portfolio-review
Skill2 starsChanged 51 days agoMITView on GitHub
Review a sourced personal balance sheet, cross-account exposure, and hypothetical trades against the user's explicit limits. Use for portfolio checkups and proposal assessment, not order execution.
15 other projects use a version of this.
Adopted by
Most recently taken up by
- PatrickSUDO/fadacai-portfoliotheir own version, first seen Nov 13, 2026
- CSPulse/customer-success-skillstheir own version, first seen Nov 8, 2026
- rgourley/quant-garagetheir own version, first seen Nov 1, 2026
- Shubhamkumartrichy/claude-trading-skills-indiatheir own version, first seen Nov 1, 2026
- JasmineNy/codex-skills-portfoliotheir own version, first seen Oct 20, 2026
- monellonasti/portfolio-pipelinetheir own version, first seen Oct 17, 2026
Used with
Projects with it also use thesis-tracker.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
OpenAISkillthesis-tracker
Use when building or updating Public Equity Investing thesis trackers. Do not use for generic news summaries, trade pitches, or first-pass memos.
Also in 3 projects that use this
Other versions15 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 15
- digitalinnovationone/dio-agent★ 2.8ksame name
- PatrickSUDO/fadacai-portfolio★ 145same name
- Shubhamkumartrichy/claude-trading-skills-india★ 64same name
- nimadorostkar/Claude-Skills-collection★ 37same name
- Mozurok/fhorja.dev★ 10same name
- rgourley/quant-garage★ 7same name
- CSPulse/customer-success-skills★ 2same name
- ryanbaumann/fieldwork★ 2same name
- tusharagg1/aifolimizer★ 2same name
- yeshelloAB/investment-analysis-skills★ 1same name
5 more not listed
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 repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- finance-dashboardSkill
- finance-gatherSkill
- finance-memorySkill
- finance-planSkill
- finance-setupSkill
- investment-researchSkill
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 4 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 14 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Use the installed finance-core.
- Very specific: line 15
Read the selected private workspace's setup.md and the active project's applicable AGENTS.md, when present, to resolve the interpreter and …
- Very specific: line 19
Read ledger.json, rules.json, facts.json, and decisions.json in the selected private workspace.
- Distinctive: line 32
Read review semantics before interpreting totals or proposals.
- Distinctive: line 35
Do not describe securities or private investment marks as available cash.
- Distinctive: line 41
Add such analysis only with sources and a stated method.
- Very specific: line 43
Read the user's actual limits.
- Very specific: line 51
Use the proposal contract.
- Distinctive: line 56
Do not describe a limit flag from the calculation as a broker block or execution safeguard.
“Common” is measured: kept by at least 6 in 10 of the 14 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Portfolio review
Explain the portfolio's condition and the effect of a proposed change using verified inputs. A stock's research rating and suitability for this portfolio are separate questions.
Load the current state
Use the installed finance-core; inspect finance-core --help if needed. The runtime
must be installed from the trusted project checkout in a dedicated environment.
Read the selected private workspace's setup.md and the active project's applicable
AGENTS.md, when present, to resolve the interpreter and any documented status, summary, or research
adapter. Preserve the project's existing context and risk checks. Run the commands
yourself; explain results and needed inputs in ordinary language.
Read ledger.json, rules.json, facts.json, and decisions.json in the selected
private workspace. Resolve superseded records and distinguish confirmed decisions
from earlier model suggestions. This skill is usable without sibling skills.
Run finance-core validate --workspace /private/path, then
finance-core summary --workspace /private/path --as-of YYYY-MM-DD using the review date.
Review source dates, currency/FX dates, included accounts, restricted assets, and
known coverage gaps. Confirm that wrapper accounts are not counted twice.
Missing, stale, unverified, estimated, or future-dated data cannot support a definitive
within-limits finding. A successful schema check does not establish complete coverage.
Explain the balance sheet
Read review semantics before interpreting totals or proposals. Distinguish gross assets, liabilities, net worth, unrestricted cash, and restricted or illiquid assets. Label unknown totals and partial coverage explicitly. Do not describe securities or private investment marks as available cash.
Aggregate a security across included accounts using the actual security identity. Confirm any mapping between share classes, ADRs, or listings before combining them. The core aggregates exact symbols; it does not infer economic equivalence, fund look-through exposure, sector classification, correlations, or option delta exposure. Add such analysis only with sources and a stated method.
Read the user's actual limits. null means report only, not zero and not permission
to choose a threshold on their behalf. If the user explicitly sets a limit, update
only the relevant rule and record that confirmed choice with its date and source.
Explain observed concentration or leverage even when no threshold is configured.
Evaluate a proposal
Capture account alias, security, side, quantity, proposed price, and as-of date.
Use the proposal contract; keep the input in the private workspace.
Run finance-core review --workspace /private/path --proposal /private/path/proposal.json.
Report its status and reasons, including needs_data or report-only results.
The calculation uses a hypothetical cash-funded transaction and does not execute it.
Do not describe a limit flag from the calculation as a broker block or execution safeguard. The calculation also does not model taxes, fees, lot selection, slippage, settlement, or future price paths. Research those separately when they affect the user's requested decision. Unknown tax basis or jurisdiction cannot be replaced by an assumed zero tax cost. State a proposal's funding source; do not infer margin authorization from buying power.
Write and save the review
Lead with the material finding and its practical implication. Compare current and proposed values on the same as-of date and valuation basis, with a short assumptions table where useful. Cite the exact private snapshot, rules, and proposal files. Separate measured facts, model-generated research, and your conditional assessment.
Save the review privately. Record an unaccepted idea only as proposal; a confirmed
decision is not an executed trade. Reconcile actual fills through subsequent
account evidence before updating positions. No command in this workflow places orders.
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.

