AB organize-task-package
Organize discussed or evolving development, repair, testing, research, migration, or complex operational work into an executable, resumable, independently reviewable task documentation package, then derive a launch configuration from the current request and relevant task-family history for user confirmation. Use when Codex needs to record a task, create a dated task directory, split verifiable work items, freeze implementation and validation plans, create GOAL documents, arrange or reuse Worker and Reviewer sessions, coordinate parallel worktrees, confirm execution settings, maintain execution receipts, or audit task completion. Do not use for a short one-off task that does not need durable records.
Organize discussed or evolving development, repair, testing, research, migration, or complex operational work into an executable, resumable, independently…
As a process B 68/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
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
-
low Concealment
en-hide-from-userreferences/launch-configuration.md:191Instruction to hide actions from the user (negated — the text forbids it)Fail closed when the requested pair is unsupported or the tool cannot enforce it: keep execution unauthorized, record `mismatch`, and ask for a replacement model, reasoning level, or topology. Never s
negated
Files scanned: 12. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5060 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 25 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 70Execution cost. Instruction body is 5060 tokens
- 100Tools and files. No external tools needed
- 100Steps. 74 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 708: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 74 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (8 of 8)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.