AC next
Suggest next actions after completing any task. Auto-invocation via Stop hook + UserPromptSubmit reactive backstop, owned by the `next-invocation-guard` plugin (local-only, ported from `resources/next-trigger.sh` + `resources/next-reactive-guard.sh`). Fires when assistant response contains completion keywords (locale patterns in `data/*.regex`). stall-detect - detect stalled follow-up steps and invoke /fix [stall-detect.md], ask-gates - recording-skip / decision-deferral forced-ask / TaskList primary-source / current-work confirmation gates [ask-gates.md], suggestion-patterns - per-context "After X" next-action option templates [suggestion-patterns.md]. Use when "next action", "what next", "stall", "stuck", "not progressing", "follow-up missing" is mentioned.
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions
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: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6147 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "depends-on"
Process rating: all ten parameters 62/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 6147 tokens
- 100Steps. 27 steps
- 100Failures and branches. 11 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 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
- -5TODO / placeholder text left in the skill
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 769: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 27 items
- +4Has examples (1 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.