Audits a proposed numeric heuristic, threshold, cap, or empirical claim destined for SKILL.md or a reference file against AZIMUTH's existing evidence base. Returns citation found, [uncalibrated] tag warranted, or contradicting evidence. Read-only — never modifies SKILL.md or references. Use before any new…
Stress-tests a pasted AZIMUTH analysis output against the skill's own structural rules. Use when a real AZIMUTH verdict has been produced and needs adversarial review for sycophancy, confidence inflation on cautious verdicts, output discipline failures, or hook-rule violations. Read-only — never modifies the skill or…
Audits AZIMUTH's coverage completeness. Cross-references what SKILL.md claims to handle against what reference, diagnostic, and domain-policy files actually cover. Identifies thin coverage, missing domains, and structural inconsistencies. Run before major version planning.
Authoring discipline for new AZIMUTH reference files and templates. Use when adding a new domain reference file, extending an existing one, or creating a new template. Covers: (1) EXTEND vs. CREATE decision heuristic, (2) the Module 7 vocabulary header pattern that prevents domain-gap recurrence, (3) the sourcing…
Tracks AZIMUTH's 8 primary citation source families for new publications or significant updates. Stages validated findings in research/staged-findings.md for human review before promotion to references/base-rates.md. Invoke with 'run the research scout' or 'promote staged findings'.
Stress-tests an AZIMUTH output against the skill's own structural rules. Paste an AZIMUTH output and invoke to get a severity-rated diagnostic. Diagnoses only — does not rewrite. Use after any real AZIMUTH session to detect quality drift.
Decision-quality pre-commitment analysis for initiative-level go/no-go calls with meaningful downside and limited reversibility — launches, rewrites, key hires, partnerships, strategic bets, timelines. Invoke when the user explicitly asks to pressure test, validate, or evaluate such a decision (e.g. 'should we do…