AB context-manager
AI-powered context management for OpenClaw sessions
As a process B 65/100 · Nearly there — weak spots: when it triggers, consistency, progress reporting
This is a copy of a skill from another catalog; the rating counts the canonical one: context-manager (ClawHub)
How to improve
For the model run — optional
- 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: 2. 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 65/100
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (context-manager) differs from the folder (qui-context-manager)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 28 steps, 1 vague phrases
- 100Failures and branches. 1 branches, has a failure section
- 100Execution cost. Instruction body is 1815 tokens
- 100Running it twice. Mutating operations check current state
- low 11 top-level sections: this looks like several domains in one skill
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)
- +3Description length 51: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 25 headings
- +3Step-by-step instructions: 28 items
- +3Output format is stated explicitly
- +4Has examples (9 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.
External checks
ClawHub: clean
The skill is a clearly disclosed context-compression helper, but users should understand it can read, summarize, back up, and reset OpenClaw session history when explicitly invoked.
LLM: benign (high) · VirusTotal: · 29 May 2026