Hypothesis Generation
spacering-net/codeg
Structured hypothesis formulation from observations. An agent skill from spacering-net/codeg.
Methylation cycle analysis — enzymatic activity profiles, Net Methylation Capacity, BH4 axis estimates, compound heterozygosity detection from SNP genotype data.
$ npx skills add ClawBio/ClawBio --skill claw-methylation-cycle -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ClawBio/ClawBio claw-methylation-cycle --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/ClawBio/ClawBio.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/claw-methylation-cycle .claude/skills/claw-methylation-cycle && 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 "claw-methylation-cycle" agent skill from https://github.com/ClawBio/ClawBio/tree/main/skills/claw-methylation-cycle into .claude/skills/claw-methylation-cycle/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claw-methylation-cycle", 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/ClawBio/ClawBio/tree/main/skills/claw-methylation-cycleType 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 ClawBio/ClawBio --skill claw-methylation-cycle -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ClawBio/ClawBio claw-methylation-cycle --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ClawBio/ClawBio.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/claw-methylation-cycle .agents/skills/claw-methylation-cycle && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "claw-methylation-cycle" agent skill from https://github.com/ClawBio/ClawBio/tree/main/skills/claw-methylation-cycle into .agents/skills/claw-methylation-cycle/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claw-methylation-cycle", 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 ClawBio/ClawBio --skill claw-methylation-cycle -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ClawBio/ClawBio claw-methylation-cycle --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ClawBio/ClawBio.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/claw-methylation-cycle .cursor/skills/claw-methylation-cycle && 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 "claw-methylation-cycle" agent skill from https://github.com/ClawBio/ClawBio/tree/main/skills/claw-methylation-cycle into .cursor/skills/claw-methylation-cycle/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claw-methylation-cycle", 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/ClawBio/ClawBio.git --path skills/claw-methylation-cycle--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 ClawBio/ClawBio --skill claw-methylation-cycle -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ClawBio/ClawBio claw-methylation-cycle --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ClawBio/ClawBio.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/claw-methylation-cycle .gemini/skills/claw-methylation-cycle && 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 "claw-methylation-cycle" agent skill from https://github.com/ClawBio/ClawBio/tree/main/skills/claw-methylation-cycle into .gemini/skills/claw-methylation-cycle/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claw-methylation-cycle", 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 ClawBio/ClawBio claw-methylation-cycleInstalls 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 ClawBio/ClawBio --skill claw-methylation-cycle -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ClawBio/ClawBio.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/claw-methylation-cycle .github/skills/claw-methylation-cycle && 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 "claw-methylation-cycle" agent skill from https://github.com/ClawBio/ClawBio/tree/main/skills/claw-methylation-cycle into .github/skills/claw-methylation-cycle/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claw-methylation-cycle", 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 ClawBio/ClawBio --skill claw-methylation-cycle -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ClawBio/ClawBio claw-methylation-cycle --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ClawBio/ClawBio.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/claw-methylation-cycle .opencode/skills/claw-methylation-cycle && 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 "claw-methylation-cycle" agent skill from https://github.com/ClawBio/ClawBio/tree/main/skills/claw-methylation-cycle into .opencode/skills/claw-methylation-cycle/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "claw-methylation-cycle", 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.
claw-methylation-cycleMethylation cycle analysis — enzymatic activity profiles, Net Methylation Capacity, BH4 axis estimates, compound heterozygosity detection from SNP genotype data.
Claw Methylation Cycle is an agent skill from ClawBio/ClawBio. Methylation cycle analysis — enzymatic activity profiles, Net Methylation Capacity, BH4 axis estimates, compound heterozygosity detection from SNP genotype data.
Its SKILL.md is about 4.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `methylation_cycle.py` and `tests/test_methylation_cycle.py`).
It sits in Research & Science. The repository describes itself as: 🦖 ClawBio - The first bioinformatics-native AI agent skill library. Local-first. Reproducible. Open. Free. The licence is MIT.
8 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit dece754. 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:
pythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
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.
Claw Methylation Cycle loads about 4.3k tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 1,656 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 ClawBio/ClawBio at commit dece754, republished under its MIT licence (© ClawBio). 1,656 words, ~4,293 tokens.
.claude/skills/claw-methylation-cycle/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.Methylation cycle analysis skill for ClawBio. Produces enzymatic activity profiles, Net Methylation Capacity (NMC), BH4 axis estimates, compound heterozygosity detection, and clinician-review genotype findings from raw SNP genotype data.
Fire this skill when:
methylation, MTHFR, BH4, folate cycle,
metilación, ciclo de metilación, homocysteine, 5-MTHF,
methylcobalamin, neurotransmitter synthesis, dopamine upstream.Do NOT fire this skill when:
Receive input — Accept either a raw genotype file path or a pre-parsed
snp_dict. If a file is provided, call parse_genotype_file() to extract
the rsID → genotype mapping.
