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 agentmods add skills/blackblue-labs/skill2/skill2-createnpx skills add blackblue-labs/skill2 --skill skill2-creategit clone --depth 1 https://github.com/blackblue-labs/skill2Wrote 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/blackblue-labs/skill2/skill2-create)<a href="https://agentmods.dev/skills/blackblue-labs/skill2/skill2-create"><img src="https://agentmods.dev/badge/skills/blackblue-labs/skill2/skill2-create.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00023 | $0.00672 |
| Opus 5 | $0.00012 | $0.00336 |
| Sonnet 5 | $0.00005 | $0.00134 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
skill2-create 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 4d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Agent Skills
Create the smallest reusable instruction set that changes agent behavior without duplicating existing ownership.
Scope
| Signal | Landing |
|---|---|
| Distinct reusable trigger and standalone workflow | Top-level skills/<name>/SKILL.md |
| More depth under the same trigger and workflow | references/ under the owning skill |
| Repo-bound paths, commands, or conventions | Project-local skill |
| One-off answer or pure mechanical rule | No skill → script / validator / docs / lint / CI |
When uncertain, prefer references/ or project-local placement over expanding the top-level namespace.
Authoring
- Define user trigger, desired behavior, output, and hard constraints.
- Find existing ownership before creating a new top-level skill.
- Choose scope and name from user intent, not implementation or one harness.
- Write minimal
SKILL.md; add resources only when they reduce noise or make execution deterministic. - Apply changes only when requested. Run repository validator when available.
SKILL.md
- Plain Markdown with YAML frontmatter
name: kebab-case; match directory namedescription: trigger conditions only; do not summarize workflow- Body: principles, decisions, constraints, and output contract
- Keep instructions terse; explain only non-obvious choices
- Use relative paths; never embed secrets or accidental machine-local paths
- Preserve existing user rules unless change is required
Resources
| Resource | Use |
|---|---|
references/ |
Heavy detail loaded under the same trigger |
scripts/ |
Deterministic, repeated, or fragile execution |
assets/ |
Files copied or transformed into deliverables |
Create only needed directories. Keep references one hop from SKILL.md. Do not nest discoverable skills.
Do not create optional metadata unless the target repository or distribution format requires it.
Commands
Skill-owned scaffold:
uv run --script <skill-dir>/scripts/run -- scaffold skill <name>
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 83 lines · 23 tokens per session scan A 7b985f5dc9d1
skill2-create is a skill published in the GitHub repository blackblue-labs/skill2 (33 stars, last pushed 20d ago), licensed MIT. It adds 23 tokens to every session and 672 once invoked, about $0.0001 per session on Opus 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
ligandmpnn
Inverse-fold a backbone with ligand, nucleic-acid, and metal context using LigandMPNN (Dauparas et al. 2023, github.com/dauparas/LigandMPNN). Reach for this skill to redesign the residues lining a binding pocket around a bound small molecule or cofactor, to design metal-coordinating sites where the geometry must be…
evo2
Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing per-nucleotide or per-sequence likelihoods for variant effect scoring, (2) Embedding genomic windows for downstream classification, (3) Generating DNA conditioned on a prefix, (4) Scoring…
package-author
当用户要把手头的工具打包/标准化成 pinvou 插件包时使用——包括纯技能(SKILL.md)、纯 MCP 服务或它们的组合包。用户说"打包/做成插件包/标准化这个工具/给我一个能上传的标准包/写 plugin.json/加个图标"等，或给了散乱脚本/目录要整理成可上传 zip 时，用本技能把内容规范成 plugin-protocol 标准包（补 plugin.json、补 mcp/manifest.json、补 SKILL.md、补图标、校验命名）。.
google-meet
Google Meet via gws: create spaces, fetch join links, list recordings.