AC context-management
Manage AI agent context window consumption, prevent compaction death spirals, and enforce sub-agent spawn policies. Use when: (1) context is filling up and work quality may degrade, (2) deciding whether to spawn a sub-agent or work in main session, (3) preparing for compaction or session handoff, (4) user asks "what's eating my context?" or "how much runway left?", (5) after compaction to restore working state from checkpoint files. NOT for: general memory/workspace management (use memory-keeper or workspace-standard).
Manage AI agent context window consumption, prevent compaction death spirals, and enforce sub-agent spawn policies.
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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: 4. 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 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 3 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, write, web) that frontmatter does not declare
- 100Steps. 56 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3292 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- high The skill tells the model to perform an irreversible action with no human approval
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
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 524: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 56 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 98.