Alphagenome Single Variant Analysis
google-deepmind/science-skills
Analyzes genetic variant effects on gene expression (RNA-seq), chromatin accessibility (DNASE), histone marks (ChIP), and transcription factors using the AlphaGenome API.
Co-designs qPCR/RT-qPCR primers and hydrolysis (TaqMan) or molecular-beacon probes with primer3-py (PRIMERPICKINTERNALOLIGO, PRIMERINTERNAL tags), for assays whose deliverable is a quantitative…
$ npx skills add GPTomics/bioSkills --skill bio-primer-design-qpcr-primers -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install GPTomics/bioSkills bio-primer-design-qpcr-primers --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/GPTomics/bioSkills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/primer-design/qpcr-primers .claude/skills/bio-primer-design-qpcr-primers && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "bio-primer-design-qpcr-primers" agent skill from https://github.com/GPTomics/bioSkills/tree/main/primer-design/qpcr-primers into .claude/skills/bio-primer-design-qpcr-primers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bio-primer-design-qpcr-primers", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/GPTomics/bioSkills/tree/main/primer-design/qpcr-primersType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add GPTomics/bioSkills --skill bio-primer-design-qpcr-primers -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install GPTomics/bioSkills bio-primer-design-qpcr-primers --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GPTomics/bioSkills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/primer-design/qpcr-primers .agents/skills/bio-primer-design-qpcr-primers && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "bio-primer-design-qpcr-primers" agent skill from https://github.com/GPTomics/bioSkills/tree/main/primer-design/qpcr-primers into .agents/skills/bio-primer-design-qpcr-primers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bio-primer-design-qpcr-primers", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add GPTomics/bioSkills --skill bio-primer-design-qpcr-primers -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install GPTomics/bioSkills bio-primer-design-qpcr-primers --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GPTomics/bioSkills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/primer-design/qpcr-primers .cursor/skills/bio-primer-design-qpcr-primers && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "bio-primer-design-qpcr-primers" agent skill from https://github.com/GPTomics/bioSkills/tree/main/primer-design/qpcr-primers into .cursor/skills/bio-primer-design-qpcr-primers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bio-primer-design-qpcr-primers", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/GPTomics/bioSkills.git --path primer-design/qpcr-primers--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add GPTomics/bioSkills --skill bio-primer-design-qpcr-primers -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install GPTomics/bioSkills bio-primer-design-qpcr-primers --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GPTomics/bioSkills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/primer-design/qpcr-primers .gemini/skills/bio-primer-design-qpcr-primers && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "bio-primer-design-qpcr-primers" agent skill from https://github.com/GPTomics/bioSkills/tree/main/primer-design/qpcr-primers into .gemini/skills/bio-primer-design-qpcr-primers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bio-primer-design-qpcr-primers", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install GPTomics/bioSkills bio-primer-design-qpcr-primersInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add GPTomics/bioSkills --skill bio-primer-design-qpcr-primers -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/GPTomics/bioSkills.git skills-src && mkdir -p .github/skills && cp -r skills-src/primer-design/qpcr-primers .github/skills/bio-primer-design-qpcr-primers && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "bio-primer-design-qpcr-primers" agent skill from https://github.com/GPTomics/bioSkills/tree/main/primer-design/qpcr-primers into .github/skills/bio-primer-design-qpcr-primers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bio-primer-design-qpcr-primers", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add GPTomics/bioSkills --skill bio-primer-design-qpcr-primers -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install GPTomics/bioSkills bio-primer-design-qpcr-primers --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GPTomics/bioSkills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/primer-design/qpcr-primers .opencode/skills/bio-primer-design-qpcr-primers && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "bio-primer-design-qpcr-primers" agent skill from https://github.com/GPTomics/bioSkills/tree/main/primer-design/qpcr-primers into .opencode/skills/bio-primer-design-qpcr-primers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bio-primer-design-qpcr-primers", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
bio-primer-design-qpcr-primersCo-designs qPCR/RT-qPCR primers and hydrolysis (TaqMan) or molecular-beacon probes with primer3-py (PRIMERPICKINTERNALOLIGO, PRIMERINTERNAL tags), for assays whose deliverable is a quantitative…
Bio Primer Design Qpcr Primers is an agent skill from GPTomics/bioSkills. Co-designs qPCR/RT-qPCR primers and hydrolysis (TaqMan) or molecular-beacon probes with primer3-py (PRIMERPICKINTERNALOLIGO, PRIMERINTERNAL tags), for assays whose deliverable is a quantitative measurement device. Covers why amplification efficiency (90-110%, slope -3.6 to -3.1) and single-product specificity make the 2^-ddCq / Pfaffl math valid, why the short amplicon (70-150 bp), tight Tm, and zero-dimer requirement exist, the coupled probe rules (probe Tm 8-10 C above primers so it is bound when Taq's…
Its SKILL.md is about 4.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `examples/qpcr_design.py` and `usage-guide.md`).
