Xclaw-bot/benchmark-task-authoring

Claude Code skill: measured laws for authoring hard Terminal-Bench 2 / Harbor benchmark tasks, plus the review-pipeline map for clearing CI in one push

2Stars on the repository
10Mods indexed here, across every type
17d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

00-mission

01

Xclaw-bot/benchmark-task-authoring

Cursor rule Cursor

Cursor rule "00-mission" from Xclaw-bot/benchmark-task-authoring, covering the program authoring — always in force, priorities, in order, authorship — do not cross this line, measurements are never invented and read your category brief before you design anything.

2 17d ago A 719 tokens original MIT

05-retrieval

02

Xclaw-bot/benchmark-task-authoring

Cursor rule Cursor

Cursor rule "05-retrieval" from Xclaw-bot/benchmark-task-authoring, covering retrieve, do not re-read, cache measurements, never re-derive or re-run them, store: pipe the command's output straight in and reuse, or re-run if missing (3) or stale (4).

2 17d ago A 546 tokens original MIT

10-hardness-gate

03

Xclaw-bot/benchmark-task-authoring

Cursor rule Cursor

Cursor rule "10-hardness-gate" from Xclaw-bot/benchmark-task-authoring, covering the hardness gate, the law, why those conditions and not others, pre-build check — run before writing task files and strong probe — diagnostic, runs last.

2 17d ago A 1,669 tokens original MIT

20-design-doctrine

04

Xclaw-bot/benchmark-task-authoring

Cursor rule Cursor

Cursor rule "20-design-doctrine" from Xclaw-bot/benchmark-task-authoring, covering design doctrine — what is measured, not theorised, the decisive finding, dead ends — do not retry these, what the accepted corpus looks like and working hypothesis for new designs.

2 17d ago A 1,151 tokens original MIT

30-harbor-format

05

Xclaw-bot/benchmark-task-authoring

Cursor rule Cursor

Cursor rule "30-harbor-format" from Xclaw-bot/benchmark-task-authoring, covering harbor format — the mechanical gate, layout, task.toml, dockerfile and before every push.

2 17d ago C 1,115 tokens original MIT

40-authoring

06

Xclaw-bot/benchmark-task-authoring

Cursor rule Cursor

Cursor rule "40-authoring" from Xclaw-bot/benchmark-task-authoring, covering authoring the prose artifacts, instruction.md, the 4-section proposal, rubric alignment and instruction defects that recur.

2 17d ago A 1,028 tokens original MIT

50-verifier

07

Xclaw-bot/benchmark-task-authoring

Cursor rule Cursor

Cursor rule "50-verifier" from Xclaw-bot/benchmark-task-authoring, covering verifier craft, ground truth must be unreachable, assertions, tolerances and anti-cheat.

2 17d ago A 1,016 tokens original MIT

60-pipeline

08

Xclaw-bot/benchmark-task-authoring

Cursor rule Cursor

Cursor rule "60-pipeline" from Xclaw-bot/benchmark-task-authoring, covering pipeline and iteration, flow, the difficulty gate, economics — treat runs as scarce and reading a bad result.

2 17d ago A 964 tokens original MIT