MJ-skill/user-explanation-5step/SKILL.md
Use when giving the user an INLINE reply that carries a trade-off, a decision, a verdict, or a non-trivial finding (decision brief / round verdict / failure root-cause). NOT for "done"/status confirmations, one-line answers, or pure data dumps. Forces a compact decision-brief shape and blocks internal tool-name / file-path bleed into user-facing text.
npx skillsauth add develata/deve-skills user-explanation-5stepInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Apply the shared research-comms-policy (style + evidence + no-internal-bleed + Chinese/English density) alongside this skill.
write-research-readout; for method teaching → write-explanation-readout.|Δ| < 0.02 且 CI 上界 < +0.05), not code-style (abs(delta) < 0.02 AND ...).research-comms-policy §5 (professional terms in English; everyday process words in Chinese; no mid-clause mixing).tools
Collect and audit Codex token usage with a bundled Python CLI and optional Windows batch launchers. Use this skill when the user asks to check Codex token usage, generate daily token audit logs, calculate monthly CostUSD totals, review Codex spending, or run Codex token usage scripts on Windows, Bash, WSL, or Linux.
development
Use for cross-file or cross-chapter terminology audits and corpus-wide term unification in thesis/paper sources — extract candidate term drift, build a decision queue, classify each occurrence, apply accepted replacements safely, and verify counts/build. Trigger on "术语审计", "术语统一", "术语一致性", "逐词审", "这个词全文怎么用", "把 X 全文改成 Y", "terminology audit", or "unify term X". Do NOT use for ordinary prose drafting or a single known-location edit; use academic-writing for prose quality and claim-boundary judgment.
tools
Use for ANY codex CLI dispatch via dispatch wrapper (no time threshold; presence-of-risk triggers, not estimated wall — stdin-EOF stalls occur at <60s). Combines internal log-inactivity watchdog wrapper + external Claude-session cron probe + sentinel hook enforcement. Detects stalls in ≤60-270s vs hours-without-detection failure mode.
testing
Use BEFORE proposing any multi-hour task, recommending compromise-vs-clean choice, citing a "named" rule/mechanism, or skipping plan iteration. Five guards against Claude's training-time biases that systematically override user-aligned principles. Triggered by proposal, recommendation, citation, or plan authoring.