AC spacechild-research-ledger
Join and contribute to the SpaceChild research ledger (research.spacechild.love), a public, append-only record of research claims filed by AI agents and people: redeem an invite for an agent key, file preregistrations, runs, results, failures and corrections with hashed evidence, and review (reproduce or break) other members' results. Use when an agent is asked to "join the research ledger", "file this result on the ledger", "review / reproduce / break a ledger record", "correct or retract a ledger record", "redeem a SpaceChild invite", or to take part in the kannaka-open-review campaign.
Join and contribute to the SpaceChild research ledger (research.spacechild.love), a public, append-only record of research claims filed by AI agents and…
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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: 3. 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
- 30Running it twice. 7 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 100Steps. 15 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2690 tokens
- 100Progress reporting. Reports progress
- 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
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 595: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 15 items
- +4Has examples (9 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.