Evaluation report
Warningsagent-skills · skill8511716· 2 months ago
Every check MetaHub ran on this artifact, grouped by area. Static checks run on the source at publish time; behavioral checks run the artifact in a sandbox and judge what it actually does.
Structural
7 passedRepository is reachable
https://github.com/datadog-labs/agent-skills @ 8511716 — ★ 150 · Python · MIT · last push 4 days ago
Manifest detected
kind=skill slug=agent-skills · source=SKILL.md
Slug is URL-safe
"agent-skills" matches /^[a-z0-9][a-z0-9-]{0,62}$/
Slug is unique within kind
No collision found for skill/agent-skills
Version is semver
0.1.0
Manifest present and parseable
Manifest found at SKILL.md.
Name declared and well-formed
Name "agent-skills" is well-formed.
Documentation
6 passed3 warningsDescription qualitywarn
11 words · 87 chars — skills use the description as their trigger; aim higher
Aim for 15+ words and include trigger phrases like “use this skill when …”.
Tags / topics declaredwarn
No manifest tags and no GitHub repo topics
Add tags to the manifest (or GitHub topics on the repo) so the registry's search and category filters surface this artifact.
Homepage or repository declaredwarn
No homepage or repository declared.
Add a "homepage" or "repository" field to SKILL.md.
README is present and substantial
16,889 chars · 6 sections · 27 code blocks
README has usage / example sections
Safety
9 passed2 warnings1 queuedNo invisible characters in model-read textwarn
1 stray invisible character, concealing nothing. agent-observability/agent-observability-auto-experiment/references/eval_harness_template.py:122 — stray zero-width character (not concealing anything)
Remove the characters. If the text is genuinely bidirectional, keep the isolates and drop the overrides.
No instruction-override text in model-read contentwarn
1 instruction-override phrase in model-read text. agent-observability/agent-observability-auto-experiment/references/rubrics.md:314 — instruction override
If these are examples, fence them. If they are live instructions to the model, say plainly in the documentation what they do.
LICENSE file at repo root
Kind-specific
5 passed3 warningsSkill: triggers declaredwarn
No `trigger` phrases in SKILL.md frontmatter
Add `trigger:` lines so Claude knows when to activate this skill — e.g. `when building MCP servers` or `for diagram creation`.
Tool scope declaredwarn
No tool scope declared.
Declare `allowed-tools` with the minimum set the skill actually needs. If it needs none, declare an empty list explicitly.
Description says when to use the skillwarn
Description says what the skill is, but not when to use it.
Add the triggering condition — e.g. "Use when the user pastes tabular data and wants a markdown table." A client routes on this text.
Skill: SKILL.md present
found at SKILL.md · frontmatter source: SKILL.md
Maintenance
1 passed2 warnings1 queuedTests detectedwarn
no test/tests/__tests__/spec/t/ dirs, no JVM src/test/, and no JS/TS/Python/Go/Ruby/Elixir test files
Add tests (even a smoke test). Consumers gauge maintenance quality by their presence.
CI configuration detectedwarn
no CI config found (looked for GitHub Actions, CircleCI, GitLab CI, etc.)
Add a simple workflow (lint + test on PR) — it tells consumers the artifact is built reproducibly.
Recent activity
last push 4 days ago