It sits in Research & Science, covering Bioinformatics. The repository describes itself as: a set of SKILLS.md for doing bioinformatics with agents like claude code. The licence is MIT.
3 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit d91ed3d. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships script files (Python), which the agent can run.
Shell commands in SKILL.md call:
pipFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Bio Primer Design Qpcr Primers loads about 4.4k tokens when it runs. Until then it costs about 264 tokens; SKILL.md has 1,925 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from GPTomics/bioSkills at commit d91ed3d, republished under its MIT licence (© GPTomics). 1,925 words, ~4,375 tokens.
.claude/skills/bio-primer-design-qpcr-primers/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.Reference examples tested with: primer3-py 2.3+.
Before using code patterns, verify installed versions match. If versions differ:
pip show primer3-py then help(primer3.design_primers) to check signaturesIf code throws ImportError, AttributeError, or TypeError, introspect the installed package and adapt the example to match the actual API rather than retrying.
"Design qPCR primers (and a probe) for this target" -> Co-design a short, single-product, Tm-matched amplicon with an optional internal probe whose constraints are coupled to the primers -- because the assay's job is not to amplify but to MEASURE, and every qPCR-specific rule protects the efficiency the quantification math assumes.
primer3.design_primers(seq_args, global_args) with PRIMER_PICK_INTERNAL_OLIGO=1 and PRIMER_INTERNAL_* for the probe.Scope: co-designing qPCR/RT-qPCR primers and hydrolysis/beacon probes under coupled Tm/size/junction constraints. Genome-wide specificity / pseudogene checking -> primer-specificity. Intramolecular dimers/hairpins of the oligos and probe -> primer-validation. Standard (non-quantitative) PCR -> primer-basics.
(1+E)^-dCq (at ideal E=1, 2^-ddCq). That requires amplification efficiency E ~ 90-110% (standard-curve slope -3.6 to -3.1, R^2 > 0.99) AND a single product. The short amplicon (70-150 bp), tight Tm, and zero-dimer requirement all exist to protect E and specificity. 2^-ddCq is valid ONLY when the target and reference-gene efficiencies are matched and near 100% -- so design for matched ~100% E, or fall back to Pfaffl's efficiency-corrected model.PRIMER_INTERNAL_MUST_MATCH_FIVE_PRIME='HNNNN' (IUPAC H = not G) or a post-hoc filter. This is the hydrolysis (TaqMan) probe path; a molecular beacon needs engineered complementary stem arms (a deliberate hairpin) that primer3's internal-oligo picker does NOT design and would flag as a liability -- design the linear core here, add the stem afterward, and exclude that hairpin from validation.Efficiency from a standard curve: E = 10^(-1/slope) - 1; perfect doubling is slope -3.32 (E = 100%). Relative quantification with matched ~100% efficiency uses 2^-ddCq (Livak & Schmittgen 2001 Methods 25:402); with UNEQUAL efficiencies use the efficiency-corrected ratio E_target^dCq / E_ref^dCq (Pfaffl 2001 Nucleic Acids Res 29:e45). Report per MIQE (Bustin 2009 Clin Chem 55:611): efficiency, slope, R^2, Cq method, NTC and no-RT controls, and validated reference genes. The design objective is therefore "single short amplicon with slope near -3.32," not "two oligos that amplify."
