BD context-engineering
Diagnose and improve context usage in AI agent sessions. Use when context grows large, instructions are being missed, output quality degrades, token usage rises, or a project needs deliberate context organization.
Diagnose and improve context usage in AI agent sessions.
As a process D 44/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 213 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - note
edit-residuethe text marks something as outdated (lines 128, 158): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 44/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 5 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Consistency. The Hermes dialect needs category and tags
- 100Steps. 72 steps
- 100Execution cost. Instruction body is 3141 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- -31 of 3 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 213: enough signal without eating the budget
- +4Structure: 32 headings
- +3Step-by-step instructions: 72 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.