Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Jacs Methods

ASecurity

Use when checking synthesis and characterization rigor for a Journal of the American Chemical Society (JACS) manuscript — purity, NMR/HRMS/IR/UV-vis, elemental analysis or HPLC, single-crystal X-ray/CCDC, and catalysis controls/mechanism/kinetics. Audits experimental rigor — it does not write narrative or polish prose.

1,052 stars
0 votes
0 copies
0 views
Added 6/5/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 6/5/2026

Install to Claude Code

$npx -y skills add brycewang-stanford/Awesome-Journal-Skills --skill jacs-methods --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Jacs Methods?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Jacs Methods
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/brycewang-stanford-jacs-methods/badge)](https://www.skillsdirectory.com/skills/brycewang-stanford-jacs-methods)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: jacs-methods
description: Use when checking synthesis and characterization rigor for a Journal of the American Chemical Society (JACS) manuscript — purity, NMR/HRMS/IR/UV-vis, elemental analysis or HPLC, single-crystal X-ray/CCDC, and catalysis controls/mechanism/kinetics. Audits experimental rigor — it does not write narrative or polish prose.
---

# Synthesis and Characterization Rigor (jacs-methods)

## When to trigger

- New compounds are reported and you must confirm full characterization
- A reviewer could ask "is this compound pure?" or "where is the X-ray?"
- A mechanism is claimed but only proposed, not tested
- Catalysis scope/selectivity is reported and controls are unclear

## Characterization rigor by claim type

JACS requires that **claims are fully supported by characterization data and
appropriate controls**. Match the data package to what you assert.

### Every new, isolable compound

- [ ] **¹H NMR** — solvent, field; δ (ppm), multiplicity, J (Hz), integration
- [ ] **¹³C{¹H} NMR** — all resolvable carbons (note coincident peaks)
- [ ] Heteronuclear NMR as relevant: **¹⁹F**, **³¹P**, **¹¹B**, etc.; 2D for assignment
- [ ] **HRMS** — ionization mode, calcd vs found m/z for the assigned formula
- [ ] **IR** — diagnostic bands (C=O, N–H, C≡N, M–CO, etc.) when structurally informative
- [ ] **Purity evidence** — at least one of: CHN(S) elemental analysis (calcd vs found, typically within accepted tolerance), or HPLC/GC purity, plus clean NMR
- [ ] Melting point / optical rotation / UV-vis as appropriate to compound class

### Stereochemistry / chirality

- [ ] **ee** by chiral HPLC/GC/SFC (column, eluent, flow, detector; report racemate trace)
- [ ] **dr** by NMR or HPLC; specify how measured
- [ ] Absolute configuration assigned (X-ray, VCD, comparison to known, or derivatization) — state the method

### Solid-state structure

- [ ] **Single-crystal X-ray** for structurally pivotal claims; deposit CIF with **CCDC** and cite the number
- [ ] Crystal/refinement table (formula, space group, R1/wR2, GooF, completeness)
- [ ] **checkCIF/PLATON** run; A/B-level alerts resolved or justified
- [ ] PXRD for bulk-phase identity of solids/materials

### Catalysis

- [ ] **Scope table** — representative, honest substrate range (not only easy cases); note failures
- [ ] **Control experiments** — no-catalyst, no-ligand, no-additive, radical traps/clocks as relevant
- [ ] **Mechanism** — evidence-based: kinetics (orders, rate law), KIE, labeling, intermediates (isolation/spectroscopy), Hammett, ee–ee(cat) correlation
- [ ] Catalyst loading, TON/TOF, and reproducibility (replicate runs) reported
- [ ] Metal/ligand source, purity, and any trace-metal control where relevant

### Materials / physical

- [ ] Composition and phase: PXRD, EDX/XPS, ICP, TGA, BET as appropriate
- [ ] Morphology with **scale bars** and representative-vs-statistical imaging (SEM/TEM/AFM)
- [ ] Property measurement with method, conditions, and error/replication
- [ ] Spectroscopy (UV-vis/PL/Raman/EPR/electrochemistry) tied to the claimed property

### Computation (if used to support mechanism/structure)

- [ ] Functional, basis set/pseudopotentials, solvation model, software + version
- [ ] Stationary points characterized (frequencies; TS has one imaginary mode)
- [ ] Optimized coordinates (xyz) deposited in SI; energies referenced consistently

## Reproducibility test

Could an independent chemist reproduce each yield, ee, and spectrum from the
written procedure alone? If not, the procedure is incomplete — fix before figures.

## Anti-patterns

- New compound reported with no purity criterion (no EA, no HPLC, no clean ¹³C)
- "Pure by NMR" as the only purity statement for a key compound
- Mechanism drawn as a cycle with no kinetic/labeling/control support
- Crystal structure shown but CIF not deposited / no CCDC number
- Scope table that hides failed substrates; idealized yields not reproducible
- HRMS reported without ionization mode or calcd/found pair

## Output format

```
【Compounds】N new; full characterization complete for [ ] / missing for [...]
【Purity basis】EA / HPLC / clean NMR — per compound
【Stereochem】ee/dr method + absolute config method (if chiral)
【X-ray】CCDC # [...]; checkCIF clean? Y/N
【Mechanism】claimed = [...]; evidence = [kinetics/KIE/labeling/controls]
【Reproducible from text?】Y/N — gaps: [...]
【Next】jacs-figures → jacs-supplementary
```

## Related resources

- [`../../resources/external_tools.md`](../../resources/external_tools.md) — instruments, CCDC/PDB deposition, crystallography and computational software

Attribution

brycewang-stanfordbrycewang-stanford
View sourceMore from brycewang-stanford →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →