AD self-improving
Self-reflection, correction logging, persistent memory, WAL protocol, cold-boot recovery, and automated daily review with self-healing cron. Evaluates own work, catches mistakes, learns from corrections, manages tiered memory that compounds execution quality across restarts and context resets. Includes a mandatory daily cron that rewrites workspace .md files with new lessons — auto-created on first session if missing. Use when: (1) a command, tool, or operation fails; (2) the user corrects you or rejects your work; (3) you realize your knowledge is outdated or incorrect; (4) you discover a better approach; (5) you complete significant work and want to evaluate the outcome; (6) context persistence and session state management is needed; (7) recovering from a restart or context reset.
As a process D 45/100 · Unfinished process — 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Risky intent
intent-offensive-securityreferences/boundaries.md:13Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)| Access patterns | System access details | Privilege escalation |
detector
Files scanned: 10. 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 45/100
- 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. 16 mutating operations with no state check
- 40Consistency. Frontmatter name (self-improving) differs from the folder (self-maturing)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Failures and branches. 4 branches
- 85Steps. 73 steps, 2 vague phrases
- 100Execution cost. Instruction body is 3695 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 15 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 793: enough signal without eating the budget
- +4Structure: 29 headings
- +3Step-by-step instructions: 73 items
- +4Has examples (14 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.