Results for “verdict”

Reviews code diffs or explicit file sets through independent correctness and QA lenses, producing a severity-ordered verdict for pre-merge audits or review gates.

Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.

Verify the accuracy of claims and statements by extracting individual assertions, identifying authoritative sources, cross-referencing evidence, and assigning confidence-scored verdicts. Use when the user requests fact checking or provides relevant inputs for this workflow.

Assesses NumPy code for cuPyNumeric migration readiness by analyzing source code against an API support manifest and GPU-scaling idioms, producing a structured verdict with per-finding reasoning.

Conducts patent prior-art searches and landscape intelligence across Google Patents, Espacenet, USPTO, and Lens.org, producing an editable Word document with verdict and ranked closest art.

Scores any US stock ticker through Warren Buffett's four-lens framework (business simplicity, moat, management, valuation) and returns a weighted HOLDABLE/WATCHABLE/AVOID verdict.

Audits source code across C++, Android, iOS, and Web to classify files, detect embedded third-party libraries, and produce four-level verdicts with interactive HTML reports.

Use before a tag, GitHub release, or Zenodo archive, when README, CATALOG, CHANGELOG, CITATION.cff, the disclosure aggregate, and skill discovery must agree, or when a go or no-go release verdict needs recorded evidence behind it.

Runs a six-phase security audit covering attack-surface mapping, STRIDE/PASTA threat modeling, technical checklists, red/blue team exercises, and a final verdict, plus incident-response and monitoring guidance.

Runs a structured security audit across six phases: attack-surface mapping, STRIDE/PASTA threat modeling, technical checklists, red/blue team analysis, and a final verdict, with optional Python automation scripts.

Use when paired tr.md and en.md files need a parity verdict, when titles, frontmatter, headings, or DOI sets may have drifted between languages, or when a bilingual document is approaching release and its translation coverage needs an audit.

Benchmark-relative quality gate. Scores the draft against the research dossier's beat spec (depth, consensus coverage, evidence) plus AI-tell and voice signals, runs an adversarial read armed with the SERP benchmark, and emits the verdict that gates the pipeline.

Performs a comprehensive cross-artifact QA/QC review of a virtual team pipeline, checking completeness, consistency, security, and compliance, then issues an advisory verdict with quality, compliance, and sign-off reports.

Runs a structured 6-phase security audit covering attack-surface mapping, STRIDE/PASTA threat modeling, technical checklists, red/blue team exercises, and a final verdict, plus incident-response and monitoring playbooks.

Scans source code repositories across C++, Android, iOS, and Web to classify files, detect embedded third-party libraries, and produce actionable four-level verdicts per module with interactive HTML reports.

Pressure-test any business idea with a five-angle adversarial panel (Critic, Champion, Analyst, Investigator, Customer) that returns a single GO/RESHAPE/KILL verdict with the cheapest test to de-risk it.

Automates the collection of suspicious files from endpoints and email gateways, submission to sandbox and multi-engine scanners, and generation of verdicts with IOCs for SIEM integration.

Verifies a claim by finding primary sources and rates the evidence as supported, mixed, unsupported, or unverifiable, with citations and what would change the verdict.

Reviews a plan from a prior session by extracting the canonical reference prompt from seed/plan-reviewer-design.md and invoking the plan-reviewer agent with it, surfacing the verdict without auto-applying changes.

Runs a structured security audit across six phases: attack-surface mapping, STRIDE/PASTA threat modeling, technical checklists, red/blue team exercises, and a final verdict, covering code, infrastructure, APIs, bots, payments, AI agents, and compliance.

Reconcile canonical declarative documents under docs/ with verified implementation discoveries after a FULLY_IMPLEMENTED moonspec-verify verdict. Use when an orchestration run must decide whether verified discoveries show the owning canonical document is impossible, unclear, or inconsistent, apply the smallest correct doc update, or escalate ambiguous authority conflicts and deliberate divergences instead of editing.

