AD lucid-dreamer
Nightly AI memory reasoning system. Lucid runs every night while you sleep - it reads your daily notes and memory files, detects stale facts, unresolved todos, recurring problems, forgotten decisions, and can optionally perform aggressive cleanup and contradiction detection. Includes optional session debrief for quick end-of-day memory capture. Zero dependencies, no database, no embeddings. Just a scheduled job and markdown files. Use when you want your AI agent to automatically maintain and improve its long-term memory over time. Triggers on "memory dreamer", "nightly memory review", "lucid", "auto memory", "memory cleanup", "memory hygiene".
As a process D 49/100 · 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: 16. 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 49/100
- 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. 3 mutating operations with no state check
- 60Tools and files. Uses tools (git) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 27 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1153 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- -32 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 651: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 27 items
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.