unknowns-reference-map
Skill2 starsChanged 4 months agoMITView on GitHub
Prove semantic understanding before porting, reimplementing, or matching a reference implementation. Use when the user points at another file/package/language/repo as the desired behavior, asks for a semantics map, or wants confirmation before Codex writes code based on a reference.
In this repository11 other files it gives its agents.
- know-your-unknownsSkill
- unknowns-blindspot-passSkill
- unknowns-buy-in-docSkill
- unknowns-design-directionsSkill
- unknowns-domain-bootstrapSkill
- unknowns-implementation-notesSkill
- unknowns-intervention-brainstormSkill
- unknowns-merge-quizSkill
- unknowns-mock-before-wireSkill
- unknowns-spec-interviewSkill
- unknowns-tweakable-planSkill
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 20
Stop condition: the user confirms the map or corrects it before implementation starts.
- Distinctive: line 24
Do not implement until the semantics map is accepted unless the user explicitly overrides that gate.
- Distinctive: line 26
Use HTML when side-by-side code excerpts, highlighted notes, and correction buttons make review easier.
≈ “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
Unknowns Reference Map
Workflow
Map behavior before porting.
Return:
- Reference inventory: key behaviors, invariants, edge cases, and tests.
- Source-to-target semantic pairs.
- Preserved behavior, adapted behavior, deliberately dropped behavior.
- Gotchas where syntax translation would break semantics.
- Tests required to prove equivalence.
- Confirmation/correction prompt.
- Stop condition: the user confirms the map or corrects it before implementation starts.
Rules
Do not implement until the semantics map is accepted unless the user explicitly overrides that gate. Distinguish exact equivalence from intentional product/API adaptation.
Use HTML when side-by-side code excerpts, highlighted notes, and correction buttons make review easier.
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.