Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Earnings Quality · travisun | DecimalAI

financeby travisun

Earnings Quality

travisun/earnings-quality

Source travisun/opptrix ↗License Apache-2.0

盈利质量分析。用户说「盈利质量」「利润含金量」「应计」「现金流质量」「earnings quality」「/earnings-quality」时使用。vs earnings-quick-read：本技能深挖质量而非速读亮点；含 financial_indicators；不做假造假实锤。默认 create_web。

NewMaintained

Automatic

Finance & Accounting pack

Last verified 9/25/2026

What it changes

Passed 6 of 11 test cases with the skill, and 6 of 11 without it.

Without skill55%

With skill50%

Checks it passed that the model alone missed

The response specifies executing list_web_vendor prior to calling create_web.
The response specifies using read_web or update_web to modify the existing web report.
The report structures content under dedicated sections for Fact, Hypothesis, and Inference.

and 2 more in the full report

5 fixed6 passed either way5 still failing6 broke

Pass-rate lift: -5 pp
Tokens: +1%
Agent turns: 0%
Response time: -23%

Model gemini-3.6-flashMeasured 9/25/2026v111 of 22 cases passed with skill · 11 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/travisun-earnings-quality/SKILL.md https://app.decimal.ai/s/travisun-earnings-quality/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add travisun-earnings-quality, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/travisun-earnings-quality/ and pins it in .decimal/skills.lock

decimalai skills add travisun-earnings-quality

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/travisun-earnings-quality/SKILL.md https://app.decimal.ai/s/travisun-earnings-quality/SKILL.md

Raw file: /s/travisun-earnings-quality/SKILL.md ↗ · machine-readable summary at /s/travisun-earnings-quality.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 5

Prompt

请帮我分析一下最新财报的收益质量与营运资金压力，列出红旗清单。

What was checked, without and with the skill
Checked	Without skill	With skill
The response prompts the user to specify the target company and financial reporting period before proceeding.	Missed	Passed

case-12 · gemini-3.6-flash · 9/25/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md52 linessingle file

盈利质量

何时使用

用户要评估 会计利润的质量与可持续性（现金流匹配、应计、费用资本化线索、一次性项目等），而非只要报告期速读亮点。边界：vs @skill:earnings-quick-read——速读给关键数字变化；本技能给 质量框架与红旗清单。三表完整预测模型用 @skill:financial-model。

分析架构（投研方法）

问题/假设：利润增长是否由经营现金支撑？是否存在质量红旗需跟踪？
证据清单：三表、财务指标、概况中的业务描述
多维交叉验证：净利润 vs 经营现金流；应收/存货 vs 收入；非经常性 vs 扣非（若可得）
结论与不确定：比率与科目为事实；「操纵嫌疑」仅为待查推断，不做造假实锤
风险与缺口：缺指标、跨市场科目名差异
事实 | 假设 | 推断 分栏强制

数据维度

维度	取数方向	缺失时
标的与报告期	`ask_user` / 用户指定	先确认
财务摘要	`get_instrument_financials`	质量结论降级
三表	income / balance / cash_flow 工具	缺表现省略对应检验
指标	`get_instrument_financial_indicators`	用原始科目手算并说明
概况	`get_instrument_profile`	不做强行行业对比
交付	`list_web_vendor` → `create_web`	用户只要口头要点时可跳过

步骤

确认标的与报告期。
取数：财务摘要、三表、get_instrument_financial_indicators。
质量体检：现金转化、应计粗估、营运资本压力、一次性项目（若可识别）。
红旗清单：仅列「待核实」项，禁止实锤造假。
交付网页（默认）：list_web_vendor → create_web；已有则 read_web / update_web。

网页报告建议目录

标的、报告期与时效
利润与经营现金流对照
关键质量指标表
营运资本与应计线索

Track record

Benchmark

6 / 11

test cases passed, vs 6 / 11 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/27/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

travisun / opptrix

packages/agent-skills/builtin/earnings-quality/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/27/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.