编程

ken-gain

试用

Show ken measured impact as a scoreboard from its own benchmark results. Honest empty state when none exist. One-shot display.

它能做什么

Show ken measured impact as a scoreboard from its own benchmark results. Honest empty state when none exist. One-shot display.

技能文档

Ken Gain

Display the scoreboard when invoked. One-shot: do NOT change mode, write flag files, or persist anything.

Source of truth

The only figures this card may show are medians from ken's own runs recorded in benchmarks/results/ of the ken repo. Render the recorded figures as plain ASCII bars (bar length = measured range, label = exact figure).

If benchmarks/results/ has no ken results yet, print:

  ken gain: no measured numbers yet.

  Nothing is claimed that wasn't measured. Run the harness in benchmarks/
  (see benchmarks/README.md; needs API keys in .env) to produce the first
  real entry.

  This repo, today:  /ken-debt  (the counted ceilings ledger)
                     /ken-audit (what's rewritable right now)

Honesty boundary

Figures are benchmark medians, not this repo. NEVER print a per-repo savings number ("you saved X lines/tokens here"): the unbuilt version was never written, so there is no real baseline to subtract from in a live repo. The only real per-repo figures come from /ken-debt (a counted ledger), and this card points there instead of inventing one. Never render another project's numbers as ken's.

Boundaries

One-shot display. Edits nothing, changes no mode. "stop ken" or "normal mode": revert.

相关技能

ken-help

Quick reference for ken modes, skills, and commands. One-shot display.

ken

Thompson-mode discipline for any coding task: think first, build bottom-up, brute force until measured, rewrite over patch. Not for non-coding requests.

Minimalist Gain

Report what minimalist actually measured in this session or project — LOC avoided, scope rejected, dependencies declined. Use when the user says "minimalist...

1 次安装

Kb Query

Answer Research KB questions from the team Gitea-backed knowledge base with OpenClaw reasoning, optional reference attachments, stable citations, OpenClaw-led evidence selection, and optional high-value Q&A persistence.

1 次安装

kenkyu research

Run deep, multi-source research queries via the kenkyu API and get back a cited answer with sources. Use for any question that benefits from a thorough, sourced investigation rather than a quick answer.

thinking-kepner-tregoe

Use when a selective defect needs IS/IS-NOT difference analysis or a consequential option choice needs must/want weighting and adverse-consequence comparison.

1 次安装