, lifecycle commands, revie...
10 installs
Minimize tool call overhead. Every tool call costs tokens and latency. This skill teaches agents to batch independent calls, avoid redundant reads, cache results within a session, prefer single powerful commands over multiple weak ones, and track a 'tool budget'.