BF llm-inference-radar
Build and run a Chinese research intelligence radar for LLM inference acceleration, AI infra, model serving, kernels, reproducibility, open-source project signals, company infra updates, horizon transfer opportunities, feedback learning, and a persistent knowledge base. Use when the user asks for daily or weekly briefs, paper radar, open-source watch, infra watch, transfer matrix updates, hidden opportunities, or maintaining a research radar for LLM inference acceleration.
Build and run a Chinese research intelligence radar for LLM inference acceleration, AI infra, model serving, kernels, reproducibility, open-source project…
As a process F 53/100 · Will not run — References files that are not bundled: references/output-templates.md, references/ranking-and-evidence.md, references/taxonomy.yaml
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: references/output-templates.md - warning
missing-refreference to a missing file: references/ranking-and-evidence.md - warning
missing-refreference to a missing file: references/taxonomy.yaml - warning
missing-refreference to a missing file: references/watchlist.yaml - warning
missing-refreference to a missing file: references/transfer-matrix.md - warning
missing-refreference to a missing file: references/feedback-learning.md - warning
missing-refreference to a missing file: references/knowledge-base-schema.md - warning
missing-refreference to a missing file: references/config.yaml
Process rating: all ten parameters 53/100
- 0Tools and files. 8 referenced file(s) missing: references/output-templates.md, references/ranking-and-evidence.md, references/taxonomy.yaml
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 55Failures and branches. 1 branches
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 85Steps. 27 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1824 tokens
- 100Running it twice. No mutating operations
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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 477: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 27 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.