agentii-ai/agentii-investment-intelligence

Claude-type skills for institutional equity research — 25 AI agent skills with SEC filings, XBRL financials, earnings calendars, DCF/comps/LBO models, and PPT generation. Powered by agentii.ai data plane. Works with Claude Code, OpenCode, Codex, OpenClaw, Goose.

203Stars on the repository
128Mods indexed here, across every type
todayLast push, which is what freshness is scored on
Apache-2.0Licence, which decides whether bodies are shown

agentii-ai/agentii-investment-intelligence

Skill Claude CodeCodex

Institutional-grade equity research skills for AI agents. 31 Claude-type skills across 5 verticals (equity-research-core, business-intelligence, industry-analysis, models-and-pitches, quantitative-analysis) powered by agentii.ai's agent-use-ready SEC filing data plane — 10 years of filings, XBRL financials, earnings…

not rated 203 changed 4d ago A 149 tokens original Apache-2.0

agentii-ai/agentii-investment-intelligence

Skill Claude Code

Med-adapted earnings preview: consensus estimates, historical surprises, guidance sensitivities, and the FDA-catalyst overlay (PDUFA/AdCom/trial readouts near the print) for biotech/pharma names.

not rated 203 today A 50 tokens Apache-2.0

peer-bench-med

03

agentii-ai/agentii-investment-intelligence

Skill Claude Code

Med peer benchmarking: select actual biotech/pharma peers via the med universe (drug/indication overlap where possible) and compare med-relevant metrics — pipeline depth, catalyst density, cash position, margins, valuation multiples.

not rated 203 today A 49 tokens Apache-2.0

recent-quarter-med

04

agentii-ai/agentii-investment-intelligence

Skill Claude Code

Med-adapted recent-quarter review: last print financials, pipeline-milestone awareness, and FDA-event context — reads the quarter through the med lens (milestones moved, runway, regulatory updates) rather than generic financials alone.

not rated 203 today A 52 tokens Apache-2.0

sector-overview-med

05

agentii-ai/agentii-investment-intelligence

Skill Claude Code

Med-sector overview using the 049 taxonomy (med.medicinesbiotech, med.medicaldevices, med.healthcareservices, med.lifesciencestools) with med trends, catalysts, and FDA-decision context. Use to frame any biotech/pharma analysis before diving into a single name.

not rated 203 today A 65 tokens Apache-2.0

challenge

06

agentii-ai/agentii-investment-intelligence

Skill Claude CodeCodex needs its repo

Adversarial verification of research theses — cross-run/cross-thesis contradiction via the entity index, pre-mortem (Klarman/Kahneman: assume the loss already happened, reverse the path), inversion (Munger: invert, always invert), and wrongif falsifiability review. ≈50-finding cap sorted by severity; content-derived…

not rated 203 today A 101 tokens Apache-2.0

constitution

07

agentii-ai/agentii-investment-intelligence

Skill Claude CodeCodex needs its repo

Scaffold and amend the L1 Investment Constitution — [ALLCAPS] placeholder bootstrap, SemVer bump rules, Sync Impact Report, MINOR/MAJOR re-examination dispatch after the gate-5 budget confirm. Thesis creation stays refused until ratification (Q83).

not rated 203 today A 57 tokens Apache-2.0

converge

08

agentii-ai/agentii-investment-intelligence

Skill Claude Code needs its repo

Append-only gap closure and the cadence engine for research theses. Evaluates artifact CURRENT state (never git history, never task checkboxes) against current pins and wrongif falsifiers, then appends a Convergence section to tasks.md re-proposing the gaps. A clean run leaves tasks.md byte-identical. Deterministic…

not rated 203 today A 93 tokens Apache-2.0

agentii-ai/agentii-investment-intelligence

Skill Claude CodeCodex

The Auto 档 scenario — a soft-plan orchestrator for a complete fundamental equity research thesis: understand → financials → valuation → synthesize. The body is a soft plan (stages), not a rigid DAG; correctness is enforced by each referenced skill's own requires: preconditions, never by this plan's rigidity (Q2).

not rated 203 today A 74 tokens Apache-2.0

implement

10

agentii-ai/agentii-investment-intelligence

Skill Claude CodeCodex needs its repo

Execute research tasks — checklist soft gate, phase dispatch with explicit thesisdir, budget enforcement (halt + approval card on overrun), skillpin recording (versionhash content-hashed per skill directory), [x] written on completion.

not rated 203 today A 48 tokens Apache-2.0

plan

11

agentii-ai/agentii-investment-intelligence

Skill Claude CodeCodex needs its repo

Author the research plan — fundamentals first, trade ideas last; Constitution Check evaluated twice; Deviation Register with mandatory Expiry; emits the four side artifacts (brief/entities/reproduce/contracts). Technical (marketdatastage: early) theses MUST emit the entities.md bars schema before implement (Q42).

not rated 203 today A 61 tokens Apache-2.0

specify

12

agentii-ai/agentii-investment-intelligence

Skill Claude CodeCodex needs its repo

Create a research thesis — theses/{nnn}-{slug}/ via mkdir-as-CAS, pillar-prioritized spec.md, initialized thesis.md, and the thesis-quality checklist. Refuses creation while the workspace constitution is unratified (spec 046 Q83 A+).

not rated 203 today A 58 tokens Apache-2.0

tasks

13

agentii-ai/agentii-investment-intelligence

Skill Claude CodeCodex needs its repo

Decompose the plan into research tasks — one task per ticker × skill × mode, grouped by pillar, [P]-marked by the different-files-and-no-incomplete-deps rule, with source-refs. mode: all expands to N tasks at generation, never exists as one task (Q79).

not rated 203 today A 63 tokens Apache-2.0

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: