SKILLEMALL.ai
GitHub ↗ RU Sign in

BC subwave-worktree-dev

Stage a SUB/WAVE git worktree so the dev stack can run from it, then start it. A git worktree only checks out tracked files — the dev stack also needs gitignored files (controller/.env, web/.env.local, docker/.env, web/node_modules, and a state/ directory) that this skill copies or scaffolds from the main working tree. Use this skill whenever the user wants to test branch changes in a worktree, run subwave from a worktree, "prep"/"set up" a worktree for dev mode, or asks to copy env files / node_modules / state into a worktree — phrases like "test this worktree in dev mode", "start subwave from the worktree", "prep the worktree", "run my branch locally", "copy the required files into the worktree". Do NOT use it for the main checkout (that's subwave-control) or for production.

The skillemall take

The skill stages a git worktree for SUB/WAVE with a complete dev environment. It promises to copy or scaffold gitignored files (env files, node_modules, state/) that worktree won't fetch from the repo, then start the stack. Three components, two scripts, no critical errors—B grades on quality (88) and process (62) suggest functional but unpolished code. Sandbox untested; one medium-severity finding left unexplained. Supports all major platforms.

Worth installing if you test branches via worktree regularly and tire of copying env files by hand. Skip it if worktree is exotic to your workflow.

perminder-klair/subwave Agent Skills author: perminder-klair 3 files · 2 scripts body ≈ 2 145 tokens Open the sourcegithub.com↗ analyzed 6 d ago

Stage a SUB/WAVE git worktree so the dev stack can run from it, then start it.

As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions

ProcedureDockerInfrastructureCommerceSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
B
92/100
safety, quality, tests
Safety 60%
95
Quality 40%
88
Run on models
none yet
Process rating
C
62/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Tools and files w 18
60
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

    For the model run — optional
    • 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 · 1

    ✓ No critical or high findings

    Medium and low: 1
    • medium Dangerous commands cmd-privilege scripts/prep-worktree.sh:153
      Privilege escalation / world-writable permissions
      chmod -R a+rwX "$STATE" 2>/dev/null || true

    Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note edit-residue the text marks something as outdated (lines 16, 18): check that old rules are not kept next to new ones — the full check reads the text for contradictions

    Process rating: all ten parameters 62/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 60Tools and files. Uses tools (web, node) that frontmatter does not declare
    • 60Failures and branches. 2 branches
    • 85Steps. 16 steps, 1 vague phrases
    • 100When it triggers. States when to use and when not to
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2145 tokens
    • 100Running it twice. Mutating operations check current state
    • 100Progress reporting. Reports progress

    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
    • -2localhost URLs: will not work for another user
    • -31 of 2 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 6 example trigger phrases
    • +4Description says when NOT to use the skill
    • +3Description length 787: enough signal without eating the budget
    • +4Structure: 13 headings
    • +3Step-by-step instructions: 16 items
    • +4Has examples (6 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.