Panel coverage check — Compare detected rsIDs against the 9-gene
methylation panel. Log missing SNPs. For any SNP absent from the input,
mark the corresponding gene as not_assessed — do NOT silently assume
normal activity (Safety Rule 6).
Enzymatic activity scoring — For each gene, map the diplotype to an estimated activity percentage. Heterozygous risk variants reduce activity by their assigned weight; homozygous variants apply the full reduction.
Compound heterozygosity detection — Check MTHFR C677T (rs1801133) and
A1298C (rs1801131) simultaneously. If both are heterozygous, set
compound_heterozygosity = True and apply the combined activity reduction
(~15% of normal — more severe than either variant alone).
Net Methylation Capacity (NMC) — Compute the weighted average of all
enzyme activities. Clamp to [0, 100]. Expose coverage_pct and
snps_missing; flag NMC as partial if key SNPs are absent.
BH4 axis capacity — Derive BH4 from MTHFR activity and MTRR modifier. Report clinical implications for dopamine and serotonin synthesis in neurodevelopmental presentations.
Prioritised recommendations — Generate PRIORITY 1 / 2 / 3 recommendations based on active findings. Lead with highest clinical impact (compound het MTHFR or severely reduced BH4).
Output — Write report.md (human-readable) and result.json
(structured, for downstream integration).
╔══════════════════════════════════════════════════════════════╗
║ ClawBio · Methylation Cycle Analysis Report ║
║ Author: Samuel Carmona Aguirre · RUO — Not a medical device ║
╚══════════════════════════════════════════════════════════════╝
Executive Summary
─────────────────
Net Methylation Capacity : 53 / 100 🔴 Reduced
BH4 Axis Capacity : 31 / 100 🔴 Reduced
MTHFR Compound Het. : YES ⚠️ (C677T + A1298C)
Dopamine Synthesis : Severely Reduced
Serotonin Synthesis : Severely Reduced
Enzymatic Activity Profile
──────────────────────────
Gene Activity Status Key Variants
MTHFR 15% 🔴 Severely reduced C677T, A1298C
MTRR 60% 🟡 Moderately reduced A66G
MTR 100% 🟢 Normal –
CBS 100% 🟢 Normal –
BHMT 40% 🔴 Moderately reduced R239Q
SHMT1 80% 🟢 Mildly reduced C1420T
COMT 55% 🟡 Moderately reduced Val158Met
AHCY 100% 🟢 Normal –
Clinical Recommendations — FOR CLINICIAN REVIEW ONLY
──────────────────────────────────────────────────────
⚠️ The following is genotype-based information for qualified clinician use.
Do not self-administer. All nutrients listed are reported in the peer-reviewed
literature for the pathways indicated; dosing and indication require
individualised clinical assessment.
Genotype findings:
• 5-MTHF (methylfolate) preferred over synthetic folic acid (MTHFR C677T/A1298C).
Ref: Lamers Y et al. (2004) Am J Clin Nutr 80(5):1234-41.
• MTHFR compound het: methylcobalamin co-administration reported in literature.
Ref: Ledford AW et al. (2021) Nutrients 13(3):768.
• BH4 capacity at 31%: riboflavin (B2) reported as MTHFR cofactor supporting BH4
regeneration. Ref: McNulty H et al. (2017) Am J Clin Nutr 106(1):128-36.
• MTRR A66G: methylcobalamin preferred over cyanocobalamin per functional studies.
Ref: Olteanu H et al. (2002) Biochemistry 41(45):13378-85.
• BHMT R239Q: betaine and choline-rich foods reported as alternative methyl donors.
Ref: Slow S et al. (2004) Clin Chim Acta 340(1-2):57-67.
Some literature reports an association between BH4 deficiency and
ADHD/depression/anxiety phenotypes. This genotype indicates reduced BH4
production capacity. A clinician should contextualise this finding with
the patient's clinical history.
Where clinically relevant, a clinician may evaluate whether neurodevelopmental
symptoms correlate with BH4 capacity for potential non-pharmacological support.Missing SNPs must never be silently normalised. The current
implementation (line 471) defaults to assuming normal activity for SNPs
absent from the input. This produces an artificially high NMC. When key
SNPs are missing, always expose coverage_pct and snps_missing so
downstream consumers know the score is partial.
Compound heterozygosity is synergistic, not additive. C677T and A1298C
affect different MTHFR domains. Their combined effect (~15% activity) is
greater than either variant alone. Do not compute as
activity(677) × activity(1298).
BH4 capacity is an estimate, not a measured value. The BH4 score is derived from MTHFR activity and literature-based weights. It does not account for DHFR variation or dietary cofactor availability. Always include the RUO disclaimer.
