perf(skills): cap every description at 40 words and test the listing budget

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

skills/active-listening/SKILL.md

@@ -1,11 +1,10 @@
 ---
 name: active-listening
 description: >
-  Gather every requirement before acting. Trigger at the start of any task
+  Ask focused questions until every requirement is pinned down, then reflect
-  whose scope, constraints, or success criteria are not fully pinned down, and
+  the task back. Trigger at the start of any task with unclear scope,
-  whenever another skill needs an operator-only fact — ask focused questions
+  constraints or success criteria, and when another skill needs an
-  until nothing needed is still open, then reflect the understanding back.
+  operator-only fact.
-  Portable across projects.
 ---
 
 Do not act on a half-understood request. Listen actively until you could state

skills/advocate/SKILL.md

@@ -1,14 +1,10 @@
 ---
 name: advocate
 description: >
-  Check a commit for legal soundness before it lands: is the project licence
+  Check a commit for legal soundness: licence compatibility of added code and
-  compatible with the code and dependencies the change brings in, are the
+  dependencies, attribution, copied snippets, GDPR, trademarks. Run
-  attribution duties met, is copied code traceable, does the change touch
+  AUTOMATICALLY before every commit the operator requests; also on /advocate
-  personal data (GDPR) or third-party trademarks. Run AUTOMATICALLY, without
+  [ref|range], "rechtlich prüfen", "lizenz prüfen".
-  being asked, every time the operator requests a commit in any wording,
-  BEFORE executing that request; also on /advocate [ref|range], "rechtlich
-  prüfen", "lizenz prüfen", or when the operator asks whether a change is
-  legally clean. Portable across projects.
 ---
 
 The stance is the project's counsel: find what would make the change unlawful

skills/auto-feature/SKILL.md

@@ -1,13 +1,10 @@
 ---
 name: auto-feature
 description: >
-  Derive the missing work of a codebase and turn it into requirement
+  Derive missing work (sceptic pass for structural flaws, usability pass for
-  documents: a sceptic pass for what the code gets structurally wrong, a
+  missing features) and write requirement documents after single-select
-  usability pass for what the product does not do yet, then active-listening
+  confirmation. Trigger on /auto-feature, "was fehlt noch", "welche features
-  to confirm every proposal through single-select (radio button) questions
+  brauchen wir", or when the operator asks what to build next.
-  before anything is written. Trigger on /auto-feature, "was fehlt noch",
-  "welche features brauchen wir", or when the operator asks what to build
-  next. Portable across projects.
 ---
 
 Two blind spots produce different work: the code has defects of structure,

skills/autoskill/SKILL.md

@@ -1,10 +1,10 @@
 ---
 name: autoskill
 description: >
-  Detect operator repetition and turn it into a skill. Trigger when the
+  Turn operator repetition into a skill. Trigger when the operator gives the
-  operator gives an instruction, correction, or prompt pattern for roughly
+  same instruction, correction or prompt pattern about the third time in a
-  the third time in a conversation (or says they keep repeating themselves),
+  conversation, or says they keep repeating themselves, and the pattern is
-  and the pattern is general enough to reuse. Portable across projects.
+  reusable.
 ---
 
 Its objective is the `autotune` skill's **Objective** section: a skill is worth

skills/autotune/SKILL.md

@@ -1,12 +1,10 @@
 ---
 name: autotune
 description: >
-  Generate new agent skills and optimize existing ones so the agent works more
+  Generate new skills or optimize existing ones (fewer tokens, fewer errors,
-  efficiently: fewer input and output tokens, fewer errors, more focus, and
+  persistent learnings), each proposal confirmed by single-select question.
-  learnings that persist across sessions. Every proposal is confirmed with the
+  Trigger ONLY on an explicit request: /autotune, "autotune", "tune the
-  operator through single-select (radio button) questions. Trigger ONLY on an
+  skills"; never on your own initiative.
-  explicit operator request (/autotune, "autotune", "tune the skills"); never
-  run it on your own initiative. Portable across projects.
 ---
 