| Tool / method | Citation | Mechanism / role | When |
|---|---|---|---|
| primer3-py internal oligo | Untergasser 2012 Nucleic Acids Res 40:e115 | PRIMER_PICK_INTERNAL_OLIGO=1 + PRIMER_INTERNAL_* co-designs the probe with the primers | TaqMan / hydrolysis-probe assays |
PRIMER_INTERNAL_MUST_MATCH_FIVE_PRIME | Untergasser 2012 Nucleic Acids Res 40:e115 | constrains the probe 5' end (use HNNNN to forbid 5'-G) | enforce the no-5'-G probe rule |
SEQUENCE_OVERLAP_JUNCTION_LIST | Untergasser 2012 Nucleic Acids Res 40:e115 | forces a primer/probe to straddle a splice junction | cDNA-specific expression assays |
| MIQE reporting | Bustin 2009 Clin Chem 55:611 | the minimum information / efficiency-from-standard-curve standard | every quantitative assay |
| geNorm / NormFinder | Vandesompele 2002 Genome Biol 3:RESEARCH0034; Andersen 2004 Cancer Res 64:5245 | rank reference-gene stability | choosing normalizers, validated per condition |
| In-silico PCR (genome) | (route OUT) | catches pseudogenes / gDNA off-targets | mandatory gDNA/specificity check -> primer-specificity |
| Scenario | Recommended | Why |
|---|---|---|
| Probe-based (multiplex-capable, second specificity check) | TaqMan: PRIMER_PICK_INTERNAL_OLIGO=1, probe Tm 8-10 C above primers, HNNNN 5' | the probe adds sequence specificity and enables multiplex |
| Single target, cheapest, no probe | SYBR (no internal oligo) + mandatory melt-curve QC | dye reports any dsDNA; melt curve is the specificity readout |
| Expression assay, avoid gDNA | exon-junction-spanning primers (SEQUENCE_OVERLAP_JUNCTION_LIST) | the junction does not exist contiguously in unspliced gDNA |
| Gene has a processed pseudogene | junction-spanning is NOT enough -> primer-specificity (search genome) + no-RT control | the pseudogene carries the junction |
| Single-exon gene (no junction) | DNase + no-RT control; no design-level gDNA exclusion | there is no intron/junction to exploit |
| AT-rich target / allele discrimination | MGB or LNA probe (shorter, higher effective Tm) | raises probe Tm where a standard probe cannot reach |
| Multiplex panel | spectrally distinct fluorophores, matched E, primer-limiting, all-pairs cross-dimer | competition and cross-dimers dominate; primer-limiting = drop the abundant target's primer concentration so it plateaus early and stops starving the rare target of shared reagents |
| Choosing normalizers | rank a candidate panel with geNorm/NormFinder, validate per condition | a single unvalidated reference gene is a classic error |
Default when uncertain: TaqMan primers+probe, amplicon 70-150 bp, primers Tm ~60 C (within 2 C), probe Tm ~68-70 C with HNNNN, exon-junction-spanning for expression, then route the pair to primer-specificity and run a standard curve.
Goal: Produce a short, Tm-matched amplicon with an internal probe whose Tm is 8-10 C above the primers and whose 5' base is not G.
Approach: Turn on internal-oligo picking, set the primer Tm window and a short product range, RAISE the PRIMER_INTERNAL_* Tm window 8-10 C above the primers (the defaults equal the primer Tm), and forbid a 5'-G probe with PRIMER_INTERNAL_MUST_MATCH_FIVE_PRIME='HNNNN'. For an expression assay add SEQUENCE_OVERLAP_JUNCTION_LIST.
