AC context-compactor
Automatic context compression for OpenClaw sessions. Summarizes long conversations into structured digests (decisions, facts, pending items, technical details), saves compressed summaries to disk, and injects them into new sessions. Reduces token waste from redundant context repetition. Use when conversation exceeds ~50 turns, when context feels bloated, when starting a new session and prior context is needed, or when the user says "compact", "summarize this conversation", "start fresh but remember".
As a process C 58/100 · Has gaps — weak spots: result and completion, consistency, 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 58/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (context-compactor) differs from the folder (context-compactor-zero-dep)
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 56 steps
- 100Execution cost. Instruction body is 1683 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (4 tags): a typed call is more reliable
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
- -5TODO / placeholder text left in the skill
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 505: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 56 items
- +4Has examples (4 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.