 Autotune turns observed friction into durable skills. It runs on demand only,

skills/break-risk/SKILL.md

@@ -1,10 +1,9 @@
 ---
 name: break-risk
 description: >
-  Derive the break-risk percentage from measurement instead of feel. Called by
+  Derive the break-risk percentage from measurement, not feel. Called by
-  the `confidence` skill every time it reports, and usable alone whenever the
+  `confidence` on every report; also when the operator asks "what could this
-  operator asks "what could this break?" or names a break-risk threshold.
+  break?" or names a break-risk threshold.
-  Portable across projects.
 ---
 
 Break risk is the probability the change breaks something it did not intend to

skills/changelog/SKILL.md

@@ -1,12 +1,10 @@
 ---
 name: changelog
 description: >
-  Write the release message for everything since the last release, ready to
+  Write the release message since the last release for `pkgmgr release`;
-  paste into `pkgmgr release` (its editor or `--message`). Trigger on
+  prints it only, never edits CHANGELOG.md, tags or releases. Trigger on
-  /changelog, "release message", "changelog entry", or when the operator is
+  /changelog, "release message", "changelog entry", before cutting a release,
-  about to cut a release or pastes pkgmgr's markdown-lint rejection of an
+  or on pkgmgr's markdown-lint rejection.
-  entry. Prints the message only: never edits CHANGELOG.md, never tags, never
-  releases. Portable across projects.
 ---
 
 The message is one text that pkgmgr writes to four places: the CHANGELOG.md

skills/ci-artifacts/SKILL.md

@@ -1,10 +1,9 @@
 ---
 name: ci-artifacts
 description: >
-  Get the real evidence out of a CI run: per-job logs even while the run is
+  Get the evidence out of a CI run: failed job logs (also mid-run) clustered
-  still in progress, and the artifacts that hold the cause rather than the
+  by error line, and the artifacts that hold the cause. Trigger whenever a CI
-  symptom. Trigger whenever a CI failure has to be explained, and from the
+  failure must be explained, and from triage.
-  triage skill's artifact step. Portable across projects.
 ---
 
 A job log tells you what broke. An artifact tells you why. Investigating a CI

skills/cleanup/SKILL.md

@@ -1,13 +1,10 @@
 ---
 name: cleanup
 description: >
-  Free the disk space agents filled: ask every other agent session on this
+  Free disk space agents filled: ask peer sessions what they still need,
-  machine which data it still needs, inventory /tmp, Docker and the other
+  inventory /tmp, Docker and agent dirs, and delete only what the operator
-  directories agents write to, then propose a cleanup with its risks and let
+  picks. Trigger on /cleanup, "aufräumen", "bereinigen", "platte voll", "no
-  the operator choose through single-select (radio button) and multi-select
+  space left on device".
-  (checklist) questions before anything is deleted. Trigger on /cleanup,
-  "aufräumen", "bereinigen", "platte voll", "no space left on device", or when
-  the operator asks to clean up after agents. Portable across projects.
 ---
 
 Nothing is deleted before the operator has picked it. Every candidate carries

skills/comments-clean/SKILL.md

@@ -2,12 +2,9 @@
 name: comments-clean
 description: >
   Purge explanatory comments from staged and unstaged changes. Run
-  AUTOMATICALLY, without being asked, every time the operator requests a
+  AUTOMATICALLY before every commit or stage request (commit, commit
-  commit or stage in any wording (commit, commit no-verify, stage next,
+  no-verify, stage next, socon, sobu, socobu, "commite ..."); also on
-  socon, sobu, socobu, "commite ..."), BEFORE executing that request; also
+  /comments-clean or comment complaints.
-  on /comments-clean or when the operator complains about comments.
-  Explanatory comments are bad practice: they narrate code instead of
-  letting it speak. Portable across projects.
 ---
 