import primer3
template = 'ATGC...' # cDNA (mark the junction position if expression-specific)
result = primer3.design_primers(
seq_args={'SEQUENCE_ID': 'assay1', 'SEQUENCE_TEMPLATE': template},
global_args={
'PRIMER_PICK_LEFT_PRIMER': 1, 'PRIMER_PICK_RIGHT_PRIMER': 1,
'PRIMER_PICK_INTERNAL_OLIGO': 1, # design the probe
'PRIMER_PRODUCT_SIZE_RANGE': [[70, 150]], # short amplicon for efficiency
'PRIMER_NUM_RETURN': 3,
'PRIMER_OPT_TM': 60.0, 'PRIMER_MIN_TM': 58.0, 'PRIMER_MAX_TM': 62.0,
'PRIMER_PAIR_MAX_DIFF_TM': 2.0,
'PRIMER_INTERNAL_OPT_TM': 70.0, 'PRIMER_INTERNAL_MIN_TM': 68.0, 'PRIMER_INTERNAL_MAX_TM': 72.0,
'PRIMER_INTERNAL_MUST_MATCH_FIVE_PRIME': 'HNNNN', # IUPAC H = A/C/T = not G at the probe 5' end
# 'SEQUENCE_OVERLAP_JUNCTION_LIST': [junction_pos], # add for cDNA-specific assays
})
for i in range(result['PRIMER_PAIR_NUM_RETURNED']):
probe = result[f'PRIMER_INTERNAL_{i}_SEQUENCE']
print(result[f'PRIMER_LEFT_{i}_SEQUENCE'], result[f'PRIMER_RIGHT_{i}_SEQUENCE'], probe,
'probe5=', probe[0], 'probeTm=', round(result[f'PRIMER_INTERNAL_{i}_TM'], 1),
'size=', result[f'PRIMER_PAIR_{i}_PRODUCT_SIZE'])For a cDNA-specific assay, place a primer or the probe across a splice junction with SEQUENCE_OVERLAP_JUNCTION_LIST = [pos] plus PRIMER_MIN_3_PRIME_OVERLAP_OF_JUNCTION (default 4) and PRIMER_MIN_5_PRIME_OVERLAP_OF_JUNCTION (default 7); the 3' overlap is the specificity-determining knob because a primer that only overlaps at its 5' end can still prime off gDNA from its 3' anchor. The internal-oligo equivalents (PRIMER_INTERNAL_MIN_3_PRIME_OVERLAP_OF_JUNCTION / _5_PRIME_) constrain the probe. The hard caveat: this does NOT protect against processed pseudogenes, which typically carry the junction in DNA -- so the assay still needs a genome specificity check (-> primer-specificity), DNase treatment, and a no-RT control. Intron-flanking (primers in different exons across a large intron) is the alternative, but fails across tiny introns.
Multiplex is the most failure-prone mode; assemble it in order: (1) design each assay independently (short amplicon, matched Tm, probe offset); (2) check ALL primer+probe oligos pairwise for cross-dimers -- for k assays that is O((2k primers + k probes)^2) checks (a 5-plex = 10 primers + 5 probes = 105 pairwise calls), weighting 3'-end involvement (-> primer-validation); (3) run in-silico PCR over the POOLED primer set so cross-pair amplicons (one assay's forward meeting another's reverse) are caught (-> primer-specificity); (4) assign spectrally distinct fluorophores -- the instrument's optical channels and spectral overlap CAP the plex (most platforms resolve ~4-6 dyes, with color compensation), so the channel count, not the chemistry, usually limits a high-plex; (5) match efficiencies on a multiplex standard curve and primer-limit the abundant targets so they do not starve the rare ones.
Trigger: Applying 2^-ddCq without a standard curve. Mechanism: the method assumes target and reference efficiencies are matched and ~100%; if not, fold-changes are systematically biased. Symptom: numbers that are not measurements; results that do not replicate across instruments. Fix: run a standard curve, report E/slope/R^2 (MIQE), and use Pfaffl if efficiencies differ.
Trigger: Leaving PRIMER_INTERNAL_* Tm at the default (equal to the primers). Mechanism: the probe is not bound when the polymerase extends through it, so the exonuclease never cleaves it. Symptom: weak or no TaqMan signal. Fix: raise the internal Tm window 8-10 C above the primer window.
Trigger: Not forbidding a 5' guanine. Mechanism: a 5'-G quenches the reporter even after cleavage. Symptom: low signal despite good amplification. Fix: PRIMER_INTERNAL_MUST_MATCH_FIVE_PRIME='HNNNN' or filter returned probes; prefer the C-rich strand.
Trigger: Trusting junction-spanning alone. Mechanism: processed pseudogenes carry the spliced junction in genomic DNA. Symptom: a positive no-RT control; a genomic amplicon at the cDNA size. Fix: genome specificity check (primer-specificity), DNase, and a no-RT control.
