Skip to main content
skill CX Codex

tooluniverse-primer-design — Claude Code skill: what it does

tooluniverse-primer-design designs PCR and qPCR primers, computes Tm and Ta, and screens oligonucleotides for hairpins and dimers.

Apache-2.0 131 installs ★ 1,798 updated 2026-10-24

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add mims-harvard/ToolUniverse --skill tooluniverse-primer-design -a claude-code
Open on GitHub

What tooluniverse-primer-design does

The skill runs primer design via tu run DNA_primer_design using SantaLucia nearest-neighbor thermodynamics. It outputs forward and reverse sequences, lengths, GC percentages, coordinates, and expected product sizes. For reaction setup, tu run NEB_Tm_calculate provides annealing temperatures tuned to specific enzymes like Q5, while IDT_analyze_oligo and scripts/primer_qc.py detect hairpins and primer-dimer formation.

Boundary constraints are rigid: the target span must fit strictly within product_size_min and product_size_max, leaving sufficient flanking space on both sides. The tool does not perform genome-wide off-target searches or SNP masking, so running BLAST remains necessary before ordering oligos.

What it helps with

  • design forward and reverse primers for a target DNA region
  • calculate annealing temperature for Q5 polymerase
  • screen oligo sequences for hairpins and self-dimers
  • validate GC clamp and 3-prime complementarity in primer pairs

Example prompts for the agent

  • Design primers for sequence ATGGCG...AACGTG spanning target region 40 to 125
  • Calculate annealing temperature Ta for Q5 polymerase with primer CTACCTGAAGAACCTGAG
  • Run primer_qc.py to check my forward and reverse primers for secondary structures

How to install tooluniverse-primer-design

1Skills CLI (Vercel)

npx skills add mims-harvard/ToolUniverse --skill tooluniverse-primer-design -a claude-code

2Manually: put the files in place

~/.claude/skills/tooluniverse-primer-design/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/tooluniverse-primer-design/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about tooluniverse-primer-design

How to install tooluniverse-primer-design in Claude Code?

Run npx skills add mims-harvard/ToolUniverse --skill tooluniverse-primer-design -a claude-code. The file will be placed in ~/.claude/skills/tooluniverse-primer-design/SKILL.md.

What does tooluniverse-primer-design do?

It calculates PCR and qPCR primer pairs, estimates melting temperatures, and inspects sequences for structural flaws.

Does this tool screen for off-target binding across the genome?

No, it evaluates thermodynamic parameters and secondary structures only, requiring a separate check with Primer-BLAST for genomic specificity.

Source text

SKILL.md · Apache-2.0
---
name: tooluniverse-primer-design
description: PCR / qPCR primer and oligo design — design forward/reverse primers for a target region (SantaLucia nearest-neighbor thermodynamics), compute melting temperature (Tm) and annealing temperature (Ta), check GC content, and screen an oligo for hairpins and primer-dimers. Use when you need primers for a sequence, want to QC an existing primer pair, or need the Tm of an oligo. Covers the primer-design rules (Tm matching, GC clamp, 3'-end, length) and the tools' constraint quirks.
disable-model-invocation: true
---

# PCR / qPCR Primer & Oligo Design

Design primers for a target DNA region, get their Tm/Ta, and QC them for the secondary-structure problems that make a PCR fail.

## When to use this

- Design a forward/reverse primer pair to amplify a region of a sequence.
- Compute the Tm / annealing temperature of a primer.
- QC an existing primer pair (GC clamp, 3'-end, hairpins, self/cross dimers, Tm match).

## Step 1 — Design a primer pair

```bash
tu run DNA_primer_design '{"operation":"primer_design",
  "sequence":"ATGGCG...AACGTG",        # full template; must be >= target_end + flanking primer room
  "target_start":40, "target_end":125,
  "tm_target":60, "product_size_min":80, "product_size_max":140}'
```

Returns `forward_primer` / `reverse_primer` (sequence, tm, gc_content, length, position) and `product_size`. (`target_end` is clamped to the sequence length, so a too-short template silently shrinks the target — see the constraint quirk below.)

> **Constraint quirk — read this or it will error.** `target_start..target_end` is the region the **amplicon must cover**, and the design only succeeds when that span fits inside the product-size window AND good-Tm primers can be placed flanking it. So you need roughly: `product_size_min ≤ (target span) ≤ product ≤ product_size_max`, with enough flanking sequence on both sides. Common errors and the fix:
> - *"Target region (N bp) is smaller than product_size_min"* → your target is narrower than `product_size_min`; lower `product_size_min` or widen the target.
> - *"product does not cover the target / does not span"* → the target is too wide for `product_size_max`, or runs too close to a sequence end; widen `product_size_max` or give more flanking sequence.

## Step 2 — Get Tm / annealing temperature for specific primers

```bash
tu run NEB_Tm_calculate '{"primer_sequence":"CTACCTGAAGAACCTGAG",
  "primer_sequence_2":"CTTGATGTCCTCCAGCAT",
  "polymerase":"Q5", "primer_concentration":500, "monovalent_salt_mm":50}'
```

NEB returns Tm for each primer and a recommended **annealing temperature (Ta)** for the chosen polymerase. `IDT_analyze_oligo` (sequence, salt/Mg/dNTP/oligo concentrations) adds GC%, molecular weight, and **hairpin / self-dimer** screening. `DNA_calculate_gc_content` is a quick GC check.

