earnings-review
Skill23 starsChanged 3 months agoMITView on GitHub
Manual, event-driven earnings review for a US or HK holding, backed by first-party filings. Use when a company reports, when a management promise comes due, or when a thesis review needs primary-source numbers. Produces a structured artifact under memory/earnings/<TICKER>/<period>.json whose earnings-quality math, promise ledger, and thesis evidence are computed by the packaged clawock earnings command — not by prose. Never places trades and never changes thesis state.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- JasmineNy/codex-skills-portfoliotheir own version, first seen Oct 20, 2026
- daloopa/investingtheir own version, first seen Oct 8, 2026
- edinetdb/ai-berkshire-jptheir own version, first seen Jul 11, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- daloopa/investing★ 488same name
- edinetdb/ai-berkshire-jp★ 8same name
- JasmineNy/codex-skills-portfolio★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- site/llms.txtllms.txt
- daily-deep-briefSkill
- entry-gateSkill
- hk-stock-analysisSkill
- openclaw-tuneSkill
- openclaw-upgradeSkill
- portfolio-risk-reviewSkill
- portfolio-swarm-reviewSkill
- scraplingSkill
- serenity-skillSkill
- tavilySkill
- us-stock-analysisSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
Never assert a computed number in prose.
- Very specific: line 71
Every published number needs two independent sources in provenance (see clawock.provenance).
- Distinctive: line 104
No persona scoring and no aggregate "master score" — a red-line or integrity failure is never averaged away by good numbers elsewhere.
- Distinctive: line 106
No trade from a single earnings classification.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Earnings Review
Event-driven, never scheduled. Run this when an issuer reports, when a commitment comes due, or before a thesis review that needs first-party numbers. It is not part of any cron path.
The output is not a report. It is memory/earnings/<TICKER>/<period>.json, and the
Markdown you write afterwards is a rendering of that file.
What the code owns and what you own
Owned by clawock earnings | Owned by you |
Source grade A/B/C and whether footnote claims are allowed | Reading the filing and paraphrasing what it says |
| Cash conversion, FCF, working-capital gaps, dilution, SBC share, margins | Choosing which segments and footnotes matter |
| Guidance beat / inline / miss | Recording the commitment and its measurable target |
Promise roll-forward to met / partial / missed / not_due / unverifiable | Locating the document that proves the result |
| The release gate over the provenance manifest | Deciding whether the period changes the thesis |
Never assert a computed number in prose. Run the script and quote its output.
Step 1 — collect first-party documents
Source order is not negotiable:
- US — SEC filing (10-K/10-Q/8-K) or issuer IR first;
clawock filingssupplies the structured XBRL numbers used to verify them. - HK — HKEX announcement or issuer IR first;
clawock fundamentals(Eastmoney) is a secondary structured source, never a substitute for a footnote. - A third-party summary may only fill a gap, and it lowers the grade.
Record each document once in documents[] with its source_class, a stable
locator, retrieved_at, and whether it covers_period. Store a short paraphrase
and the locator — never long transcript passages.
Grades are mechanical: A needs a covering primary document plus a structured
dataset; B has the dataset but no covering primary document; C is
third-party only. B/C disable every footnote claim, and the validator enforces
that. A low grade describes the sources, not the company.
Step 2 — build the comparable history
At least four comparable quarters (or four half-years, or three annual periods).
basis, currency and unit must be identical across every comparable — a
GAAP/non-GAAP or currency switch mid-history is a validation error, not a caveat.
revenue, net_income and ocf are mandatory per period; anything else you omit
becomes an explicit unavailable with a reason instead of a number.
Step 3 — promises and capital allocation
Carry the previous period's ledger forward; a promise may never be dropped, and
met/partial/missed are terminal.
clawock earnings promises \
memory/earnings/TICKER/<previous>.json memory/earnings/TICKER/<current>.jsonAn overdue promise with no reported result becomes missed when this reporting
period covers its due date, and unverifiable when the due date has merely passed
with no covering report yet. Log buybacks, dividends, M&A, leverage changes,
divestitures and new-business spend in capital_allocation[].
Step 4 — provenance and release
Every published number needs two independent sources in provenance (see
clawock.provenance). The release gate refuses the artifact when
any number is single-sourced or the two sources disagree beyond tolerance.
clawock earnings validate memory/earnings/TICKER/<period>.json
clawock earnings review memory/earnings/TICKER/<period>.jsonreview prints the source grade, the provenance verdict, the quality metrics and
anomaly_flags. A non-zero exit means the artifact is not releasable — fix the
artifact, do not narrate around it.
Step 5 — hand evidence to the thesis, not a verdict
clawock earnings thesis-evidence memory/earnings/TICKER/<period>.jsonThis emits evidence[] rows in the thesis registry's shape plus
dimension_suggestions. It deliberately carries no thesis state. To change a
thesis, append these evidence rows to a new version of
memory/theses/<thesis-id>.json and run the registry's own drift evaluator:
clawock thesis drift old.json new.jsonThe registry re-checks freshness itself and will reject a dimension change that leans on evidence older than the last check.
Hard limits
- No persona scoring and no aggregate "master score" — a red-line or integrity failure is never averaged away by good numbers elsewhere.
- No trade from a single earnings classification. Sizing stays with the existing decision and risk contracts.
- A price move or a headline is not a filing fact.
- Missing documents lower the grade. They never justify a fabricated number.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

