AD prompt-slimmer
Audit and slim down OpenClaw workspace files (SOUL.md, AGENTS.md, TOOLS.md, IDENTITY.md, USER.md, HEARTBEAT.md, MEMORY.md) to reduce system prompt token usage. Analyzes each file for redundancy, low-frequency content, and cross-file duplication, then produces an actionable slim-down plan with before/after metrics. Moves archived content to memory/archive/ while preserving searchability via memory_search. Use when: token costs are high, context window is filling up, system prompt feels bloated, or you want to optimize workspace files. Triggers on: "slim prompt", "reduce tokens", "optimize workspace", "瘦身", "精简 prompt", "audit system prompt", "trim workspace files", "token bloat".
Audit and slim down OpenClaw workspace files (SOUL.md, AGENTS.md, TOOLS.md, IDENTITY.md, USER.md, HEARTBEAT.md, MEMORY.md) to reduce system prompt token…
As a process D 47/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 130): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 47/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 6 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 85Steps. 37 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1655 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
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 687: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 37 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.