AD fork-manager
Manage forks with open PRs - sync upstream, rebase branches, track PR status, and maintain production branches with pending contributions. Supports automatic conflict resolution via --auto-resolve flag (spawns AI subagents to resolve rebase conflicts). Use when syncing forks, rebasing PR branches, building production branches that combine all open PRs, reviewing closed/rejected PRs, or managing local patches kept outside upstream. Requires Git and GitHub CLI (gh).
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, 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: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 9501 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 49/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 40Execution cost. Instruction body is 9501 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash, web, git) that frontmatter does not declare
- 60Steps. 139 steps, 4 vague phrases
- 100Failures and branches. 4 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
- low 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (5 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -214 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 468: enough signal without eating the budget
- +4Structure: 57 headings
- +3Step-by-step instructions: 139 items
- +4Has examples (35 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.