AB hyperthink
Triple-perspective deep research engine. Triggered by /hyperthink. Runs an interrogate flow to narrow scope, then executes a 6-stage fully automatic pipeline: (1) Opus master brief + 3 persona-branched prompt variants, (2) 36 parallel deep-dives (12 sections × 3 agents: Optimist / Analyst / Critic), (3a) Analyst-only trifecta audit — fact-checks Optimist, confidence-tags all claims, compresses each section to a structured comparison doc, (3b) unified synthesis narrative weaving all 3 perspectives with embedded confidence tiers, (4) executive brief + docx delivered to Telegram. Fully hands-off after trigger. Output: synthesis.md + brief.docx. Cost: ~$55–75/run.
As a process B 71/100 · Nearly there — weak spots: when it triggers, progress reporting
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
✓ Guard found no suspicious behaviour. 1 matches are attack strings quoted in this security skill's own documentation.
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5662 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "requires"
Process rating: all ten parameters 71/100
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5662 tokens
- 100Steps. 55 steps
- 100Failures and branches. 2 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 17 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)
- +1No license
- +2Single-language instructions
- +3Description length 668: enough signal without eating the budget
- +4Structure: 33 headings
- +3Step-by-step instructions: 55 items
- +3Output format is stated explicitly
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.