BD checkpoint-mode
Pauses for human review every N tasks (selective autonomy). Use when work needs short autonomous bursts with feedback instead of one long run.
This skill makes your AI agent pause after every N tasks and wait for human approval. It promises alternating autonomous bursts with controlled checkpoints—useful when you need short unsupervised work sessions but with feedback loops.
One file, no broken references, no critical issues. Safety scores at 100, quality at 81. The process score of 43 is the catch: the pause mechanism fires, but the task-counting logic or trigger conditions may drift in practice. That means the agent could skip a checkpoint or stop earlier than intended.
Install it if you specifically need this workflow and are willing to tune the N parameter against actual model behavior.
Pauses for human review every N tasks (selective autonomy).
As a process D 43/100 · 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 · 0
✓ No critical or high findings
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "agent_types" - note
frontmatter-keyunknown frontmatter key "research_source" - note
frontmatter-keyunknown frontmatter key "activation"
Process rating: all ten parameters 43/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Steps. 22 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1036 tokens
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 142: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 22 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.