COMT Val158Met has a dual role. rs4680 appears in both methylation (SAM consumption) and dopamine/catecholamine panels. Always note this — do not report it in isolation.
DTC array coverage varies by platform. ADNTRO covers all 9 panel SNPs
for most European-ancestry samples. 23andMe v3 and Ancestry v1 may not
include rs1801394 (MTRR) or rs3733890 (BHMT). Always check snps_missing.
This skill does not cover pharmacogenomics. SLCO1B1, CYP enzymes, and statin/warfarin risk belong to PharmGx Reporter, not this skill.
| Gene | rsID | Variant | Allele Assessed | Effect Direction |
|---|---|---|---|---|
| MTHFR | rs1801133 | C677T | T (risk) | Decreased MTHFR activity |
| MTHFR | rs1801131 | A1298C | C (risk) | Decreased MTHFR activity |
| MTRR | rs1801394 | A66G | G (risk) | Decreased MTRR activity |
| MTR | rs1805087 | A2756G | G (risk) | Decreased MTR activity |
| CBS | rs234706 | C699T | T (risk) | Increased CBS activity |
| BHMT | rs3733890 | R239Q | A (risk) | Decreased BHMT activity |
| SHMT1 | rs1979277 | C1420T | T (risk) | Decreased SHMT1 activity |
| COMT | rs4680 | Val158Met | A/Met (risk) | Decreased COMT activity |
| AHCY | rs819147 | AHCY | T (risk) | Decreased AHCY activity |
Activity is estimated as a percentage of normal function based on homozygous vs. heterozygous status of risk alleles. These are approximations derived from published functional studies — they are NOT direct enzyme assays.
| Genotype | Estimated Activity |
|---|---|
| 0 risk alleles (WT) | 100% |
| 1 risk allele (het) | 60–80% (gene-specific, see below) |
| 2 risk alleles (hom) | 15–40% (gene-specific, see below) |
Gene-specific estimates (homozygous risk):
Source: Nazki FH et al. (2014) Gene 533(1):11-20; Ledford AW et al. (2021) Nutrients 13(3):768.
NMC is a composite index (0–100) derived from weighted enzymatic activities:
NMC < 40: Severely reduced NMC 40–60: Moderately reduced NMC 60–80: Mildly reduced NMC > 80: Within normal range
Note (ACMG 2013): Routine population screening for MTHFR variants is not recommended for thrombosis risk assessment. This tool reports genotype facts for clinician contextualisation; NMC bands are descriptive outputs, not intervention triggers. Clinical decisions require individual patient evaluation.
BH4 (tetrahydrobiopterin) is an essential cofactor for tyrosine hydroxylase (dopamine) and tryptophan hydroxylase (serotonin). MTHFR activity directly constrains BH4 regeneration via the folate cycle.
BH4 thresholds:
65%: Within normal range
MTHFR compound heterozygous (C677T + A1298C simultaneously) is the most clinically significant single-gene methylation finding. Total MTHFR activity is reduced more than either variant alone. Flagged explicitly in output.
Developed by Samuel Carmona Aguirre (samuel@unimed-consulting.es) as part of a contribution to the ClawBio open-source bioinformatics library.
Conflict of Interest (COI): The author develops clinical genomics workflows in a private practice context and may use tools derived from this skill as a component in those workflows. This skill is contributed as a standalone open-source genotype reporting tool; its output is not specific to any proprietary clinical platform. All clinical integration decisions rest with the qualified end-user clinician.
ACMG caveat on MTHFR testing (Green et al., Genet Med 2013, 15:153–156): Routine population screening for MTHFR variants is not currently recommended by ACMG for assessment of thrombosis risk, neural tube defect risk, or psychiatric phenotypes. Genotype findings from this tool should be interpreted in the context of the individual patient's clinical history by a qualified clinician.
python skills/claw-methylation-cycle/methylation_cycle.py \
--input path/to/genotype.txt \
--output results/| Version | Date | Change |
|---|---|---|
| 0.1.0 | 2026-04-07 | Initial release. Validated on ASES-2307-002. |
| 0.1.1 | 2026-04-14 | Fixed SKILL.md per PR #133: single YAML block, added Trigger, Workflow, Example Output, Gotchas. Removed unused pandas. Documented line-471 design decision. |
| 0.1.2 | 2026-05-12 | Framing revisions per Manuel Corpas review: reworded BH4 causal language to association-based; reformatted supplement list as clinician-review block with per-nutrient citations; added 6 DOIs; converted em-dashes to ASCII in test docstrings; removed duplicate top-level test file. |
| 0.1.3 | 2026-05-15 | Per PR #133 third review: (1) removed all specific dosages from recommendations; (2) stripped Holomedicina/CAPS/UNIMED/MH-AIAP branding from YAML, description, trigger, example output, Domain Decisions, report header — kept as author attribution only; (3) reframed NMC and BH4 bands as descriptive outputs, not intervention triggers; (4) added ACMG 2013 caveat on routine MTHFR testing; (5) added author COI disclosure; (6) removed obsolete Gotcha #5 (pandas); (7) softened compound het "strongly indicated" language. |
© ClawBio, 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 3 other files in skills/claw-methylation-cycle of ClawBio/ClawBio.
