BF superthink
Deep-dive research and analysis engine. Triggered by /superthink. Runs an interrogate flow to narrow topic and scope, then executes a 4-stage fully automatic pipeline: (1) master reasoning brief via Opus, (2) parallel deep-dive sections via Sonnet batch, (3) synthesis pass producing ~60,000 word document via Sonnet batch, (4) executive brief ~3,000 words via Sonnet batch. Fully hands-off after scope confirmation. Each stage uses an idempotent self-terminating cron poller. Requires the interrogate skill.
As a process F 51/100 · Will not run — References files that are not bundled: scripts/batch-worker-spec.md, scripts/md2docx-spec.md
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Instruction override
en-ignore-previousbatch-worker-spec.md.md:113Instruction-override phrase ("ignore previous instructions") (test fixture / example file; quoted — discussed, not commanded)"system": "Override system prompt for this request only",
fixturequoted
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: scripts/batch-worker-spec.md - warning
missing-refreference to a missing file: scripts/md2docx-spec.md - note
frontmatter-keyunknown frontmatter key "requires"
Process rating: all ten parameters 51/100
- 0Tools and files. 2 referenced file(s) missing: scripts/batch-worker-spec.md, scripts/md2docx-spec.md
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4638 tokens
- 100Steps. 57 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 18 top-level sections: this looks like several domains in one skill
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 508: enough signal without eating the budget
- +4Structure: 35 headings
- +3Step-by-step instructions: 57 items
- +4Has examples (14 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.