Produces a decision-grade dossier on a specific company, person, nonprofit, or government org by testing the user's hypothesis rather than confirming it. Outputs an editable Word document with verdict, identity facts, 12-month activity timeline, network and reputation signals, and red flags.

Verifies that every entry in a bibliography ACTUALLY EXISTS by cross-checking it against four keyless public scholarly APIs (Crossref, OpenAlex, Semantic Scholar, arXiv) with a polite mailto identifier, resolving DOI/arXiv IDs, fuzzy-matching title and authors (difflib SequenceMatcher ratio >=0.70), flagging retractions marked in Crossref (update-to) or OpenAlex (is_retracted), and emitting per-entry JSON verdicts mapped to the AlterLab citation-hallucination taxonomy (TF/PAC/IH/PH/SH). Accepts BibTeX, a DOI/arXiv ID list, or free-form references; degrades gracefully offline by emitting 'unverified' verdicts and never silently passing. Use when the request mentions verify citations, check references, fabricated or hallucinated references, fake DOI, retraction check, bibliography audit, or reference existence check. Does NOT write or draft papers — for authoring a manuscript (whose citation-check mode inserts citations) prefer alterlab-paper-writer instead. Part of the AlterLab Academic Skills suite.

Use when asked to "QA this", "is this ready to ship?", "test it like a user", "bug hunt", "sign off this build/phase", or before declaring a web app / feature shippable — a real-user QA pass that files severity-ranked bug reports and returns a binary ship verdict. Not for visual/CRO polish (frontend-audit) or fixing an already-reported UI bug (ui-fix-observe-first).

Turn "is this deal real?" into a deal-by-deal risk verdict. An 8-state risk taxonomy, a qualification-vs-stage gap check, multi-thread coverage, days-dark per deal, and a commit-creep watch. Built for B2B sales teams, customizable to your CRM and your sales process. Trigger on "how are my deals", "which deals are stuck", "what's at risk this month", "is the rep sandbagging", "multi-thread check", or any open-deal diagnostic.

Turn "what's the plan" into a GTM plan you can defend, verdict-first. Names the two or three bets, the motions behind each, the targets, the capacity math that says whether the number is reachable, and the risks that would break it. Built for B2B GTM leaders, customizable to your model and stage. Trigger on "build our GTM plan", "plan the quarter", "is this number reachable", "what are our bets", "annual GTM planning", "do we have the capacity", or any planning cycle.

Verify a Jira issue against the current repository state, then post a Jira comment with a PASS, PARTIAL, FAIL, or BLOCKED verdict. Works in two modes: (a) feature-branch mode, comparing a checked-out branch to its base ref; or (b) main/trunk mode, verifying that an issue is already implemented on the current default branch (typical for stories that have already merged). Use when a user asks whether a branch or merged change completes a Jira ticket, or needs a Jira-visible verification comment.

Verify a GitHub issue against the current repository state, then post a GitHub issue comment with a PASS, PARTIAL, FAIL, or BLOCKED verdict. Works in two modes: (a) feature-branch mode, comparing a checked-out branch to its base ref; or (b) main/trunk mode, verifying that an issue is already implemented on the current default branch. Optionally close the issue as completed after a PASS. Use when a user asks whether a branch or merged change completes a GitHub issue, or needs an issue-visible verification comment.

Cost-benefit analysis. Produces economic NPV and financial NPV side by side, with BCR, optimism bias (with mitigation), Marginal Excess Tax Burden, real-terms rebasing, WELLBY / QALY / VPF wellbeing valuation, sensitivity, switching values, EANC for unequal-life options, validation gate, and a one-line headline verdict (socially worthwhile vs financially self-sustaining). Backed by the greenbook R package (HM Treasury Green Book primitives) when available, with graceful fallback. Supports HMT Green Book, EU Better Regulation, World Bank, ADB, and Victorian HVHR. Reads a longlist markdown file directly via --from.

