fix(skills): trim 22 descriptions back under the listing budget

The skill listing stood at 1498 of 1500 words; the trimmed descriptions bring it to 1420, so the new kvb-check-ansible description fits without pushing others out.

🎯 Fix: 95 %
💥 Break: 1 %
💸 Cost: 99 %
⏱️ Time: 100 %
🛡️ Security: 100 %
🏆 Score: 95
🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 %

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

skills/kvb-agent-relax/SKILL.md

@@ -2,7 +2,7 @@
 name: kvb-agent-relax
 description: >
   Relax this agent on kvb-org-evening: finish its task, end its loops, start
-  nothing new. Trigger on its request.
+  nothing new.
 ---
 
 Verify first: `${CLAUDE_SKILL_DIR}/../kvb-org-sunset/scripts/night.py status`

skills/kvb-agent-sleep/SKILL.md

@@ -2,7 +2,7 @@
 name: kvb-agent-sleep
 description: >
   Put this agent to sleep on kvb-org-sunset: park work, end loops, write a
-  morning handover, stay idle. Trigger on its request.
+  morning handover, stay idle.
 ---
 
 Verify first: `${CLAUDE_SKILL_DIR}/../kvb-org-sunset/scripts/night.py status`

skills/kvb-agent-wakeup/SKILL.md

@@ -2,7 +2,7 @@
 name: kvb-agent-wakeup
 description: >
   Wake this agent from kvb-agent-relax or kvb-agent-sleep into its old roles;
-  kvb-org-sunrise sends it to all. Trigger on its request.
+  kvb-org-sunrise sends it to all.
 ---
 
 Verify first with `${CLAUDE_SKILL_DIR}/../kvb-org-sunset/scripts/night.py

skills/kvb-check-break-risk/SKILL.md

@@ -2,8 +2,8 @@
 name: kvb-check-break-risk
 description: >
   Derive the break-risk percentage from measurement, not feel, for every
-  `kvb-check-confidence` report; also when the operator asks "what could this
+  `kvb-check-confidence` report; also on "what could this break?" or a named
-  break?" or names a break-risk threshold.
+  break-risk threshold.
 ---
 
 Break risk is the probability the change breaks something it did not intend to

skills/kvb-check-security/SKILL.md

@@ -1,9 +1,8 @@
 ---
 name: kvb-check-security
 description: >
-  Run the MEDUSA scanner on a repository, working tree or secret stores:
+  MEDUSA security scan of a repository, working tree or secret stores:
-  security scans, vetting a repo, leaked secrets in chat or shell history.
+  vetting a repo, leaked secrets in chat or shell history. Defensive only.
-  Defensive only.
 ---
 
 MEDUSA is a defensive AI-first security scanner (40,000+ patterns: CVEs, prompt injection, MCP tool poisoning, leaked secrets).

skills/kvb-ci-artifacts/SKILL.md

@@ -1,9 +1,8 @@
 ---
 name: kvb-ci-artifacts
 description: >
-  Pull a CI run's failed job logs (also mid-run), clustered by error line,
+  Pull failed CI job logs (also mid-run), clustered by error line, and
-  and cause-holding artifacts. Trigger when a CI failure needs explaining,
+  cause-holding artifacts. Trigger to explain a CI failure, and from triage.
-  and from triage.
 ---
 
 A job log tells you what broke. An artifact tells you why. Investigating a CI

skills/kvb-ci-observe/SKILL.md

@@ -1,8 +1,8 @@
 ---
 name: kvb-ci-observe
 description: >
-  Watch a CI run, pipeline, build or log on a cadence and triage new failures.
+  Watch a CI run, pipeline, build or log on a cadence, triaging and fixing
-  Trigger on a request to keep monitoring and fix regressions.
+  new failures. Trigger when asked to keep monitoring.
 ---
 
 Keep a target under watch and act only when it degrades: the loop watches,

skills/kvb-ci-triage/SKILL.md

@@ -1,8 +1,8 @@
 ---
 name: kvb-ci-triage
 description: >
-  Triage a failing CI run to verified root causes and real fixes, one
+  Triage a failing CI run or build, test or deploy pipeline to verified root
-  cluster per worktree. Trigger when a build, test or deploy pipeline fails.
+  causes and real fixes, one cluster per worktree.
 ---
 
 Drive a red pipeline green by root cause. Every failing job is its own

skills/kvb-code-refactor/SKILL.md

@@ -2,8 +2,7 @@
 name: kvb-code-refactor
 description: >
   Refactor every uncommitted file to the project's standards without
-  changing behaviour. Trigger when asked to clean up, tidy or polish the
+  changing behaviour. Trigger when asked to clean up, tidy or polish them.
-  current changes.
 ---
 
 The unit of work is the uncommitted change set, not the repository. Behaviour

skills/kvb-code-scope-guard/SKILL.md

@@ -2,7 +2,7 @@
 name: kvb-code-scope-guard
 description: >
   Deliver exactly what was asked. Trigger on every task creating files,
-  commands or commits, on autonomous runs and hand-overs, and when asked why
+  commands or commits, autonomous runs, hand-overs, and when asked why
   something unrequested exists.
 ---
 

skills/kvb-create-plan/SKILL.md

@@ -2,7 +2,7 @@
 name: kvb-create-plan
 description: >
   Turn a request into an objective-oriented plan for kvb-org-robot.
-  Trigger on a request for a plan, breakdown or strategy before work starts.
+  Trigger on a plan, breakdown or strategy request before work starts.
 ---
 
