AF arena-research
General-purpose Are.na research agent. Searches Are.na for curated collections, references, visual inspiration, and linked resources across any topic. Explores the connection graph between channels to discover adjacent ideas and key curators. Use when: (1) user says "arena research", "search arena for", "search are.na for", "what's on arena about", "find arena channels about", "who's curating [topic]", "explore arena for", "/arena-research", (2) user is working on something where curated human-collected references would be valuable (design research, cultural analysis, art direction, conceptual exploration, reading lists, visual references), (3) user wants to discover how people organize ideas around a topic — the channel structure IS the insight. NOT for: posting content, account management, or real-time/breaking news (use x-research for that).
As a process F 40/100 · Will not run — References files that are not bundled: source_url, references/arena-api.md
How to improve
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: source_url - warning
missing-refreference to a missing file: references/arena-api.md
Process rating: all ten parameters 40/100
- 0Tools and files. 2 referenced file(s) missing: source_url, references/arena-api.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (arena-research) differs from the folder (arena-research-skill)
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 52 steps
- 100Execution cost. Instruction body is 2761 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +3Description length 856: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 22 headings
- +3Step-by-step instructions: 52 items
- +3Output format is stated explicitly
- +4Has examples (22 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.