AC insforge-cli
Use this skill whenever the user needs backend infrastructure management — creating database tables, running SQL, deploying serverless functions, managing storage buckets, deploying frontend apps, adding secrets, setting up cron jobs, or checking logs — especially if the project uses InsForge. Trigger on any of these contexts: creating or altering database tables/schemas, writing RLS policies via SQL, deploying or invoking edge functions, creating storage buckets, deploying frontends to hosting, managing secrets/env vars, setting up scheduled tasks/cron, viewing backend logs, or exporting/importing database backups. If the user asks for these operations generically (e.g., "create a users table", "deploy my app", "set up a cron job") and you're unsure whether they use InsForge, consult this skill and ask. For writing frontend application code with the InsForge SDK (@insforge/sdk), use the insforge skill instead.
As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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: 9. 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 56/100
- 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. 50 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 65Failures and branches. 3 branches
- 70When it triggers. States when to use, but not when not to
- 100Steps. 65 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3282 tokens
- low The response is described with custom markup (26 tags): a typed call is more reliable
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 924: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +4Structure: 33 headings
- +3Step-by-step instructions: 65 items
- +4Has examples (13 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.