 Produce a plan whose every item is an outcome with a check, then execute it

skills/kvb-dream/SKILL.md

@@ -2,8 +2,7 @@
 name: kvb-dream
 description: >
   Process the last 24 hours of every repository and session: memory,
-  improvements, kvb-optimize, cleanups. Trigger on a request to learn from
+  improvements, kvb-optimize, cleanups. Trigger to learn from recent work.
-  recent work.
 ---
 
 Replay what happened, separate what held from what broke, keep only

skills/kvb-git-changelog/SKILL.md

@@ -1,9 +1,9 @@
 ---
 name: kvb-git-changelog
 description: >
-  Write the release message for `pkgmgr release`; prints only. Trigger on
+  Write the `pkgmgr release` message; prints only. Trigger on "release
-  "release message", "changelog entry", before cutting a
+  message", "changelog entry", before cutting a release, or pkgmgr's
-  release, or on pkgmgr's markdown-lint rejection.
+  markdown-lint rejection.
 ---
 
 Read `reasons.md` next to this file when a rule seems not to fit or a lint

skills/kvb-git-commit-no-verify/SKILL.md

@@ -1,9 +1,8 @@
 ---
 name: kvb-git-commit-no-verify
 description: >
-  Commit the staged changes with --no-verify. Trigger on any no-verify commit
+  Commit the staged changes with --no-verify on request; invoking it IS the
-  request; invoking it IS the per-commit --no-verify authorization, never
+  per-commit --no-verify authorization, never carried over to later commits.
-  carried over to later commits.
 ---
 
 1. Run the kvb-code-clean pass (comments, defaults, principles) over the

skills/kvb-git-merge-fix/SKILL.md

@@ -1,7 +1,8 @@
 ---
 name: kvb-git-merge-fix
 description: >
-  Find commits on any branch carrying a described fix and merge them here. Trigger on a request to bring over a fix from another branch.
+  Bring over a described fix: find the commits carrying it on any branch and
+  merge them here.
 ---
 
 The free text after the skill name is the fix description and the only input.

skills/kvb-help/SKILL.md

@@ -2,7 +2,7 @@
 name: kvb-help
 description: >
   List and explain every session skill. Trigger on "welche skills gibt es",
-  "skill übersicht", or questions on what skills exist or what one does.
+  "skill übersicht", or questions on what skills exist or do.
 ---
 
 Produce a one-shot overview of every skill the session can invoke:

skills/kvb-org-coordinate/SKILL.md

@@ -2,8 +2,7 @@
 name: kvb-org-coordinate
 description: >
   Coordinate a failure or fix with agents on related branches through
-  merges: claim, ask, report. Trigger when a fix touches code other
+  merges: claim, ask, report. Trigger when a fix touches shared code.
-  branches share.
 ---
 
 Run the `kvb-org-organize` skill's **Peer protocol**, its `lineage.md`

skills/kvb-org-robot/SKILL.md

@@ -2,8 +2,7 @@
 name: kvb-org-robot
 description: >
   Work fully autonomously to a goal: no check-ins, no stop before it, only
-  commands already cleared. Trigger when the operator wants hands-off,
+  commands already cleared. Trigger on a hands-off request.
-  uninterrupted execution.
 ---
 
 Operate as an autonomous robot: given a goal, reach it without hand-holding.

skills/kvb-skill-auto/SKILL.md

@@ -1,9 +1,8 @@
 ---
 name: kvb-skill-auto
 description: >
-  Turn operator repetition into a skill. Trigger when the operator repeats an
+  Turn an instruction, correction or prompt pattern the operator repeats
-  instruction, correction or prompt pattern thrice, or says they keep
+  thrice into a skill, also when they say they keep repeating themselves.
-  repeating themselves.
 ---
 
 Its objective is the `kvb-skill-tune` skill's **Objective** section: a skill is

skills/kvb-skill-compile/SKILL.md

@@ -1,8 +1,8 @@
 ---
 name: kvb-skill-compile
 description: >
-  Turn deterministic skill steps into tested scripts in the skill's own repo.
+  Turn deterministic skill steps (fixed command sequences) into tested
-  Trigger on a skill step that is a fixed command sequence.
+  scripts in the skill's own repo.
 ---
 
 A deterministic step's result follows from its inputs alone: fixed command

skills/kvb-skill-silence/SKILL.md

@@ -1,8 +1,8 @@
 ---
 name: kvb-skill-silence
 description: >
-  Cut the tokens and agent messages the skills of this repository and of the
+  Cut the tokens and agent messages this repository's skills and the skills
-  skills repo cost. kvb-optimize runs it.
+  repo cost. kvb-optimize runs it.
 ---
 
 Every word in the skill listing, a loaded SKILL.md or a hook's output is paid

skills/kvb-think-explain/SKILL.md

@@ -1,8 +1,8 @@
 ---
 name: kvb-think-explain
 description: >
-  Explain code and its interactions. Trigger when the operator asks what code
+  Explain on request what code does, how a mechanism works or why
-  does, how a mechanism works or why components interact.
+  components interact.
 ---
 
 Explain the named code so an engineer who has never seen it can follow it: