Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add matteotitta/genesys-skills --skill skill-cataloggit clone --depth 1 https://github.com/matteotitta/genesys-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/matteotitta/genesys-skills/skill-catalog)<a href="https://agentmods.dev/skills/matteotitta/genesys-skills/skill-catalog"><img src="https://agentmods.dev/badge/skills/matteotitta/genesys-skills/skill-catalog/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/matteotitta/genesys-skills/skill-catalog"><img src="https://agentmods.dev/badge/skills/matteotitta/genesys-skills/skill-catalog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 85 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00096 | $0.10203 |
| Opus 5.5 | $0.00038 | $0.04081 |
| Sonnet 5.5 | $0.00019 | $0.02041 |
| Haiku 4.5 | $0.00010 | $0.01020 |
Grade A, and why
skill-catalog scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 547 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Catalog
Central registry of all Claude skills. The body of this file is auto-generated from each SKILL.md frontmatter by scripts/regenerate-catalog.py, run on every commit via the pre-commit hook. The 107-row table + edge index that follows is the skill's actual deliverable, not bloat — hence the slim_exemption.
To use this catalog, scan the table by primitive (research, content, social, etc.) for the skill you need. Each row shows ontology type, review gate, owning agent, and edge counts. The edge index at the end lists every dependency relationship in flat form for quick grep.
Claude Code Triggers
Invoke when:
- "What skills do I have?" / "Show me the skill catalog"
- "What skill should I use for [task]?"
- "What does [skill] need as input?" / "What can I do after [skill]?"
- "Show skill dependencies" / "Skill registry"
Do NOT invoke when:
- User wants to run a specific skill → Run that skill directly
- User wants to create a new skill → Use
prompt-designorworkflow-design
How to update the catalog
Don't hand-edit between the BEGIN/END markers. Edit individual SKILL.md frontmatter — the pre-commit hook regenerates this section automatically. To regenerate manually:
bash.claude/skills/meta/catalog/skill-catalog/scripts/regenerate-catalog.sh
To validate chains without regenerating:
bash.claude/skills/meta/catalog/skill-catalog/scripts/chain-lint.sh --validate-ontology
For a one-glance catalog state + health check (totals by primitive / status / owner, graph health, recency) — read-only, built on chain-lint:
bash.claude/skills/meta/catalog/skill-catalog/scripts/catalog-query.sh # human summary
bash.claude/skills/meta/catalog/skill-catalog/scripts/catalog-query.sh --json # machine-readable
Skill catalog (auto-generated)
167 active skills. Last commit touching .claude/skills/: 2026-07-27T15:47:14+01:00
AUTO-GENERATED — do not hand-edit between the BEGIN/END markers. Edit individual
SKILL.mdfrontmatter; the pre-commit hook regenerates this section. To regenerate manually:bash.claude/skills/meta/catalog/skill-catalog/scripts/regenerate-catalog.sh.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 547 lines · 96 tokens per session scan A 26458a571db0
skill-catalog is a skill published in the GitHub repository matteotitta/genesys-skills (46 stars, last pushed 13d ago), licensed MIT. It adds 96 tokens to every session and 10,203 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
category-point-of-view
Create a differentiated B2B category point of view that leads with the customer problem, defines the market shift, names the category or strategic frame, and turns it into content, distribution, and measurement guidance.
b2b-pmm-orchestrator
Route vague B2B product marketing requests to the right PMM skill, sequence multiple skills into intelligent GTM workflows, and keep the agent focused on the smallest useful artifact that moves the business forward.
ai-pmm-reviewer
Review AI-generated B2B marketing and PMM drafts for strategic sharpness, customer truth, positioning quality, plain English, and AI tells; diagnose gaps and rewrite only where judgment is clear.
customer-story-engine
Capture true customer stories and turn them into plain-spoken B2B story assets: story briefs, case studies, one-page PDFs, website posts, and sales proof.
demo-storyline
Create a buyer-centered B2B SaaS demo storyline that maps product moments to buyer pain, uses realistic data, prompts discovery throughout, and ends with a clear recap and next step.
sales-narrative-deck
Create a sales-ready B2B narrative deck outline that starts with buyer pain, teaches the market, shows the solution, supports a demo, and gives reps a clear path to proof, pricing, competition, recap, and next steps.