Open the folder on GitHubat commit dece754
Claw Methylation Cycle 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 |
|---|---|---|---|---|---|---|
| Claw Methylation Cycle this skillClawBio/ClawBio | 1.2k | — | ~4.3k | Automated safety check: Pass | MIT | |
| Hypothesis Generationspacering-net/codeg | 3.9k | 14 repos | ~3.6k | Automated safety check: Notes | MIT | |
| GitHub Deep Researchbytedance/deer-flow | 84k | 4 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Nature Paper CardYuan1z0825/nature-skills | 47k | 2 repos | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| Content Research Writerweapp-tailwindcss/weapp-tailwindcss | 1.9k | 25 repos | ~3.5k | Automated safety check: Pass | MIT | |
| Peer Reviewspacering-net/codeg | 3.9k | 17 repos | ~5.9k | Automated safety check: Notes | MIT |
spacering-net/codeg
Structured hypothesis formulation from observations. An agent skill from spacering-net/codeg.
bytedance/deer-flow
Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.
Yuan1z0825/nature-skills
Builds a structured deep-reading card for one scientific paper, covering methods, how experiments support claims, limitations and research ideas, with a script to prepare the source.
weapp-tailwindcss/weapp-tailwindcss
Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section.
spacering-net/codeg
Structured manuscript/grant review with checklist-based evaluation.
mvanhorn/last30days-skill
Research what people actually say about any topic in the last 30 days.
ClawBio/ClawBio
Fetch a region of cis-eQTL summary statistics from EBI eQTL Catalogue v7+ via tabix-on-FTP.
ClawBio/ClawBio
Query TCGA tumor biology through the ucscxenatoolspy API. An agent skill from ClawBio/ClawBio.
ClawBio/ClawBio
Fetch a region of GWAS summary statistics from the NHGRI-EBI GWAS Catalog harmonised collection via tabix-on-FTP.
ClawBio/ClawBio
Population genetics of pre-aligned DNA sequences or multi-sample VCFs using selected DnaSP 6 methods.
ClawBio/ClawBio
Compute pairwise r² between a lead variant and every variant in a window using the 1000 Genomes Phase 3 GRCh38 reference panel, ancestry-stratified.
ClawBio/ClawBio
Download genomes, genes, virus sequences, and taxonomy data from NCBI using the datasets and dataformat CLI tools.
Categories
Methylation cycle analysis — enzymatic activity profiles, Net Methylation Capacity, BH4 axis estimates, compound heterozygosity detection from SNP genotype data. Claw Methylation Cycle is an agent skill from ClawBio/ClawBio. Methylation cycle analysis — enzymatic activity profiles, Net Methylation Capacity, BH4 axis estimates, compound heterozygosity detection from SNP genotype data.
Claw Methylation Cycle fits situations like: research & Science work in your project.
Run `npx skills add ClawBio/ClawBio --skill claw-methylation-cycle -a claude-code`. Or copy the skill folder (skills/claw-methylation-cycle in ClawBio/ClawBio) into .claude/skills/claw-methylation-cycle in your project. Claude Code loads it when a task matches its description.
Run `npx skills add ClawBio/ClawBio --skill claw-methylation-cycle -a codex`. Or copy the skill folder (skills/claw-methylation-cycle in ClawBio/ClawBio) into .agents/skills/claw-methylation-cycle 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 ClawBio/ClawBio --skill claw-methylation-cycle -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/claw-methylation-cycle, .gemini/skills/claw-methylation-cycle, .github/skills/claw-methylation-cycle and .opencode/skills/claw-methylation-cycle in your project.
Going by SKILL.md and its folder, Claw Methylation Cycle needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. 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.
Claw Methylation Cycle is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.3k tokens (SKILL.md is roughly 17k 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 Claw Methylation Cycle: Hypothesis Generation (spacering-net/codeg, 3.9k stars), GitHub Deep Research (bytedance/deer-flow, 84k stars), Nature Paper Card (Yuan1z0825/nature-skills, 47k stars) and Content Research Writer (weapp-tailwindcss/weapp-tailwindcss, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
ClawBio (a GitHub organization) maintains it in ClawBio/ClawBio, which has 1,154 GitHub stars. The repository holds 104 skills in this directory. The repository was last updated on October 8, 2026.
Source: ClawBio/ClawBio on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.