 When the operator asks to commit or stage, run this audit first and only

skills/commit-next/SKILL.md

@@ -1,11 +1,9 @@
 ---
 name: commit-next
 description: >
-  Fetch every branch and check whether the staged fix already exists
+  Check every branch for the staged fix, commit the staged bundle with
-  elsewhere, then commit the staged bundle with --no-verify, stage the next
+  --no-verify, then stage and brief the next bundle. Trigger on /commit-next
-  logical bundle and brief the operator on it. Trigger on /commit-next or
+  or when the operator asks to commit and stage the next bundle in one step.
-  when the operator asks to commit and stage the next bundle in one step.
-  Portable across projects.
 ---
 
 1. `git fetch --all --prune --tags`, then hunt the staged fix across every

skills/commit-no-verify/SKILL.md

@@ -1,11 +1,9 @@
 ---
 name: commit-no-verify
 description: >
-  Commit the currently staged changes with --no-verify (skip the pre-commit
+  Commit the staged changes with --no-verify. Trigger on /commit-no-verify or
-  hooks). Trigger on /commit-no-verify or when the operator asks for a
+  any request for a no-verify commit; invoking it IS the per-commit
-  no-verify commit in any wording. Invoking this skill IS the explicit
+  authorization --no-verify requires, never carried over to later commits.
-  per-commit authorization that --no-verify requires; it never carries over
-  to later commits. Portable across projects.
 ---
 
 1. Run the comments-clean audit over the staged and unstaged changes first,

skills/confidence/SKILL.md

@@ -1,10 +1,9 @@
 ---
 name: confidence
 description: >
-  Report calibrated confidence unprompted. Trigger whenever you stage
+  Report calibrated fix confidence and break risk unprompted whenever you
-  changes, declare a fix or bundle ready, or summarize completed work the
+  stage changes, declare a fix or bundle ready, or summarize work the operator
-  operator may commit or deploy — the operator must never have to ask "how
+  may commit or deploy.
-  sure are you?". Portable across projects.
 ---
 
 Every stage summary, fix report, or ready-to-commit bundle ends with a

skills/coordinate/SKILL.md

@@ -1,10 +1,9 @@
 ---
 name: coordinate
 description: >
-  Coordinate a failing run or a fix with the agents on related branches
+  Coordinate a failure or fix with the agents on related branches through
-  (upstream and downstream through merges): claim it, ask whether it is
+  merges: claim, ask, report. Trigger on /coordinate and when a fix touches
-  already fixed, report the result. Trigger on /coordinate and whenever a fix
+  code other branches share.
-  touches code other branches share through merges. Portable across projects.
 ---
 
 Run the `democracy` skill's **Lineage** and **Peer protocol** sections for the

skills/criticize/SKILL.md

@@ -1,13 +1,10 @@
 ---
 name: criticize
 description: >
-  Look at a problem, a plan, a design, a decision, a text, or a piece of code
+  Give constructive criticism of a problem, plan, design, decision, text or
-  critically from diverse aspects and give constructive criticism: what holds,
+  code from diverse aspects, each point hardened by dialectic. Trigger on
-  what does not, why it matters, and what to do instead. Every critique point is
+  /criticize, "kritisiere", "kritisch betrachten", "konstruktive Kritik", "was
-  hardened with the dialectic skill before it is reported. Trigger on
+  haeltst du davon", or requests for honest feedback.
-  /criticize, "kritisiere", "kritisch betrachten", "konstruktive Kritik",
-  "was haeltst du davon", or when the operator asks for honest feedback on
-  something rather than for a fix. Portable across projects.
 ---
 
 The stance is critical but constructive: the goal is a better result, not a

skills/democracy/SKILL.md

@@ -1,16 +1,10 @@
 ---
 name: democracy
 description: >
-  Organise parallel agents so no two do the same work: the first agent to
+  Keep parallel agents from duplicating work: the first to claim it owns it;
-  start a piece of work is elected its president and does all of it, the first
+  line representatives and a resource chair coordinate. Run AUTOMATICALLY
-  agent in each organisational line represents that line, the first to start a
+  before work another agent might also do (failure, cluster, feature, gate,
-  cross-cutting work cluster organises its strand, and the earliest-elected
+  deploy, cleanup), and on /democracy.
-  live president chairs the council and allocates the resources of the whole
-  system (machines, servers, cloud, CI runners, gate, deploy and iteration
-  slots, disk). Run AUTOMATICALLY before starting work another agent on the
-  same system might also be doing (a failure, a cost cluster, a feature, a
-  gate, a deploy, a cleanup), whenever several agents share a system, and on
-  /democracy. Portable across projects.
 ---
 