Trigger: Any extendable cross-dimer with SYBR detection. Mechanism: the dye reports the dimer, which competes with and can swamp a low-copy target. Symptom: a low-Tm shoulder in the melt curve; inflated NTC/low-copy signal. Fix: inspect the melt curve for a single sharp peak; validate dimers at reaction conditions (primer-validation).
Trigger: Normalizing to GAPDH/ACTB by habit. Mechanism: the reference may itself be regulated by the treatment. Symptom: apparent target changes that track a moving normalizer. Fix: rank a candidate panel with geNorm/NormFinder and validate stability in the actual experimental conditions.
| Threshold | Source | Rationale |
|---|---|---|
| Efficiency 90-110% (slope -3.6 to -3.1, ideal -3.32), R^2 > 0.99 | Bustin 2009 Clin Chem 55:611 | the acceptance band that keeps 2^-ddCq valid |
| Amplicon 70-150 bp | Bustin 2009 Clin Chem 55:611 | short products denature/re-prime fully each short cycle -> ~100% E |
| Primer Tm ~58-62 C, pair within 2 C | Koressaar & Remm 2007 Bioinformatics 23:1289 | one anneal-extend temperature; matched so neither lags |
| Probe Tm 8-10 C above primer Tm | -- | probe bound before/during extension so the exonuclease can cleave it |
| Probe: no 5'-G, prefer C-rich strand | -- | a 5'-G (and G-richness) quenches the reporter; the standard rule for 5'-reporter hydrolysis probes (reporter/quencher-chemistry dependent) |
| Standard curve: 5-6 points, 10-fold, triplicate | Bustin 2009 Clin Chem 55:611 | defines E, R^2, dynamic range, LOD |
| Reference genes: >=2 validated | Vandesompele 2002 Genome Biol 3:RESEARCH0034 | geometric mean of stable references beats one gene |
| Error / symptom | Cause | Solution |
|---|---|---|
| Weak/no TaqMan signal | probe Tm too low, or 5'-G | raise PRIMER_INTERNAL_* Tm 8-10 C; HNNNN; C-rich strand |
| No probe returned (0 pairs) | internal Tm window unreachable on this template | widen/lower internal Tm or product range; check with PRIMER_EXPLAIN_FLAG=1 |
| Positive no-RT control | gDNA / pseudogene amplification | junction-span + genome check (primer-specificity) + DNase |
| Poor efficiency (slope steep/shallow) | amplicon too long, dimers, off-target, or template inhibitors/degraded standard | shorten amplicon, fix dimers (primer-validation), check specificity, clean up template |
| Low-Tm melt peak (SYBR) | primer-dimer | redesign to remove 3'-end cross-dimers (primer-validation) |
| Fold-changes do not replicate | unmatched efficiency, unvalidated reference | match E or use Pfaffl; validate references with geNorm/NormFinder |
© GPTomics, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 2 other files in primer-design/qpcr-primers of GPTomics/bioSkills.
Open the folder on GitHubat commit d91ed3d
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in GPTomics/bioSkills, which our catalogue first saw on October 7, 2026.
Bio Primer Design Qpcr Primers next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Bio Primer Design Qpcr Primers this skillGPTomics/bioSkills | 1.2k | 1 repos | ~4.4k | Automated safety check: Pass | MIT | |
| Alphagenome Single Variant Analysisgoogle-deepmind/science-skills | 3.2k | 2 repos | ~3k | Automated safety check: Notes | Apache-2.0 | |
| 13C Metabolic Flux AnalysisK-Dense-AI/scientific-agent-skills | 48k | 1 repos | ~3.2k | Automated safety check: Pass | MIT | |
| Clinvar Databasegoogle-deepmind/science-skills | 3.2k | 2 repos | ~3.9k | Automated safety check: Notes | Apache-2.0 | |
| Metabolic Study Planneraiming-lab/AutoResearchClaw | 15k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Dbsnp Databasegoogle-deepmind/science-skills | 3.2k | 2 repos | ~3.4k | Automated safety check: Notes | Apache-2.0 |
google-deepmind/science-skills
Analyzes genetic variant effects on gene expression (RNA-seq), chromatin accessibility (DNASE), histone marks (ChIP), and transcription factors using the AlphaGenome API.
