SKILLEMALL.ai

AB red-team-my-plan

Attack your own plan the way a smart adversary would — find the weakest point, the thing you're hoping nobody notices, and where it breaks under pressure. Use when asked to red-team this, attack my plan, find the holes, or where does this break. Produces an adversarial breakdown of the plan's weakest points, the single move an opponent (or reality) would make to break it, the part you're quietly hoping holds, and the fixes that close the biggest gaps — a hostile stress-test done by your own side, before someone else does it for real.

mohitagw15856/pm-claude-skills Agent Skills author: mohitagw15856 MIT 1 file body ≈ 723 tokens Open the sourcegithub.com analyzed 2 d ago

Attack your own plan the way a smart adversary would — find the weakest point, the thing you're hoping nobody notices, and where it breaks under pressure.

As a process B 70/100 · Nearly there — weak spots: when it triggers, failures and branches, progress reporting

GeneratorSecuritytype and topics are labelled automatically from the skill text
JSON
Technical rating
A
94/100
safety, quality, tests
Safety 60%
99
Quality 40%
87
Run on models
none yet
Process rating
B
70/100
Nearly there
Failures and branches w 10
0
Progress reporting w 2
0
When it triggers w 12
20
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: red-team-my-plan (mohitagw15856/pm-claude-skills)

How to improve

    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 · 1

    ✓ No critical or high findings

    Medium and low: 1
    • low Risky intent intent-offensive-security SKILL.md:28
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
      1. **Adopt the adversary's goal.** Genuinely try to make the plan fail — a real red team, not a gentle review.
      quoted

    Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 70/100

    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 60Result and completion. Output format stated, no completion criterion
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Tools and files. No external tools needed
    • 100Steps. 30 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 723 tokens
    • 100Running it twice. No mutating operations

    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)
    • +1No license
    • +2Single-language instructions
    • +3Description length 539: enough signal without eating the budget
    • +4Structure: 9 headings
    • +3Step-by-step instructions: 30 items
    • +3Output format is stated explicitly
    • +4Has examples (0 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.