BD continuous-learning-v2
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination. Use when capturing lessons from a session, managing instincts, or promoting them into skills, commands, or agents.
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
As a process D 48/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
The same skill appears in 1 more place: ECC
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: 12. 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 48/100
- 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
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 85Steps. 42 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3425 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 17 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
- -32 of 4 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 350: enough signal without eating the budget
- +4Structure: 23 headings
- +3Step-by-step instructions: 42 items
- +4Has examples (9 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.
In the sandbox The scripts kept to themselves
The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.
Запущено 8 скриптов; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.
Из них 2 не дошли до работы, и об их поведении мы ничего не узнали.
agents/observer-loop.sh | ничего за пределами своей папки |
agents/session-guardian.sh | не запустился: session-guardian: outside active hours (336, window 800-2300) |
agents/start-observer.sh | завершился с кодом 1 |
hooks/observe.sh | ничего за пределами своей папки |
scripts/detect-project.sh | ничего за пределами своей папки |
scripts/instinct-cli.py | не запустился: usage: instinct-cli.py [-h] |
scripts/migrate-homunculus.sh | ничего за пределами своей папки |
scripts/lib/homunculus-dir.sh | ничего за пределами своей папки |
6 Oct 2026