BC neveragain
David Hogg & Lauren Hogg's "#NeverAgain: A New Generation Draws the Line" — a movement-startup toolkit born from the Parkland school shooting. Covers 5 use cases: ① Student-led organizing & protest planning — ("how to start a movement" "organize a march" "student protest playbook") ② Trauma into action pipeline — ("I want to do something after what happened" "survivor activism" "turning grief into change") ③ Digital & media warfare — ("viral campaign strategy" "social media activism" "counter conspiracy theories") ④ Countering smear / conspiracy attacks — ("they're calling me a crisis actor" "online harassment playbook" "fake news defense") ⑤ Legislative advocacy & 11-point strategy — ("pass a gun law" "lobbying for change" "red flag laws explained") Trigger when users say: "never again" "parkland" "school shooting activism" "how to organize" "student protest" "gun control" "march for our lives" "survivor activism" "youth movement" "david hogg" "lauren hogg" "crisis actor" "mass shooting response" "counter the NRA" "change the narrative"
David Hogg & Lauren Hogg's "NeverAgain: A New Generation Draws the Line" — a movement-startup toolkit born from the Parkland school shooting.
As a process C 63/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- Shorten the description to 1024 characters.
- 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: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1053 chars, limit 1024 - note
edit-residuethe text marks something as outdated (lines 66): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 63/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 32 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2003 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1053: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 31 example trigger phrases
- +4Structure: 8 headings
- +3Step-by-step instructions: 32 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.