BC parallel-orchestrate
Master orchestration skill that takes a gstack implementation plan and ships it via parallel Claude Code subagents in isolated git worktrees. Sits between /autoplan (or /plan-eng-review) and /review + /ship. Shreds plans into parallelizable subtasks, dispatches them wave-by-wave with worktree isolation, verifies each wave, and hands off to /review and /ship. Use when asked to "orchestrate this plan", "ship this plan", "parallel-orchestrate", "/parallel-orchestrate", "execute this plan in parallel", "parallelize this plan", "run plan in waves", "shred and ship", or "dispatch subagents for this plan". Proactively suggest when the user has a finished plan file (e.g. plans/*.md) and wants to execute it without manually dispatching subagents. Voice triggers (speech-to-text aliases): "gee stack orchestrate", "g stack orchestrate", "orchestrate the plan", "ship the plan in parallel", "execute the plan".
As a process C 63/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash Read Write Edit Glob Grep Agent TodoWrite AskUserQuestion Skill
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 10079 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "repository"
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
- 30Running it twice. 26 mutating operations with no state check
- 40Execution cost. Instruction body is 10079 tokens: crowds the task out of the window
- 70When it triggers. States when to use, but not when not to
- 85Steps. 56 steps, 1 vague phrases
- 100Tools and files. Tools declared in frontmatter
- 100Failures and branches. 23 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 909: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +2Single-language instructions
- +5Description quotes 14 example trigger phrases
- +4Structure: 40 headings
- +3Step-by-step instructions: 56 items
- +4Has examples (29 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.