 Two agents doing the same work waste the second run and then collide in the

skills/dialectic/SKILL.md

@@ -1,11 +1,10 @@
 ---
 name: dialectic
 description: >
-  Reach a defensible conclusion through a dialectical process — thesis,
+  Reach a defensible conclusion by thesis, independent skeptic antithesis and
-  adversarial antithesis, synthesis — iterated until one thesis survives every
+  synthesis, iterated to ~99% confidence. Trigger for any consequential root
-  attack at ~99% confidence. Trigger for any consequential root-cause, design,
+  cause, design or decision where being wrong is expensive and the answer is
-  or decision where being wrong is expensive and the answer is not yet certain.
+  uncertain.
-  Deep-inspects every accessible source. Portable across projects.
 ---
 
 Reach the truth by dialectic, not by first guess. Do not stop at a plausible

skills/dream/SKILL.md

@@ -1,16 +1,10 @@
 ---
 name: dream
 description: >
-  Consolidate the last 24 hours of work in the current repository: what the
+  Consolidate the last 24 hours of work in this repository: what held, what
-  agent did, where it was right, where it was wrong, and which hypotheses
+  broke, which hypotheses follow, into memory and improvement proposals.
-  follow. Every hypothesis is hardened with the dialectic skill, the survivors
+  Trigger on /dream or when the operator asks to reflect on or learn from
-  are written to memory, the derived improvements to the repository's code and
+  recent work.
-  to its agent instructions (CLAUDE.md, AGENTS.md) are offered as single-select
-  questions, and the run ends in autotune and autoskill. The objective is to
-  raise the confidence of future runs until those mistakes stop recurring.
-  Trigger on /dream, or
-  when the operator asks to reflect on, consolidate, or learn from recent work.
-  Portable across projects.
 ---
 
 Sleep on the work: replay what happened in this repository, separate what held

skills/essence/SKILL.md

@@ -1,10 +1,9 @@
 ---
 name: essence
 description: >
-  Compact skills and memory down to their essence so every session loads less
+  Compact skills and memory to their essence after a health pass that finds
-  context, after a health pass that finds the dead weight first. Trigger on
+  dead weight. Trigger on /essence or when skills or MEMORY.md grow too long,
-  /essence, or when the operator says the skills or MEMORY.md have grown too
+  duplicate, or eat too much context.
-  long, carry duplicates, or eat too much context. Portable across projects.
 ---
 
 Shorter, not thinner. Every fact that still earns its place survives; what goes

skills/explain/SKILL.md

@@ -1,10 +1,9 @@
 ---
 name: explain
 description: >
-  Explain code and its interactions. Trigger when the operator asks what a
+  Explain code and its interactions. Trigger when the operator asks what code
-  piece of code does, how a mechanism works, why components interact the way
+  does, how a mechanism works, why components interact, or invokes /explain on
-  they do, or invokes /explain on a file, function, role, or module.
+  a file, function, role or module.
-  Portable across projects.
 ---
 
 Explain the named code so an engineer who has never seen it can follow it:

skills/funnel/SKILL.md

@@ -1,13 +1,9 @@
 ---
 name: funnel
 description: >
-  Funnel agent work through sidetrees: every agent works in its own git
+  Keep agent work in its own git worktree until it reaches 90% fix confidence
-  worktree until its change reaches at least 90 % fix confidence and under 5 %
+  and under 5% break risk; below that bar it becomes a proposal. Trigger when
-  break risk, and only then does the change enter the main line. When that bar
+  delegating work to agents, when agents work in parallel, or on /funnel.
-  is realistically out of reach, the agent submits a proposal instead of a
-  change. Trigger when delegating implementation, fix or optimization work to
-  agents, when several agents work in parallel, or on /funnel. Portable across
-  projects.
 ---
 