K-Dense-AI/scientific-agent-skills
Estimates reaction fluxes inside cells from steady-state carbon-13 labeling data with a bundled mfapy-based solver, and reports which fluxes the data pin down.
google-deepmind/science-skills
A skill your agent uses when needing clinical significance, pathogenicity classifications (e.g., Pathogenic, Benign, VUS), clinical evidence rationales, or finding "hard positive" benchmark controls…
aiming-lab/AutoResearchClaw
Turns a broad metabolic modelling topic into a concrete, paper-shaped plan with organism, model, perturbations, metrics and figures before any FBA code is written.
google-deepmind/science-skills
A skill your agent uses when you want to look up, map, and search for short genetic variants (SNPs, indels) in NCBI's dbSNP database.
aiming-lab/AutoResearchClaw
Runs a metabolic flux analysis from model loading to phenotype prediction and figures by handing work to four sub-agents in sequence.
GPTomics/bioSkills
Read, write, and convert multiple sequence alignment files using Biopython Bio.AlignIO.
GPTomics/bioSkills
Installs the bioSkills collection of 425 bioinformatics skills in one step, or only chosen categories, so sequencing, RNA-seq, single-cell and variant tasks get specialized help.
GPTomics/bioSkills
Write biological sequences to files (FASTA, FASTQ, GenBank, EMBL) using Biopython Bio.SeqIO.
GPTomics/bioSkills
Soft- or hard-clips PCR primer footprints from aligned amplicon BAMs so primer bases stop masquerading as confirmed reference sequence.
GPTomics/bioSkills
Filters BAM alignments by FLAG bits, mapping quality and regions with samtools view or pysam, with recipes for common keep and drop cases.
GPTomics/bioSkills
Create and use BAI/CSI indices for BAM/CRAM files using samtools and pysam.
Categories
Co-designs qPCR/RT-qPCR primers and hydrolysis (TaqMan) or molecular-beacon probes with primer3-py (PRIMERPICKINTERNALOLIGO, PRIMERINTERNAL tags), for assays whose deliverable is a quantitative…. Bio Primer Design Qpcr Primers is an agent skill from GPTomics/bioSkills. Co-designs qPCR/RT-qPCR primers and hydrolysis (TaqMan) or molecular-beacon probes with primer3-py (PRIMERPICKINTERNALOLIGO, PRIMERINTERNAL tags), for assays whose deliverable is a quantitative measurement device.
Bio Primer Design Qpcr Primers fits situations like: designing TaqMan/SYBR assays; exon-spanning primers; matched-efficiency multiplex panels.
Run `npx skills add GPTomics/bioSkills --skill bio-primer-design-qpcr-primers -a claude-code`. Or copy the skill folder (primer-design/qpcr-primers in GPTomics/bioSkills) into .claude/skills/bio-primer-design-qpcr-primers in your project. Claude Code loads it when a task matches its description.
Run `npx skills add GPTomics/bioSkills --skill bio-primer-design-qpcr-primers -a codex`. Or copy the skill folder (primer-design/qpcr-primers in GPTomics/bioSkills) into .agents/skills/bio-primer-design-qpcr-primers in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add GPTomics/bioSkills --skill bio-primer-design-qpcr-primers -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bio-primer-design-qpcr-primers, .gemini/skills/bio-primer-design-qpcr-primers, .github/skills/bio-primer-design-qpcr-primers and .opencode/skills/bio-primer-design-qpcr-primers in your project.
Going by SKILL.md and its folder, Bio Primer Design Qpcr Primers needs Python for the scripts in its folder and the command-line tools its instructions call (pip). Our summary lists: Python 3.
SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Bio Primer Design Qpcr Primers is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.4k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Bio Primer Design Qpcr Primers: Alphagenome Single Variant Analysis (google-deepmind/science-skills, 3.2k stars), 13C Metabolic Flux Analysis (K-Dense-AI/scientific-agent-skills, 48k stars), Clinvar Database (google-deepmind/science-skills, 3.2k stars) and Metabolic Study Planner (aiming-lab/AutoResearchClaw, 15k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
GPTomics (a GitHub organization) maintains it in GPTomics/bioSkills, which has 1,218 GitHub stars. The repository holds 559 skills in this directory. The repository was last updated on August 15, 2026.
Source: GPTomics/bioSkills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.