BD i18n Audit
i18n key coverage auditor for multi-locale codebases. Diffs every locale file against the base locale to find missing translation keys, untranslated values (value identical to source language), empty strings masquerading as translations, and orphaned keys that exist in secondary locales but not in the base. Supports JSON (i18next, react-intl, vue-i18n), YAML (Rails i18n), PO/POT (gettext), ARB (Flutter), and nested/namespaced key structures. Reports a per-locale coverage percentage, flags the highest-impact missing keys (used in the most templates), and generates a CI fail-gate command. Zero external API — pure local file analysis. Triggers on "missing translations", "i18n coverage", "untranslated keys", "locale audit", "which strings are not translated", "/i18n-audit".
As a process D 42/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 42/100
- 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
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 5 mutating operations with no state check
- 40Consistency. Frontmatter name (i18n Audit) differs from the folder (phy-i18n-audit)
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 85Steps. 12 steps, 1 vague phrases
- 100Execution cost. Instruction body is 3552 tokens
- low 10 top-level sections: this looks like several domains in one skill
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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 780: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 12 items
- +4Has examples (16 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.