BC gingiris-twitter-agent-ops
Twitter/X Agent Operations SOP v2 — Rebuilt from real dual-account operations. Real data: • CN account: grew from 1,150 → 3,679 followers (~14 months), 1 tweet/day, OAuth1 direct post • EN account: Buffer API • Real incidents: cron silent-failed for 2 weeks unnoticed, analytics data off by 17×, thread performance worse than single posts What's new in v2: • Step-by-step onboarding (Q1→Q6), multiple choice wherever possible — no big forms • Mandatory daily log after every tweet + weekly report every Monday • Pre-publish safety checklist (agent must pass before posting) • Content pool tracker (used/unused) + alert when ≤3 items remain • Dual-account credential separation (CN: OAuth1 / EN: Buffer API) • MASTER-STATUS.md as the single source of truth — read + write every session 🇨🇳 Twitter/X Agent 运营 SOP v2 — 基于真实双账号运营经验重写。 开局对话式收集 context、强制日报+周报、发推前红线自检、素材库追踪、双账号凭证分离、MASTER-STATUS.md 单一真相来源。 真实数据：中文账号从 1,150 粉增长至 3,679 粉（约14个月），1条/天。 Triggers: "twitter运营" | "推特agent" | "发推SOP" | "AI代运营" | "推文日报" | "素材库" | "Buffer API" | "OAuth1发推" | "twitter automation" | "tweet sop" | "推特涨粉"
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Shorten the description to 1024 characters.
- 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: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1096 chars, limit 1024
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 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
- 30Running it twice. 1 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 18 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3183 tokens
- low 13 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1095: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -213 emoji in the instructions: noise for the model
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Structure: 33 headings
- +3Step-by-step instructions: 18 items
- +4Has examples (15 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 55.