realize
Skill0 starsChanged 39 days agoMITView on GitHub
Safely transform the current system toward a decided state. Use when implementing code, configuration, migrations, infrastructure, integrations, or other concrete changes, while preserving invariants and keeping the result verifiable.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- jongwony/epistemic-protocolstheir own version, first seen Oct 9, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- jongwony/epistemic-protocols★ 175same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository16 other files it gives its agents.
- create-checkSkill
- decideSkill
- design-changeSkill
- design-moduleSkill
- groundSkill
- harden-boundarySkill
- harden-checkSkill
- intentSkill
- investigateSkill
- learnSkill
- pave-pathSkill
- ratchetSkill
- specifySkill
- validateSkill
- verifySkill
- wire-checkSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Work in inspectable increments: Prefer states that can be independently understood and verified.
- Distinctive: line 18
Keep behavior observable: Add the instrumentation necessary to operate, verify, or validate new behavior.
- Distinctive: line 19
Route invalid premises backward: If implementation disproves the specification, investigation, or decision, stop forcing the implementation …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Realize
Make the chosen change real while preserving system integrity. Code existing is not completion.
Work
- Recover the contract. Know the governing intent, relevant specification, decision, invariants, and intended verification. For a small task, these may be implicit and lightweight; do not invent ceremony.
- Minimize blast radius. Make the smallest coherent change that satisfies the contract. Avoid unrelated cleanup.
- Respect architecture and product conventions. Use established boundaries and abstractions unless the decision explicitly changes them. For UI changes, inspect a comparable existing screen and its components/styles before building; preserve its visual and interaction vocabulary unless a deliberate design change is required. Do not bypass constraints for convenience.
- Preserve invariants. Protect required behavior, data integrity, security boundaries, compatibility, and operational safety.
- Work in inspectable increments. Prefer states that can be independently understood and verified. When a change depends on an unfamiliar runtime/provider boundary, prove the smallest integrated path through that boundary before expanding around the assumption. Include deployment configuration when it can invalidate the implementation.
- Harden boundaries proportionally. Validate untrusted inputs, handle external failures deliberately, bound side effects, and make retryable operations idempotent where relevant.
- Keep behavior observable. Add the instrumentation necessary to operate, verify, or validate new behavior.
- Route invalid premises backward. If implementation disproves the specification, investigation, or decision, stop forcing the implementation and return to the owning skill.
Return
Produce the actual requested change, then summarize:
- Changed
- Preserved
- Deviations from the decision/specification
- New risks or assumptions
- Verification entry points
Failure signals
Watch for scope creep, opportunistic refactors, bypassed architecture, hidden side effects, implementation that cannot be observed, and continuing after a premise has been disproven.
Done when
A coherent candidate change exists, required invariants have not knowingly been violated, and the result is in a state that can be independently verified.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.