DD self-improving-agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
Captures learnings, errors, and corrections to enable continuous improvement.
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
The same skill appears in 1 more place: ClawHub
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 15. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5178 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 46/100
- 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. 18 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, git, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 5178 tokens
- 85Steps. 106 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- low 18 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 445: enough signal without eating the budget
- +4Structure: 42 headings
- +3Step-by-step instructions: 106 items
- +4Has examples (18 code blocks)
- +4Reference files are cited in the instructions (2 of 3)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.
Model run · 19 Oct 2026
No improvement Pass rate 78% is below threshold 80%; Positive triggers activate in 67% of cases (threshold 80%) · 7 cases · $0.103
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 4 скрипта; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.
Из них 1 не дошёл до работы, и об их поведении мы ничего не узнали.
scripts/extract-skill.sh | не запустился: Usage: extract-skill.sh <skill-name> [options] |
hooks/openclaw/handler.js | ничего за пределами своей папки |
hooks/openclaw/handler.test.js | ничего за пределами своей папки |
hooks/openclaw/handler.ts | ничего за пределами своей папки |
3 Oct 2026