BC first-principles-thinking
Reason from fundamentals with in-session claim ledgers, mechanism maps, assumption checks, Fermi estimates, evidence grounding, verification questions, red-team critique, and structured brainstorming. Use for architecture, system design, technology selection, debugging, performance, migrations, strategy, product, research, scientific or business decisions, or prompts like first principles, challenge assumptions, from scratch, brainstorm, or think from fundamentals.
As a process C 62/100 · Has gaps — weak spots: result and completion, when it triggers, consistency
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 · 4
✓ No critical or high findings
Medium and low: 4
-
low Risky intent
intent-offensive-securityreferences/advanced-reasoning-tools.md:17Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Verification: [self-consistency / CoVe / backward check / sensitivity / red team]
-
low Risky intent
intent-offensive-securityreferences/advanced-reasoning-tools.md:250Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Skeptic / red team: attacks assumptions, incentives, security, and failure modes.
-
low Risky intent
intent-offensive-securitySKILL.md:157Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| High-stakes or likely hallucination risk | Chain-of-verification, backward check, red team, sensitivity analysis |
-
low Risky intent
intent-offensive-securitySKILL.md:206Offensive-security / dual-use content (legitimate for authorised testing; review intended use)mechanist, operator / implementation realist, skeptic / red team, and
Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 10607 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 62/100
- 0Result and completion. Does not say what the result is
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 8 mutating operations with no state check
- 40Consistency. Frontmatter name (first-principles-thinking) differs from the folder (b143kc47-first-principles-thinking-v2)
- 40Execution cost. Instruction body is 10607 tokens: crowds the task out of the window
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 171 steps
- 100Failures and branches. 9 branches, has a failure section
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 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 469: enough signal without eating the budget
- +4Structure: 38 headings
- +3Step-by-step instructions: 171 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (5 of 6)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.