SKILLEMALL.ai
GitHub ↗ RU Sign in

AB feature-flag-cleanup

Audit feature flag debt across LaunchDarkly, Unleash, Flagsmith, GrowthBook, Split, and home-grown flag systems. Detects stale flags (older than 90 days, fully rolled out, no toggle activity), classifies them by risk (kill-switch vs experiment vs permission vs ops toggle), tags owners from git blame and CODEOWNERS, generates removal pull requests ordered by safety, and produces a four-week cleanup playbook with rollback plans. Use when asked to find dead flags, reduce flag debt, plan a flag cleanup sprint, write a flag-removal PR, decommission a vendor flag service, or audit flag usage in a monorepo. Triggers on "feature flag", "feature toggle", "launchdarkly", "unleash", "flagsmith", "growthbook", "split.io", "stale flag", "dead flag", "flag debt", "flag cleanup", "flag audit", "kill switch", "rollout", "flag retirement".

ClawHub Agent Skills author: charlie-morrison v1.0.0 MIT-0 2 files body ≈ 5 583 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process B 77/100 · Nearly there — weak spots: inputs and preconditions, running it twice

AnalyzerSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
92/100
safety, quality, tests
Safety 60%
100
Quality 40%
79
Run on models
none yet
Process rating
B
77/100
Nearly there
Inputs and preconditions w 11
0
Running it twice w 4
30
Tools and files w 18
60
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • 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 body-long SKILL.md body ≈ 5583 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 77/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 41 mutating operations with no state check
  • 60Tools and files. Uses tools (python) that frontmatter does not declare
  • 70Execution cost. Instruction body is 5583 tokens
  • 100Steps. 67 steps
  • 100Result and completion. Output format and completion criterion are stated
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 4 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • high The skill tells the model to perform an irreversible action with no human approval

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 834: 120–800 characters recommended
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 15 example trigger phrases
  • +4Structure: 26 headings
  • +3Step-by-step instructions: 67 items
  • +3Output format is stated explicitly
  • +4Has examples (17 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.

External checks

ClawHub: clean
This instruction-only skill helps audit and retire stale feature flags, and its broad repository and flag-service access is disclosed and aligned with that purpose.
LLM: benign (high) · VirusTotal: · 29 May 2026