Kevin Veen-BirkenbachandClaude Opus 5.5
2fbbd7386c
Adds kvb-transcend (collector), kvb-skills-transcend (into the skills repo) and kvb-code-transcend (into the current repo). transcend.py scans the own scratchpad, peer scratchpads and the agent homes for scripts, tests and skills the skills repo does not ship, skips secret-named and oversized files, and remembers carried/dropped decisions by content digest in the gitignored .state/transcend.json, so a rescan offers only new or changed candidates. Wired into kvb-skills-tune (own scripts), kvb-code-tune step 6 (measurements) and kvb-skills-dream step 7. Seven descriptions are tightened to stay inside the 1300-word listing budget. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2.8 KiB
2.8 KiB
name, description
| name | description |
|---|---|
| kvb-think-dialectic | Reach a defensible conclusion by thesis, independent skeptic antithesis and synthesis, iterated to ~99% confidence. Trigger for any consequential root cause, design or decision that is uncertain and expensive to get wrong. |
Reach the truth by dialectic, not by first guess. Do not stop at a plausible answer; drive the loop until a thesis survives every attack at ~99% confidence.
Before you start: listen
Invoke the kvb-think-listen skill first. Do not begin the dialectic until you
have gathered every requirement, constraint, and success criterion the task
needs. A dialectic run on the wrong question wastes the whole loop. Return to
kvb-think-listen mid-loop whenever an objection turns on a fact only the
operator holds.
When another skill or an autonomous run (kvb-org-robot, kvb-ci-observe, a loop) invoked this skill, derive the requirements from the task and the evidence instead of asking; ask only when an operator-only fact blocks the conclusion.
The loop
- Thesis. Form the strongest initial claim you can, grounded in evidence,
not assumption. Deep-inspect every source you can reach: the source code and
git history; the running containers (exec, logs, inspect through whatever
make or CLI helpers the project exposes); CI logs and artifacts; tests; docs.
Cite
file:lineand command output — never a bare assertion. - Antithesis. Spawn MULTIPLE independent skeptics (parallel subagents or a
workflow, on the default model as the
kvb-org-performskill requires) whose only job is to REFUTE the thesis. Each re-inspects the sources itself and defaults to "refuted" on any concrete hole. Give diverse skeptics diverse lenses: correctness, an alternate mechanism, does-it- reproduce, does-the-fix-break-something-else. - Synthesis. Fold every surviving objection back into a refined thesis. A skeptic that found a real hole replaces or corrects the thesis; a skeptic that failed to refute raises confidence.
- Iterate. Repeat thesis → antithesis → synthesis until a full skeptic
round finds no new hole and the thesis holds at ~99%. If confidence stalls
below 99%, name the exact residual and the evidence that would close it, then
go get that evidence (more inspection, or
kvb-think-listenfor an operator-only fact) and loop again.
Rules
- Executed evidence beats reasoning: run it, exec into it, read the log. A thesis backed only by static reasoning caps in the low nineties.
- The antithesis MUST be independent — never let the thesis-author be its own sole skeptic.
- Diversity over redundancy: skeptics with different lenses catch failure modes identical skeptics miss.
- Report the final thesis with its evidence AND the losing objections, so the operator sees why it survived.