Give a decisive, project-grounded point of view in the subject's own shape: a graded verdict on an external-adoption question, a holistic take on a document, or a position on a user-supplied approach set. Use for a solo POV, a mid-session second opinion, a named-peer cross-check, any request to consult other models or reconcile their opinions, an `oracle` panel, or a correction-cost-gated proactive cross-check offer. Not for findings review (use ce-doc-review), neutral explainers, or generating options (use ce-ideate or ce-brainstorm).

Turn a messy quarter into a GTM board update a director reads in two minutes. Leads with the number versus plan, surfaces the two or three things that actually matter, names the risks honestly instead of burying them, and ends with clear asks. Verdict first, short, no victory lap. Built for B2B GTM and revenue leaders, customizable to your metrics and your stack. Trigger on "write the board update", "GTM update for the board", "exec summary for the QBR", "what do I tell the board", "draft my leadership update", or any board or exec GTM write-up.

Turn "what's happening with this account?" into a structured read straight from your CRM. A real-activity audit across every source, a qualification-vs-stage gap check, a one-screen account summary, and a risk verdict on the deal. Built for any sales team, customizable to your CRM and your sales process. Trigger on "analyze this account", "what's happening with this deal", "is this opp healthy", "what's stuck in my pipeline", "deal autopsy on this closed-lost", "where am I missing qualification coverage", "prep me for this account", or any account, opp, or pipeline diagnostic.

Turn "is this account a real fit?" into a stacked verdict. A composite 0-100 fit score built from every signal you have, a breakdown by source, override flags for when a scoring tool is wrong, a channel classification, and a written rationale. Built for reps, marketers, and RevOps, customizable to your CRM and whatever scoring you use. Trigger on "is {account} a real fit?", "score this list against our profile", "find lookalikes to our best customers", "why is the score wrong on {account}?", "validate this prospect list", "what's our coverage in {segment}?", or any account or list qualification.

Turn a piece of analysis into the thing that ships it. Takes the output of a read (an account verdict, a usage story, a ranked list) and drafts the CRM update, the Slack post, the follow-up email, and the next touch, draft-first and fully logged. Built for any GTM team, customizable to your CRM, your channel tool, and your outreach stack. Trigger on "draft the CRM update for this", "post this to a channel", "write a follow-up to this person", "update the qualification fields on this account", "send this recommendation to a teammate", "draft an outreach sequence", or any write, send, or notify step at the end of a workflow.

Verify a code change end-to-end in the current worktree: figure out what changed, run the relevant tests, get the app running, drive a browser to exercise the affected areas, and report a verdict with screenshots. Generic across project types (Laravel/Herd, Node/bun, frontend, CLI, library). Use this skill whenever the user wants to verify/QA/smoke-test a change, check that a PR or branch's changes actually work, validate uncommitted work before pushing, or says "/flow", "flow this", "verify this change", "does this PR work", "check my changes", "test and click through this". Accepts an optional target (a PR number/URL, a branch/ref, or a worktree path); with no argument it verifies the current uncommitted/working changes.

Score an unbuilt business idea on desirability, viability, feasibility, distribution wedge, why-now, founder-market-fit, market size, alternatives, defensibility, capital intensity, and regulatory/ethical risk — and return a GO / ITERATE / KILL verdict with kill criteria and a next kill test. Load when the user asks to evaluate a business idea, score a startup idea, screen an idea, decide whether to pursue this venture, do an idea review, or says "is this a good business idea", "should I build this", "evaluate this startup", "screen this idea", "go/no-go on this idea", "kill or pursue". Sub-skill of `venture-exploration`. Calls `fermi` for sizing, `assumption-mapping` for hidden beliefs, optional `pre-mortem` / `adversarial-hat` for high-stakes ideas. Does NOT evaluate built products — for that use `reality-check`.