AB zipcracker
CTF-oriented ZIP cracking and recovery with the bundled ZipCracker engine. Use when Codex or OpenClaw needs to analyze or recover an encrypted ZIP in authorized contexts, including pseudo-encryption repair, default dictionary attacks, custom wordlists, mask attacks, short-plaintext CRC32 recovery, known-plaintext attacks, bkcrack workflows, template KPA, WinZip AES triage, or large-dictionary handling. Trigger on requests mentioning zip password, encrypted zip, ZIP challenge, 压缩包破解, ZIP 爆破, 伪加密, 掩码, 四位数字密码, 字典跑一下, 已知明文, 明文攻击, bkcrack, CRC32, AES ZIP, 看起来像 png/exe/pcapng/zip 模板, 这个压缩包打不开, or ClawHub/OpenClaw ZIP solving.
As a process B 67/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- 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: 19. 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 67/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 79 steps
- 100Failures and branches. 13 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2495 tokens
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
- -33 of 5 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 627: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 79 items
- +4Has examples (17 code blocks)
- +4Reference files are cited in the instructions (10 of 10)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.