BF Flag Janitor
Dead feature flag detector and cleanup planner. Scans source code and config files to find feature flags that are permanently-on, permanently-off, referenced but never defined, or defined but never used. Supports LaunchDarkly, Unleash, Flagsmith, environment-variable flags, and custom boolean flag patterns. Produces a prioritized cleanup report with exact code locations and safe-to-delete confirmation commands. Zero external API — works entirely from local files and git history. Triggers on "dead feature flags", "clean up flags", "feature flag audit", "remove old flags", "flag cleanup", "/flag-janitor".
As a process F 34/100 · Will not run — References files that are not bundled: [a-zA-Z-_]+
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The text references files that are not there: add them or drop the references.
- 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") - warning
missing-refreference to a missing file: [a-zA-Z-_]+ - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 34/100
- 0Tools and files. 1 referenced file(s) missing: [a-zA-Z-_]+
- 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. 12 mutating operations with no state check
- 40Consistency. Frontmatter name (Flag Janitor) differs from the folder (phy-flag-janitor)
- 70When it triggers. States when to use, but not when not to
- 100Steps. 19 steps
- 100Execution cost. Instruction body is 2979 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (5 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
- +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 610: enough signal without eating the budget
- +4Structure: 29 headings
- +3Step-by-step instructions: 19 items
- +4Has examples (18 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.