Agent skill · research science · alirezarezvani
dossier
Use for diligence or meeting prep on a specific company, person or organization ('prep me for a meeting with X', 'due diligence on Y'). Tests the user's stated hypothesis with balanced evidence (disconfirming_evidence_balance.py) and writes a .docx dossier.
Why this skill is useful
Adds a structured methodology for hypothesis-driven research, including specific output formats and API integrations that enhance the AI's research capabilities.
What it needs
Requires bash_tool, curl, docx, node installed locally. Requires apollo, crunchbase, linkedin, pitchbook, similarweb account access. About 9k tokens when loaded. Last updated 2026-08-05. 23,939 stars on the source repository.
What this skill does
Dossier — Decision-Grade Entity Research Portability: Requires WebSearch + WebFetch, Node.js with docx package, and optionally bashtool + curl for free APIs (SEC EDGAR, GitHub, ProPublica). BYOK MCPs (LinkedIn, Crunchbase, Apollo, Pitchbook, SimilarWeb) are optional enhancements. Works in Claude Code CLI natively. Non-Generic Framing — The Differentiator This skill is decision-grade entity research with hypothesis-testing. It refuses to be "tell me about Microsoft". Every invocation forces the user to expose their hypothesis upfront (Q4) so the dossier tests it rather than confirms it. The use case shape: "I'm pitching Microsoft Tuesday. My hypothesis is they're consolidating AI spend on their first-party Foundry platform. Validate or disprove, and give me three conversation hooks tied to what you find." NOT: "Tell me about Microsoft." The forcing Q4 — the hypothesis question — is the non-generic anchor. Skip it and the skill produces a Wikipedia summary. See references/hypothesistestingdiscipline.md for the canon. Agent Integrity Rules (Research-Pack Convention) Locked verbatim per PR #657 audit. Execution discipline. Sequential search calls. WebSearch + WebFetch have looser rate limits than Consensus but still apply 1 q/sec etiquette. Confirm response received before next call. Source discipline. Cite only sources returned by this session's tool calls. Wikipedia / training knowledge labeled [Background — verify before quoting] and excluded from primary findings count. Three-count tracking. Queries sent / sources received / sources cited. Plus per-tier breakdown (primary / secondary / tertiary) unique to dossier. Surfaced in audit log. Retry policy. On failure → wait 3s → retry once → log. After 3 consecutive failures: stop, alert user. Source reliability tier. Each citation tagged primary (official, SEC, court records) / secondary (mainstream news, trade press) / tertiary (blogs, forums). DOCX surfaces tier on every flag. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills alirezarezvani/dossier--50fcb3