claude-skills-public

Use when the user wants an external second opinion on a plan from the strongest available ChatGPT model via codex, or says "send the plan to GPT", "get ChatGPT to review my plan", "codex review of the plan", "external review of the plan", "second opinion on the plan from GPT", "/review-plan-codex", or wants a cross-model critique round run as a standalone step on any plan (not just empirical Bob plans). Codex runs the convergence loops; Claude supplies the independent critique; each model's findings are audited by the other.

Use when the user wants automated iterative plan review with convergence detection (multiple review passes without manual approval between iterations) OR wants to audit a plan's adversarial-agent contract (check that Adversary, Verifier, audit-readiness, or determinism agents are wired always-on, not conditionally gated). Triggers on "auto-review the plan", "iterate on plan review", "review my plan thoroughly", "keep reviewing until it's tight", "/review-plan-auto", "check whether my adversarial agents will actually fire", "audit how the plan wires the Adversary", "stress-test the safety machinery in my plan", "is this plan safe for an overnight run", "verify the plan's adversarial-agent contract", "make sure the Adversary in this plan is not just a deterministic check", or any case where the user would otherwise run `/review-plan` repeatedly.

Use when the user wants to verify whether the citations in a LaTeX or markdown manuscript actually support the claims they're attached to, or wants a citation audit against their .bib. Triggers on "check my citations", "verify references", "citation audit", "do my citations actually support what I wrote", "audit bibliography against claims", or "/lit-review-verify". Not for producing a literature review or finding related papers (use /lit-review), and not for cleaning bib metadata (use /clean-bib).

Use when the user wants to stress-test, critique, or pressure-check a plan document — catch blind spots, missing steps, and unstated assumptions. Triggers on "review my plan", "stress-test the plan", "critique this plan", "what am I missing", "expert review of the plan", or "/review-plan". Runs structured expert critique, best-practice research, and optional fresh-context subagent review.

Use when the user says "restart", "wrap up", "snapshot before clearing", "pickup notes", "session recap", "session log", or wants to clear context and resume current work in a fresh conversation. Writes a structured restart.md to the project root, led by a Created / Sent / Waiting / Next recap and keeping goal, decisions, open items, files touched, and verification commands, appends that recap to a running SESSION_LOG.md, then instructs the user to type /clear.

Use when the user asks to audit, review, or check Stata dofiles for macro definitions, undefined paths, internal consistency, or unused variables. Triggers on "audit code", "audit dofiles", "check my Stata code", "audit my Stata project", or "/audit-code".

Audit academic papers (economics/finance) for typos, grammar, style, prose quality, apparatus, structural coherence, holistic craft, and AI-pattern detection. Default uses track-changes markup in Modules 2-7; use --clean for clean text throughout. Module 6 (Voice & Craft) is offered after Module 5 completes; Module 7 (AI Pattern Detection) is offered after Module 6. Use when user asks to audit or review a paper.

Format an informal request into a structured prompt. Output only — do not execute. Use when user invokes /prompt-only with a task description or content block.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Use when the user wants pre-submission feedback on their own paper via simulated peer review — journal-calibrated referee reports with an Editor + 2 referee structure. Triggers on "simulate referee", "simulate peer review", "what would a referee say", "pre-submission feedback", "fake referee report on my paper", or "/simulate-referee". Surfaces weaknesses before actual referees do.

Use ONLY when the user types the slash command "/memory". On first run in a project, bootstraps PROJECT_MEMORY.md at the project root with research question, decisions, data sources, architecture, workstreams, open questions, and lessons learned. On subsequent runs, applies an update sourced from the current session: volatile sections auto-apply, durable sections show a unified diff and require y/N confirmation. Always archives the prior version. Do NOT trigger on natural language; this skill is slash-invoked only.

Compile LaTeX documents using the xelatex → bibtex → xelatex → xelatex pipeline. Use when user asks to compile, build, or typeset a LaTeX file.

Sync local Overleaf project via Git. Use when the user says "overleaf pull", "overleaf push", "pull from overleaf", "push to overleaf", "sync overleaf", or wants to sync a local Overleaf clone.

MANDATORY for any task involving reading, analyzing, summarizing, reviewing, or extracting content from a PDF file. Triggers on any PDF input regardless of size. This skill replaces the default PDF reading behavior with a reliable chunked extraction method.

Format an informal, conversational request into a structured prompt, then execute it. Use when user invokes /prompt with a task description.

Systematically set up, solve, and verify an economic model with step-by-step derivations and cross-model mathematical checking. Use when user wants to formalize an economic idea into a model, solve a model, derive equilibrium conditions, check derivations, or verify mathematical results. Also use when user says "solve", "derive", "set up the model", "formalize", "verify the math", "check derivation", "model setup".