AD sweeper-plan
Plan a VS Code Sweeper agent-ready issue with the maintainer — fetch the sweeper's review record from its state repo, put the review's open decisions to the maintainer, and write a plan file (.sweeper/plans/issue-<n>.md) for them to edit in their editor; it writes no code and ends there — the sweeper-implement skill implements the approved plan. Use ONLY when the request explicitly asks for the sweeper plan — "sweeper-plan", "plan … with the sweeper", a sweeper record or agent-ready issue to plan first. Do NOT use for a plain planning request that doesn't mention the sweeper.
This skill drafts a plan for VS Code Sweeper by fetching review history from a state repository, surfacing open decisions to the maintainer, and writing a plan file (.sweeper/plans/issue-<n>.md) for manual editing. It generates no code, only prepares the document. Triggers only on explicit sweeper-plan requests—plain planning requests without sweeper mention won't activate it.
Tests show grade A with quality at 93 and safety at 100. No critical issues, files intact. In practice, it acts as a staging gate before sweeper-implement runs—the workflow split is deliberate. Supported across all major platforms and AI models.
Use it if you're in VS Code and need controlled planning before automation kicks in. For one-off tasks without reuse, skip it.
Plan a VS Code Sweeper agent-ready issue with the maintainer — fetch the sweeper's review record from its state repo, put the review's open decisions to the…
As a process D 49/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
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: 1. 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 49/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 5 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (write, web) that frontmatter does not declare
- 100Steps. 18 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2497 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 582: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 18 items
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.