feat: add submitted skills review desk

skills/skill-reviewer/SKILL.md

@@ -0,0 +1,25 @@
+---
+name: skill-reviewer
+description: Review an Agent Skill package and produce a kind, evidence-backed improvement brief. Use when assessing a SKILL.md, its trigger, instructions, scripts, references, safety, or evaluation readiness; do not rewrite the package unless asked.
+---
+
+# Skill reviewer
+
+Review the submitted package before proposing changes. Preserve the author's intent: this is a constructive assessment, not a replacement of their domain expertise.
+
+## Review flow
+
+1. Read `SKILL.md` and list bundled files. Check frontmatter validity, package-name alignment, and whether the description says both what the skill does and when it applies.
+2. Identify the narrow job, the expected inputs, safe boundaries, a default workflow, and observable output. Mark any claim you cannot verify as a question, not a defect.
+3. Recommend only additions that change execution: a small RULES section for real invariants, a script for repeated fragile work, a reference for conditional detail, or eval cases for behavior that matters.
+4. Flag secrets, destructive actions, network calls, and unclear approval boundaries prominently. Never copy credentials into review artifacts.
+5. Return a friendly brief with: what already works, highest-value improvements, suggested package layout, and a small set of realistic test prompts.
+
+## Quality bar
+
+- Prefer precise activation language over broad phrases such as "use for code."
+- Keep the main instructions lean; send conditional or lengthy material to `references/` and explain exactly when to read it.
+- Favor evidence and defaults over generic rules or tool menus.
+- Recommend scripts only when they remove repeated, error-prone mechanics; document prerequisites and use relative paths.
+
+Read [the review rubric](references/review-rubric.md) when scoring a package.

skills/skill-reviewer/references/review-rubric.md

@@ -0,0 +1,7 @@
+# Review rubric
+
+Assess six dimensions: discoverability, scope, procedure, safety, resources, and proof.
+
+For each finding, state the observed evidence, the practical consequence, and the smallest helpful change. Do not call missing files a problem unless the workflow genuinely needs them. A strong review explains why the recommendation belongs in the skill rather than in general agent behavior.
+
+Test prompts should include one normal request and one boundary case. Assertions should be observable, such as valid JSON, an explicit approval request before mutation, or a report containing file locations.