AC llm-safe-write
Safely write large files or files with CJK/special characters using incremental Edit strategy instead of direct Write. Use when: writing a file longer than 50 lines, file contains CJK characters (Chinese/Japanese/Korean), Write tool failed with "Unterminated string" or JSON truncation, writing Python/JS/TS files with multiple functions, embedding CJK strings in source code, user says "write failed", "file won't write", "large file write", "CJK write error", "encoding error on write", or "file too long to write". **Do NOT undertrigger** — when a file may exceed 50 lines or contain non-ASCII characters, use this Skill proactively instead of bare Write.
Safely write large files or files with CJK/special characters using incremental Edit strategy instead of direct Write.
As a process C 64/100 · Has gaps — weak spots: result and completion, 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: 3. 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 64/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 8 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, read, web, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 51 steps, 1 vague phrases
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3013 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 658: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 51 items
- +4Has examples (5 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.