 # Funnel

skills/help-skills/SKILL.md

@@ -1,10 +1,9 @@
 ---
 name: help-skills
 description: >
-  List and explain every skill available in the current session. Trigger on
+  List and explain every skill in the session. Trigger on /help-skills,
-  /help-skills, "welche skills gibt es", "skill übersicht", or when the
+  "welche skills gibt es", "skill übersicht", or when the operator asks what
-  operator asks what skills exist or what a skill does. Portable across
+  skills exist or what one does.
-  projects.
 ---
 
 Produce a one-shot overview of every skill the session can invoke:

skills/medusa/SKILL.md

@@ -1,11 +1,10 @@
 ---
 name: medusa
 description: >
-  Run the MEDUSA AI security scanner (medusa-security on PyPI) against a
+  Run the MEDUSA security scanner (medusa-security, PyPI) on a repository,
-  repository, working tree, or secret stores. Use when the user asks for a
+  working tree or secret stores. Use for security scans, vetting a repo before
-  security scan, supply-chain vetting of a repo before cloning, leaked-secret
+  cloning, leaked-secret detection in chat or shell history, or /medusa.
-  detection in AI chat or shell history, or invokes /medusa. Defensive scanning
+  Defensive only.
-  only.
 ---
 
 MEDUSA is a defensive AI-first security scanner (40,000+ patterns: CVEs, prompt injection, MCP tool poisoning, leaked secrets).

skills/merge-fix/SKILL.md

@@ -1,10 +1,9 @@
 ---
 name: merge-fix
 description: >
-  Fetch every branch of the repository, hunt down the commits that carry a
+  Hunt down the commits on any branch that carry a described fix and merge it
-  described fix, and merge that fix into the current branch. Trigger on
+  into the current branch. Trigger on /merge-fix <description> or when the
-  /merge-fix <description of the fix> or when the operator asks to find a fix
+  operator asks to bring over a fix from another branch.
-  that lives on another branch and bring it over. Portable across projects.
 ---
 
 The free text after `/merge-fix` is the fix description, exactly like `/loop`

skills/no-defaults/SKILL.md

@@ -1,15 +1,10 @@
 ---
 name: no-defaults
 description: >
-  Forbid default values for parameters, settings, and environment lookups in
+  Forbid default values for parameters, settings and environment lookups;
-  every language. Load and apply AUTOMATICALLY on every task that writes,
+  demand explicit values and fail loudly. Apply AUTOMATICALLY on every task
-  edits, generates, refactors, or reviews code, config, templates, schemas,
+  that writes, edits, generates, refactors or reviews code, config, templates,
-  or infrastructure — never wait to be asked. A default silently substitutes
+  schemas or infrastructure.
-  a guess for a value the caller failed to supply, so a misconfiguration
-  becomes wrong behaviour instead of a loud failure. Demand strict, explicit
-  values and fail loudly when one is missing. `false`, `null` and `""` are the
-  only free defaults; every other default needs a written justification.
-  Portable across projects.
 ---
 
 A default value is a guess, written at the point where the caller's intent is

skills/observe/SKILL.md

@@ -1,10 +1,9 @@
 ---
 name: observe
 description: >
-  Watch a named target (a CI run, a pipeline, a build, a log) on a fixed
+  Watch a named target (CI run, pipeline, build, log) on a cadence and triage
-  cadence and apply the triage skill whenever new failures appear. Trigger on
+  new failures as they appear. Trigger on /observe <target> or when the
-  /observe <target> or when the operator asks to keep monitoring something and
+  operator asks to keep monitoring and fix regressions.
-  fix regressions as they surface. Portable across projects.
 ---
 
 Keep a target under continuous watch and act only when it degrades. The loop is

skills/plan/SKILL.md

@@ -1,10 +1,9 @@
 ---
 name: plan
 description: >
-  Turn a request into an objective-oriented plan and hand it to the robot skill
+  Turn a request into an objective-oriented plan and hand it to the robot
-  for autonomous execution. Trigger on /plan or when the operator asks for a
+  skill. Trigger on /plan or when the operator asks for a plan, breakdown or
-  plan, a breakdown, or a strategy for a task before any work starts. Portable
+  strategy before work starts.
-  across projects.
 ---
 
