CB replication-package
Scaffolds or audits a social-science replication package and evaluates the manuscript and archived research objects against FAIR principles. Scaffold mode writes folder structure, README, master.R, figure-table crosswalk, codebook template, LICENSE placeholder, .gitignore, and a pre-release checklist. Audit mode grades the package and audits data, code, materials, prompts, preregistrations, DOIs, metadata, licenses, access restrictions, and availability statements. Use when setting up or repairing a package, checking one before submission, auditing FAIR, Findable, Accessible, Interoperable, Reusable, or drafting availability statements. Adapted from Yusaku Horiuchi’s replication-package-guide. Platform-neutral across Harvard Dataverse, OSF, Zenodo, GitHub releases, and institutional archives.
Scaffolds or audits a social-science replication package and evaluates the manuscript and archived research objects against FAIR principles.
As a process B 67/100 · Nearly there — weak spots: result and completion, when it triggers, inputs and preconditions
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: AskUserQuestion Read Write Edit Bash
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5967 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 472): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 67/100
- 20When it triggers. No condition that starts the skill
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 11 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 70Execution cost. Instruction body is 5967 tokens
- 85Steps. 77 steps, 2 vague phrases
- 100Tools and files. Tools declared in frontmatter
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 803: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 31 headings
- +3Step-by-step instructions: 77 items
- +4Has examples (10 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.