AC learning-loop
Proactive learning engine that makes your agent smarter every day. Combines daily journaling, decision tracking with categories, lesson extraction with lifecycle management (ACTIVE → VALIDATED → ARCHIVED), automatic memory tiering, nightly reflection, staggered review chains, correction tracking with promotion, and security boundaries. Unlike reactive systems that only learn when corrected, Learning Loop reflects, generalizes, and compounds knowledge autonomously. Use when: setting up a new agent and want it to learn over time; want structured decision tracking; need a daily reflection/journaling system; want lessons that generalize across problems; agent keeps repeating mistakes; want automatic memory organization; want your agent to get better at specific types of decisions. Zero dependencies. Works immediately after install.
As a process C 54/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 54/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 7 mutating operations with no state check
- 40Consistency. Frontmatter name (learning-loop) differs from the folder (clawmage-learning-loop)
- 60Failures and branches. 2 branches
- 100Tools and files. No external tools needed
- 100Steps. 62 steps
- 100Execution cost. Instruction body is 2375 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 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 839: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 23 headings
- +3Step-by-step instructions: 62 items
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.