AB community-building-playbook
Build and grow developer and user communities from scratch — covering ambassador programs, community-led growth (CLG), event operations, content strategy, and health metrics. Grounded in real playbooks from Notion, Lovable, AFFiNE, ClickUp, Asana, and Lark. Use when: building a community for an open-source project, SaaS product, or brand; recruiting and managing ambassadors or community leaders; planning community events (online/offline meetups, AMAs, hackathons); designing ambassador tier/points systems; setting community health KPIs; launching a Build-in-Public strategy; setting up Discord, Slack, or Lark communities; running developer relations (DevRel); or when the user asks about community operations, ambassador programs, CLG, user advocacy, KOC/KOL cultivation, UGC flywheels, community monetization, or any variation of "how do I grow my community".
As a process B 69/100 · Nearly there — weak spots: result and completion, progress reporting
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: 4. 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 69/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4440 tokens
- 85Steps. 75 steps, 2 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 866: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -221 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +4Structure: 37 headings
- +3Step-by-step instructions: 75 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.