 Produce a plan whose every item is an outcome with a check, then execute it

skills/refactor/SKILL.md

@@ -1,11 +1,9 @@
 ---
 name: refactor
 description: >
-  Refactor every file that is currently uncommitted in the git working tree -
+  Refactor every uncommitted file (staged, unstaged, untracked) up to the
-  staged, unstaged and untracked - up to the project's coding standards,
+  project's standards without changing behaviour. Trigger on /refactor or when
-  without changing behaviour. Trigger on /refactor or when the operator asks to
+  the operator asks to clean up, tidy or polish the current changes.
-  clean up, tidy, or polish the current changes before committing. Portable
-  across projects.
 ---
 
 The unit of work is the uncommitted change set, not the repository. Behaviour

skills/robot/SKILL.md

@@ -1,10 +1,9 @@
 ---
 name: robot
 description: >
-  Work fully autonomously to a goal. Trigger when the operator wants hands-off,
+  Work fully autonomously to a goal: no check-ins, no stopping before the goal,
-  uninterrupted execution — the agent drives the task to completion without
+  only commands already cleared. Trigger when the operator wants hands-off,
-  check-ins, never stops before the goal is reached, and uses only commands it
+  uninterrupted execution.
-  is already cleared to run. Portable across projects.
 ---
 
 Operate as an autonomous robot: given a goal, reach it without hand-holding.

skills/sceptic/SKILL.md

@@ -1,11 +1,10 @@
 ---
 name: sceptic
 description: >
-  Analyse a repository, a path, or a diff with a hostile eye for violated
+  Analyse a repository, path or diff with a hostile eye for violated
-  engineering principles — SPOT, DRY, KISS, SRP, and security at the trust
+  principles: SPOT, DRY, KISS, SRP, security at trust boundaries. Trigger on
-  boundaries. Trigger on /sceptic, "sei skeptisch", "kritische analyse",
+  /sceptic, "sei skeptisch", "kritische analyse", "review the architecture",
-  "review the architecture", or when the operator asks what is wrong with the
+  or "what is wrong with the code".
-  code rather than whether it works. Portable across projects.
 ---
 
 The stance is adversarial: the code is guilty until its structure proves

skills/scope-guard/SKILL.md

@@ -2,10 +2,9 @@
 name: scope-guard
 description: >
   Deliver exactly what was asked and nothing more. Trigger on every task that
-  creates files, commands, or commits, and on autonomous runs where no one is
+  creates files, commands or commits, on unreviewed autonomous runs, on
-  reviewing each step. Also when the operator asks to be given something, and
+  hand-over requests, and when the operator asks why something unrequested
-  when they ask why something exists that they never requested. Portable across
+  exists.
-  projects.
 ---
 
 The requested scope is the deliverable. A problem you noticed behind the

skills/shortcuts/SKILL.md

@@ -1,10 +1,9 @@
 ---
 name: shortcuts
 description: >
-  Portable operator conversation shortcuts, reusable across every project.
+  Operator conversation shortcuts. Trigger when the message is exactly one of
-  Trigger when the user's message is exactly one of these tokens (optionally
+  these tokens, optionally with arguments: sobu, soco, socobu, socon, sona,
-  followed by arguments): sobu, soco, socobu, socon, sona, sote. Expand the
+  sote. Expand it and act on the expanded instruction.
-  shortcut to the listed meaning and act on the expanded instruction.
 ---
 
 When an operator message is one of the shortcuts below, expand it to the meaning and act on it.

skills/status-matrix/SKILL.md

@@ -1,11 +1,9 @@
 ---
 name: status-matrix
 description: >
-  Print one matrix of everything currently in flight: open and closed tasks,
+  Print one matrix of everything in flight: tasks, workflows, background jobs,
-  running workflows and background jobs, plus confidence and break risk per
+  with confidence and break risk per item. Trigger on /status-matrix,
-  item. Trigger on /status-matrix, "status", "übersicht", "wo stehen wir", or
+  "status", "übersicht", "wo stehen wir", or what is done, left or running.
-  whenever the operator asks what is done, what is left, or what is still
-  running. Portable across projects.
 ---
 
