The research-domain clarification skill — find underspecified items in a thesis spec.md (prose wrong_if, universe rows without rationale, missing budget/expiry/pins, ambiguous pillars), ask the human structured questions WITH options (max 5 per round), encode the answers back into spec.md's Clarifications section, and re-evaluate checklists/thesis-quality.md after every write (Q32 bidirectional maintenance).
インストールする前に、エージェントに与えられる指示の中身を確認できます。
The 8th kit command — closes the gap Q32 itself assumed: upstream
speckit-clarify re-evaluates the quality checklist after every spec write, but
spec 046 never named the command that performs the clarification.
Both phases run kit Python. Resolve the kit root once per shell first —
contracts/kit-root.md. The kit's scripts do NOT ship with the skills, and this
skill's old path (kit-scripts/, below) did not exist at all: it named a directory
that has never been in this repository, so every documented invocation of clarify
failed with "No such file or directory".
# Resolve the kit root — contracts/kit-root.md. Never assume the CWD is the checkout.
KIT=""
for c in "${AGENTII_KIT_ROOT:-}" \
"$(cat "$HOME/.claude/skills/agentii/.kit-root" 2>/dev/null)" \
"${CLAUDE_PLUGIN_ROOT:-}"; do
[ -n "$c" ] && [ -f "$c/scripts/agentii_cmd.py" ] && { KIT="$c"; break; }
done
if [ -z "$KIT" ]; then d="$PWD"; while [ "$d" != "/" ]; do
[ -f "$d/scripts/agentii_cmd.py" ] && { KIT="$d"; break; }; d="$(dirname "$d")"; done; fi
[ -n "$KIT" ] || { echo "agentii kit not found — see contracts/kit-root.md" >&2; exit 1; }
python3 "$KIT/scripts/agentii_cmd.py" clarify --thesis theses/001-… --questions
Emits a JSON list of candidate questions, each with:
id (stable — content-derived from the target)target (pillar id / field / universe row)question (exact, in the spec's working language)options (derived where possible; null = free-form)Candidates come from a deterministic scanner (never vibes): prose wrong_if
(missing metric=/threshold=/source=), universe rows without rationale,
missing budget, missing expiry_triggers, subscription tokens not in
TICKER × skill form, missing as_of/pins, pillars without priority.
# $KIT comes from `## Invocation` above — re-run that resolver if this is a new shell.
python3 "$KIT/scripts/agentii_cmd.py" clarify --thesis theses/001-… --answers '<json>'
spec.md's ## Clarifications section
(- [YYYY-MM-DD] Q: … → A: …).checklists/thesis-quality.md after the write (Q32: the
machine-maintained checklist is bidirectional — report "N/M items passing"
plus regressions).まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
3-statement financial model, integrated IS BS CF, income statement projection, balance sheet forecast, cash flow statement, cross-statement balancing, financial model build, operating model, three statement model, integrated financial statements
日本語の概要は準備中です。原文の説明を表示しています。
Institutional-grade equity research skills for AI agents. 80 Claude-type skills across 14 verticals (equity-research-core, models-and-pitches, bio-pharm, scenarios, quantitative-analysis, idea-generation, options-derivatives, business-intelligence, industry-analysis, macro-strategy, portfolio-strategy, technical-analysis, risk-and-psychology, trading-as-business) powered by agentii.ai's agent-use-ready SEC filing data plane — SEC filings and 15K+ earnings call transcripts, 15.99M XBRL facts, and company profiles for 1,146+ US-public-equity tickers. Features the three-layer retrieval protocol (Document Discovery → Page Map → Deep Read, with deep-outline escalation) — measured, not asserted: 97.5% saved against a sequential read, and the page map itself is 10.0% of one (spec 062 T030, 2026-09-23) — server-side parallel multi-period search via search_cross_period, a full Excel/PPT generation pipeline with 3-tier office backend support, and the spec-046 governance layer (constitution, thesis and single-skill modes, mechanical gates, and a template-owned disclaimer on generated reports).
日本語の概要は準備中です。原文の説明を表示しています。
Audit spreadsheet, formula error detection, hardcoded cell finder, cross-sheet reference audit, workbook auditor, Excel model audit, financial model QA, spreadsheet review, cell dependency trace, formula integrity check
日本語の概要は準備中です。原文の説明を表示しています。
Business model classification, business model analysis, structural analysis of how a company makes money, product offering decomposition, distribution channel analysis, customer segment analysis, revenue model identification, market sizing TAM SAM SOM, competitive positioning, business unit performance, management team & leadership analysis, what does the company sell, how does the company go to market, business model type platform service product, channel mix direct vs indirect, revenue concentration risk, CEO CFO executive backgrounds and changes
日本語の概要は準備中です。原文の説明を表示しています。
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 wrong_if falsifiability review. ≈50-finding cap sorted by severity; content-derived finding IDs; incremental scoping with three backstops; lifecycle hooks at pillar-complete / thesis-complete / pre-reduction.
日本語の概要は準備中です。原文の説明を表示しています。
Chart pattern recognition, price action patterns, candlestick signal bars, pullback bar counting H1/H2/H3/H4, trend channels, micro channels, trading ranges, breakouts, major trend reversals 5-step sequence, wedges, double tops and bottoms, triangles, head and shoulders, climaxes, measured moves, support and resistance
日本語の概要は準備中です。原文の説明を表示しています。