AB goal-loop
Goal-driven execution supervisor for complex multi-step work: keeps an explicit goal ledger, runs execute→validate→repair→revalidate, blocks premature or lazy completion, maintains PROJECT-CHECKPOINT.md, and resumes interrupted work from the latest verified state. Use when the user asks to complete, implement, fix, build, deliver, validate, close out, resume, or continue a task where omissions, unverified results, or early stopping would be costly — including software, debugging, websites, documents (Word/Excel/PPT/PDF), data analysis, research, file processing, and multi-agent or long-running projects. Also use when the user says "Run goal check and continue", "Continue from the latest verified checkpoint", "Do not stop while required TODO items remain", or "Stop premature completion and continue". Do NOT use for trivial one-shot requests (simple Q&A, single small edits, quick lookups).
Goal-driven execution supervisor for complex multi-step work: keeps an explicit goal ledger, runs execute→validate→repair→revalidate, blocks premature or lazy…
As a process B 66/100 · Nearly there — weak spots: result and completion, inputs and preconditions, failures and branches
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: 5. 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 66/100
- 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
- 30Running it twice. 7 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 100Tools and files. No external tools needed
- 100Steps. 22 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2881 tokens
- 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
- +3Description length 900: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 18 headings
- +3Step-by-step instructions: 22 items
- +4Has examples (11 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.