 One-shot overview, no side effects: this skill reads state and reports it. It

skills/test/SKILL.md

@@ -1,11 +1,9 @@
 ---
 name: test
 description: >
-  Discover the test targets of the project's Makefile, let the operator pick
+  Discover the Makefile's test targets, let the operator pick, run and report;
-  which ones to run, then run them and report; in fix mode, loop run, diagnose,
+  fix mode loops until green. Trigger on /test, /test --fix, or when the
-  fix, re-run until green. Trigger on /test, /test --fix, or when the operator
+  operator asks to run the tests, make them pass, or get the suite green.
-  asks to run the tests, make them pass, or get the suite green. Portable
-  across projects.
 ---
 
 The Makefile is the source of truth for how this project runs tests. Never

skills/triage/SKILL.md

@@ -1,11 +1,9 @@
 ---
 name: triage
 description: >
-  Triage a failing CI run, pipeline, or job set to a verified root cause and a
+  Triage a failing CI run, pipeline or job set to a verified root cause and a
-  real fix. Trigger when a build, test, or deploy pipeline has one or more failed
+  real fix, one cluster per worktree. Trigger when a build, test or deploy
-  jobs. Applies the dialectic skill, the democracy peer protocol and the funnel
+  pipeline has failed jobs.
-  skill to every failure cluster, so each cluster is fixed in its own worktree,
-  and hands a timed-out job's log to the tune skill. Portable across projects.
 ---
 
 Drive a red pipeline to green by root cause, not by guesswork. Treat every

skills/tune/SKILL.md

@@ -1,15 +1,10 @@
 ---
 name: tune
 description: >
-  Find and apply performance optimizations (CI wall-clock, deploy duration,
+  Find and apply performance optimizations (CI, deploy, build, gate, hot
-  build and gate runtime, hot code paths) without reducing logic, coverage or
+  paths) without reducing logic, coverage or correctness. Trigger on /tune,
-  correctness, including a change of language where measurement justifies it.
+  when a job dies on its time budget, when a pipeline or deploy grows slower,
-  Asks once per session what to examine and which limits apply, measures from
+  or asked where time goes.
-  logs, coordinates every cost cluster with the other agents so the one who
-  identified it first works it, hardens every candidate with the dialectic skill
-  and funnels each optimization through a sidetree. Trigger on /tune, when a job dies on its time
-  budget, when a pipeline or deploy grows slower, or when the operator asks
-  where the time goes. Portable across projects.
 ---
 
 # Tune

tests/test_lock.py

@@ -12,6 +12,8 @@ LOCK_FILE = REPO_ROOT / "skills-lock.json"
 
 HASH_RE = re.compile(r"^[0-9a-f]{64}$")
 REQUIRED_FIELDS = ("source", "sourceType", "skillPath", "computedHash")
+DESCRIPTION_WORDS = 40
+LISTING_WORDS = 1300
 
 
 class TestSkillsLock(unittest.TestCase):
@@ -61,6 +63,16 @@ class TestSkillsLock(unittest.TestCase):
                     "description:", frontmatter, "frontmatter missing description"
                 )
 
+    def test_descriptions_fit_the_listing_budget(self):
+        total = 0
+        for skill_md in sorted((REPO_ROOT / "skills").glob("*/SKILL.md")):
+            frontmatter = skill_md.read_text(encoding="utf-8").split("---", 2)[1]
+            words = len(frontmatter.split("description:", 1)[1].split()) - 1
+            total += words
+            with self.subTest(skill=skill_md.parent.name):
+                self.assertLessEqual(words, DESCRIPTION_WORDS)
+        self.assertLessEqual(total, LISTING_WORDS)
+
     def test_first_party_skills_do_not_shadow_locked_skills(self):
         locked = set(self.lock["skills"].keys())
         for skill_dir in sorted((REPO_ROOT / "skills").glob("*/")):