agentleFS
odinfreeodinfree/storm-ecdsa-harness/skills/proximity-prize-campaign/SKILL.md

proximity-prize-campaign

Skill4 starsChanged 21 days agoMITView on GitHub

Run a Proximity Prize (better.codes) proof lane. Read the live frontier and your campaign ledger, route the math to the exact-algebra, search and Lean skills, check dead routes, and gate every promotion on Lean and ArkLib. Includes digests of BitWonka's 31 public submission notes and of the Discussion #537 thread on the 116.13 upper-track wall.

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 6 are distinctive, and 7 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 7

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this thin overlay only for better.codes or Proximity Prize work.

    line 8
  2. Distinctive:

    Read its goal, the current work queue or overturn ledger, and the latest ownership or handover record.

    line 13
  3. Distinctive:

    Check the live benchmark frontier with the documented CLI.

    line 14
  4. Distinctive:

    Read references/campaign-gates.md before assigning work, promoting a proof, or preparing a submission.

    line 17
  5. Distinctive:

    Before attacking a track, read the matching prior art: references/bitwonka-proximity-digest.md (BitWonka's 31 notes: lower-track ledger …

    line 19
  6. Very specific:

    Use $computer-algebra-oracles to expose or falsify exact algebraic statements.

    line 27
  7. Very specific:

    Use $constraint-construction-search for faithfully finite SAT, SMT, CP-SAT, or MIP constructions.

    line 28
  8. Very specific:

    Use $exact-search-engineering only after the finite search and coverage contract are explicit and profiling identifies the bottleneck.

    line 29
  9. Very specific:

    Use $proximity-prize-frontier-archaeology immediately after an accepted frontier move to compare it only with its direct accepted …

    line 30
  10. Very specific:

    Use $accepted-proof-exact-retune when the accepted architecture is fixed and a source-bound integer model can test the smallest strict …

    line 31
  11. Very specific:

    Use $fast-lean-proof-loop for dependency-aware incremental builds and Lean-verified symbol lookup during proof iteration.

    line 32
  12. Very specific:

    Use $lean-arklib-proofs for every accepted load-bearing claim.

    line 33
  13. Distinctive:

    Read the campaign dead-route and obstruction ledger before proposing a route.

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Nöchberli (proximity-prize-campaign)

Use this thin overlay only for better.codes or Proximity Prize work. Mathematical tooling comes from the reusable exact-algebra, exact-search, constraint-search, and Lean/ArkLib skills.

Establish live state

  1. Locate your campaign repository: one authoritative clone per host.
  2. Read its goal, the current work queue or overturn ledger, and the latest ownership or handover record.
  3. Check the live benchmark frontier with the documented CLI. Persist benchmark ID, accepted score and source, required strict target, timestamp, and rebase status.
  4. Confirm the current lane owner and working tree. Clone presence does not establish ownership.

Read references/campaign-gates.md before assigning work, promoting a proof, or preparing a submission.

Before attacking a track, read the matching prior art: references/bitwonka-proximity-digest.md (BitWonka's 31 notes: lower-track ledger steps 67.67 -> 68.15, binary-upper 114.11 -> 106.25 -> 106.24 via char-2 flats and an algebraic shared top) and references/discussion537-upper-116-wall.md (the nine-author attack on the prime-field upper 116.13 wall: the 2.0035-bit fibre-max gap, every closed family, the three unchecked pin cells). Since ~19 Oct the board has four tracks: prime-field lower/upper (v20) and binary lower/upper (v3).

Route work

  • Use $computer-algebra-oracles to expose or falsify exact algebraic statements.
  • Use $constraint-construction-search for faithfully finite SAT, SMT, CP-SAT, or MIP constructions.
  • Use $exact-search-engineering only after the finite search and coverage contract are explicit and profiling identifies the bottleneck.
  • Use $proximity-prize-frontier-archaeology immediately after an accepted frontier move to compare it only with its direct accepted predecessor and isolate the actual new lever.
  • Use $accepted-proof-exact-retune when the accepted architecture is fixed and a source-bound integer model can test the smallest strict centibit step before any Lean edit.
  • Use $fast-lean-proof-loop for dependency-aware incremental builds and Lean-verified symbol lookup during proof iteration.
  • Use $lean-arklib-proofs for every accepted load-bearing claim.

Read the campaign dead-route and obstruction ledger before proposing a route. If a route requires an overlap to determine the witness, check the recorded Johnson-condition inequality first; below that threshold, reject the route rather than renaming the same obstruction.

Authority boundary

This skill does not create submission, publication, spend, installation, remote-capacity, or ownership authority. Follow the live campaign instruction and keep a record of every external change. Do not publish private notes unless explicitly authorized.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.