diff --git a/skills/sceptic/SKILL.md b/skills/sceptic/SKILL.md
new file mode 100644
index 0000000..d0850c6
--- /dev/null
+++ b/skills/sceptic/SKILL.md
@@ -0,0 +1,87 @@
+---
+name: sceptic
+description: >
+  Analyse a repository, a path, or a diff with a hostile eye for violated
+  engineering principles — SPOT, DRY, KISS, SRP, and security at the trust
+  boundaries. Trigger on /sceptic, "sei skeptisch", "kritische analyse",
+  "review the architecture", or when the operator asks what is wrong with the
+  code rather than whether it works. Portable across projects.
+---
+
+The stance is adversarial: the code is guilty until its structure proves
+otherwise. This skill hunts violated principles, not bugs (`code-review`),
+not bloat (`ponytail-audit`), not leaked secrets (`medusa`). Read-only —
+report the findings, change nothing unless the operator asks afterwards.
+
+## Scope
+
+The operator names the target: a repository, a directory, a role, or a diff.
+Without a target, take the whole repository and rank by blast radius. State
+the scope in one line before reporting, and name explicitly what you did not
+read — an audit that silently covered half the tree reads as clean.
+
+## The lenses
+
+Apply each independently; a finding belongs to exactly one:
+
+1. **SPOT** — one truth, one place. A value, a version, a hostname, a
+   schema, a list of names that exists twice is a divergence waiting to
+   happen. Name both locations and the drift they will cause.
+2. **DRY** — repeated *knowledge*, not repeated text. Two blocks that look
+   alike but change for different reasons are correctly separate; merging
+   them is the violation. Prove the shared reason to change, or drop the
+   finding.
+3. **SRP** — one reason to change per unit. Look for the module that both
+   parses and persists, the function whose name contains "and", the role
+   that configures and deploys and monitors. The test: name the two
+   stakeholders who would each demand a change here.
+4. **KISS** — mechanism the problem never asked for: an abstraction with one
+   implementation, a config value that never varies, a cache with no
+   measured pressure, a retry loop around a deterministic call.
+5. **Security** — only at trust boundaries: unvalidated input crossing into
+   a query, a shell, a template, or a path; authorization checked in the
+   caller instead of the resource; a secret in a default, a log, or an
+   image layer; a permission wider than the operation needs. Defensive
+   findings only.
+6. **Silent defaults** — a fallback that substitutes a guess for a value the
+   caller failed to supply, turning a misconfiguration into wrong behaviour
+   instead of a loud failure. See the `no-defaults` skill.
+
+## Method
+
+- **Evidence before verdict.** Every finding carries `file:line` you actually
+  read. Grep for the sibling occurrences before calling something a
+  duplicate — one hit is not a pattern.
+- **Name the failure.** A finding must state what concretely goes wrong:
+  which value drifts, which caller breaks, which input reaches which sink.
+  A finding whose worst case is "feels wrong" gets deleted, not softened.
+- **Attack your own finding.** For anything consequential or expensive to
+  fix, run it through the `dialectic` skill before reporting it — the
+  strongest counter-argument is usually "these two are not the same
+  knowledge" or "this boundary is already checked upstream".
+- **Respect intent.** A deliberate marker (`ponytail:`, a documented
+  exception, a nocheck directive with a reason) is a known ceiling, not a
+  finding. Report it only when the ceiling has since been exceeded.
+
+## Output
+
+One ranked table, worst blast radius first:
+
+| Severity | Principle | Location | What is wrong | Smallest fix |
+
+Then three closing lines at most: what the scope excluded, which findings
+survived `dialectic` versus which are still derived-only, and the single
+finding to fix first. No per-finding paragraphs — the operator asks when a
+row needs unpacking.
+
+## Rules
+
+- Never report formatting, naming taste, or missing comments; a linter owns
+  those and the operator did not ask.
+- Distinguish proven (grepped, read, reproduced) from derived (reasoned
+  statically) per finding, and close with the `confidence` skill's numbers
+  for the audit as a whole.
+- No silent caps: if you ranked and cut, say how many findings were dropped
+  and by what rule.
+- Skepticism ends at the report. Do not fix, stage, or refactor as part of
+  this skill.