AD context-optimizer
Context-aware session manager that monitors token usage and automatically extracts key information to create continuation sessions when approaching context limits. Use when: (1) User wants automatic context management, (2) Long-running tasks approach 200k token limit, (3) Need to split large tasks across multiple sessions, (4) Want to preserve continuity when context nears exhaustion.
As a process D 47/100 · Unfinished process — weak spots: when it triggers, inputs and preconditions, failures and branches
How to improve
- 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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Context-aware session manager that monitors token usage and automa… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 47/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 5 mutating operations with no state check
- 40Consistency. Frontmatter name (context-optimizer) differs from the folder (context-optimizer-pro)
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 21 steps
- 100Execution cost. Instruction body is 650 tokens
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)
- -42 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +3Description length 387: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 21 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.