> **Tm depends on method + conditions.** SantaLucia NN (the design tool), NEB, and IDT use different parameter sets, and Tm shifts with monovalent salt, Mg²⁺, and primer/dNTP concentration. Pick **one** calculator + condition set and use it for the whole experiment; don't compare a SantaLucia Tm to an IDT Tm. Always state the conditions.

## Step 3 — Primer design rules (what "good" looks like)

| Property | Target | Why |
|---|---|---|
| **Length** | 18–24 nt | long enough for specificity, short enough for efficient annealing |
| **Tm** | 58–62 °C | works with standard cycling; keep the **pair within ~2–3 °C** of each other |
| **ΔTm (forward vs reverse)** | < 3 °C (≤5 absolute max) | mismatched Tm → one primer anneals poorly |
| **GC content** | 40–60 % | balanced stability |
| **GC clamp** | 1–2 G/C in the last 3 nt of the 3′ end | stabilizes 3′ priming; >3 G/C risks mispriming |
| **3′ end** | avoid 3′ complementarity within a pair and within a primer | prevents primer-dimers |
| **Runs / repeats** | avoid ≥4 identical bases in a row and di-nucleotide repeats | reduce slippage / mispriming |
| **Annealing temp (Ta)** | ~ Tm − 3 to −5 °C (use the polymerase's calculator) | specificity vs yield |
| **Amplicon (qPCR)** | 70–150 bp | efficient amplification |

`scripts/primer_qc.py` checks a primer pair against these rules (GC clamp, 3′ self/cross-complementarity, runs, GC%, length, Wallace/NN Tm, Tm match) and flags problems — use it to QC primers from any source.

## Step 4 — Specificity (the tools do NOT do this)

Tm and structure are necessary but **not sufficient**. A primer can be thermodynamically perfect and still amplify the wrong locus. These tools do **not** check genome specificity — always BLAST each primer (or use Primer-BLAST) against the target genome and confirm a single intended product before ordering. State this in any recommendation.

## Step 5 — Common gotchas

- **Forgetting specificity** (Step 4) — the #1 cause of a "well-designed" primer failing.
- **Mismatched pair Tm** — design tries to match, but a hand-picked pair often isn't; check ΔTm.
- **3′ primer-dimers** — 3′ complementarity between forward and reverse is the classic dimer; `IDT_analyze_oligo` / the QC script flag it.
- **Tm method/condition mixing** (Step 2).
- **Secondary structure in the template** (GC-rich/hairpin regions) can block priming even with good primers — consider additives or moving the target.

## Honest limitations

- Thermodynamic Tm/structure prediction ≠ empirical performance; validate by gradient PCR.
- No genome-specificity check (Step 4) and no SNP-masking — handle those separately.

## Related skills
- `tooluniverse-sequence-analysis` — upstream sequence handling (FASTQ, alignment, coverage).
- `tooluniverse-enzyme-kinetics` / `tooluniverse-dose-response` — other quantitative assay analyses.

© mims-harvard · Apache-2.0 · mims-harvard/ToolUniverse

Similar skills

All skills for Science and research →

From the same set136

The whole set →
tooluniverse-pharmacokinetics tooluniverse-pharmacokinetics calculates pharmacokinetic parameters from measured drug concentrations over time. Use it to analyze a dose profile or estimate absolute bioavailability from IV and oral data. CX Codex +1 140installs tooluniverse-protein-sae-variant-interpretation tooluniverse-protein-sae-variant-interpretation interprets protein missense variants using ESMC-6B Sparse Autoencoder features to reveal lost or gained functional biological properties. CX Codex +1 140installs tooluniverse-residue-functional-mechanism-interpretation The tooluniverse-residue-functional-mechanism-interpretation skill for Claude Code explains the significance of protein residues using structural context, UniProt annotations, and optional DMS or SAE evidence. CX Codex +1 140installs tooluniverse-mendelian-randomization The tooluniverse-mendelian-randomization skill tests whether one factor causally drives another (e.g., cholesterol → heart disease) using genetic variants as instrumental variables. CX Codex +1 137installs tooluniverse-diagnostic-test-evaluation tooluniverse-diagnostic-test-evaluation evaluates diagnostic test and biomarker accuracy from 2×2 tables or continuous scores. Computes sensitivity, specificity, ROC AUC, and Bayesian post-test probability. CX Codex +1 129installs tooluniverse-dose-response tooluniverse-dose-response fits a 4PL curve to concentration-response measurements and estimates IC50 or EC50. Use it to compare compound potency or assess how well a curve fits. CX Codex +1 128installs tooluniverse-enzyme-kinetics tooluniverse-enzyme-kinetics fits Michaelis-Menten enzyme kinetics from substrate-velocity experimental points and identifies inhibition modes. CX Codex +1 128installs tooluniverse-drug-synergy tooluniverse-drug-synergy quantifies whether two drugs act synergistically, additively, or antagonistically based on measured single-agent and combination effects. CX Codex +1 127installs

Project sponsors

Companies that keep this analytics open