AC session-distiller
Batch-distill completed and live OpenClaw session transcripts into structured daily memory files. Two components: distill.py (batch + live session distillation, Granola meeting note distillation, Captain's Log ingestion) and context-gate.py (context usage monitor with auto-distill). Use when: (1) distilling closed session transcripts to memory, (2) running live distill-in-place for approved group chats, (3) monitoring context usage and auto-gating sessions approaching limits, (4) ingesting meeting notes into daily memory files (--meeting-notes / --granola), (5) ingesting daily log AM/PM files into daily memory files (--daily-log / --captains-log). NOT for: real-time memory flush (handled by OpenClaw compaction), vector store ingestion, or manual memory file editing.
As a process C 62/100 · Has gaps — weak spots: result and completion
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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Exfiltration
exfil-webhook-urlscripts/context-gate.py:92Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)f"https://api.telegram.org/bot{BOT_TOKEN}/sendMessage",placeholder
Files scanned: 8. 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 62/100
- 0Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 38 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2311 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low The response is described with custom markup (3 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
- +5Description has no quoted example phrases that should trigger the skill
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 776: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 38 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.