AC forge
Forge-agnostic git-host driver contract. Lets code-workflow / github-flow / harness pipelines run independent of the underlying git forge (GitHub, GitLab, Gitea) through a normalized driver interface + a `--forge=<github|gitlab|gitea>` dispatch idiom with git-remote auto-detection (github fallback). Use when: designing or reasoning about forge-portable PR/MR/issue/merge operations, adding a new forge adapter, deciding how a pipeline should degrade when a forge lacks a capability (PR↔PR dependency, sub-issues, Copilot review), or normalizing repo visibility (PUBLIC/INTERNAL/PRIVATE) and reference formats (`#N` vs MR `!N`) across hosts. Triggers: "forge", "forge-agnostic", "--forge", "forge driver", "gitlab", "gitea", "glab", "tea", "MR", "capability flag", "adapter".
As a process C 63/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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: 10. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "depends-on"
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
- 20When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 8 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 898 tokens
- 100Running it twice. No mutating operations
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
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 776: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 8 items
- +4Has examples (2 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.