AB workspace-local-retrieval
Build a local-first retrieval architecture for an OpenClaw workspace with explicit corpus boundaries, deny-by-default agent access, separate personal-memory vs workspace-knowledge layers, stable agent-facing search interfaces, and maintenance-aware refresh workflows. Use when a user wants to: (1) add local RAG without indexing everything, (2) separate personal memory from reusable workspace retrieval, (3) define agent-scoped access to different corpora, (4) package a retrieval system as a reusable skill rather than private glue code, (5) add explainable status / refresh workflows, or (6) turn a one-off local search setup into a safer multi-agent retrieval pattern.
As a process B 72/100 · Nearly there — weak spots: when it triggers, 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: 17. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Build a local-first retrieval architecture for an OpenClaw workspa… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 72/100
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 5 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 82 steps
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2083 tokens
- 100Progress reporting. Reports progress
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)
- +1No license
- +2Single-language instructions
- +3Description length 672: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 82 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (11 of 11)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.