AC context-compression
Use this skill whenever the conversation context is getting long, when a user asks to "compress", "summarize", or "clean up" the conversation, or when you detect the context window is filling up. Also triggers automatically via PreCompact hook if configured. Compresses conversation history using a tiered strategy — preserving what matters, summarizing what's useful, dropping what's noise — then writes a structured memory file so nothing important is truly lost. Use this even for partial compression of recent exchanges.
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 58/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (context-compression) differs from the folder (context-compression-claude-code-custom)
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 14 steps
- 100Execution cost. Instruction body is 1133 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 524: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 14 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.