SKILLEMALL.ai
GitHub ↗ RU Sign in

BD env-secrets-manager

Environment and secrets management lifecycle: .env scaffolding, validation, leak detection, and rotation across Vault, AWS SSM, 1Password, and Doppler. Use when setting up projects, scanning for leaked secrets, or rotating credentials.

borghei/Claude-Skills Agent Skills author: borghei 9 files · 4 scripts body ≈ 2 340 tokens Open the sourcegithub.com↗ analyzed 7 h ago

Environment and secrets management lifecycle: .env scaffolding, validation, leak detection, and rotation across Vault, AWS SSM, 1Password, and Doppler. Use…

As a process D 40/100 · Unfinished process — References files that are not bundled: assets/sample.env.example, assets/sample.env.staging, assets/sample.env.production

ProcedureAWSInfrastructureSecuritytype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
B
90/100
safety, quality, tests
Safety 60%
97
Quality 40%
80
Run on models
none yet
Process rating
D
40/100
Unfinished process
References files that are not bundled: assets/sample.env.example, assets/sample.env.staging, assets/sample.env.production
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
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 · 3

✓ No critical or high findings

Medium and low: 3
  • low Secrets in code secret-aws-key assets/sample_leaky_config.py:3
    AWS access key ID (placeholder value)
    AWS_ACCESS_KEY_ID = "AKIA…PLE"
    placeholder
  • low Secrets in code secret-labelled-token assets/sample_leaky_config.py:5
    Labelled token / key literal (vendor format unknown — verify it is not a live credential) (placeholder value)
    api_key = "fake…000"
    placeholder
  • low Secrets in code secret-password-literal assets/sample_leaky_config.py:5
    Hard-coded password / key literal (may be an example) (placeholder value)
    api_key = "fake…000"
    placeholder

Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: assets/sample.env.example
  • warning missing-ref reference to a missing file: assets/sample.env.staging
  • warning missing-ref reference to a missing file: assets/sample.env.production

Process rating: all ten parameters 40/100

Will not run. References files that are not bundled: assets/sample.env.example, assets/sample.env.staging, assets/sample.env.production
  • 0Tools and files. 3 referenced file(s) missing: assets/sample.env.example, assets/sample.env.staging, assets/sample.env.production
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 8 mutating operations with no state check
  • 55Failures and branches. 1 branches
  • 100Steps. 33 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2340 tokens
  • 100Progress reporting. Reports progress
  • low 11 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

  • +5Description has no quoted example phrases that should trigger the skill
  • +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
  • +3Description length 235: enough signal without eating the budget
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 33 items
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (4 of 4)
  • +3All 3 scripts are documented
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.