BB deep-planning
Use for complex architecture, algorithm, system-design, logic, or research-planning problems where ordinary linear planning is likely to be brittle, bloated, or trapped in local assumptions. Deep Planning creates a baseline plan, abstracts the problem into domain-neutral structure, spawns a blank-context domain-questioning subagent, translates useful cross-domain mechanisms back into the original domain, compares standard/novel/hybrid plans, and emits a self-contained execution blueprint. Do not use for routine coding, simple refactors, factual lookup, straightforward API usage, or tactical bug fixes.
Use for complex architecture, algorithm, system-design, logic, or research-planning problems where ordinary linear planning is likely to be brittle, bloated…
As a process B 72/100 · Nearly there — weak spots: result and completion, consistency, running it twice
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 · 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
body-longSKILL.md body ≈ 6213 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 72/100
- 30Running it twice. 9 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (deep-planning) differs from the folder (deep-planning-skill)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 6213 tokens
- 100Steps. 292 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 3 branches, has a failure section
- 100Progress reporting. Reports progress
- low 47 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
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 608: enough signal without eating the budget
- +4Structure: 53 headings
- +3Step-by-step instructions: 292 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.