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-visualizenpx skills add blackblue-labs/skill2 --skill skill2-visualizegit 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-visualize)<a href="https://agentmods.dev/skills/blackblue-labs/skill2/skill2-visualize"><img src="https://agentmods.dev/badge/skills/blackblue-labs/skill2/skill2-visualize.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 | $0.00029 | $0.00912 |
| Opus 5 | $0.00015 | $0.00456 |
| Sonnet 5 | $0.00006 | $0.00182 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
skill2-visualize 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visualize Skill Libraries
Present local inventory, usage, and test evidence in the terminal. When review is useful, surface delete and downgrade candidates in plain language (plus optional merge/projectize). Never modify the library.
Ownership
- Visualize presents evidence and optional read-only delete/downgrade candidates.
- Audit finds static defects.
- Test produces behavior evidence.
- Create applies approved merges, moves, or restructuring.
Method
- Run terminal
uv run --script <skill-dir>/scripts/run -- visualizeagainst the skill root, Codex + Claude usage roots, and test-run evidence. - Run read-only
uv run --script <skill-dir>/scripts/run -- suggest --jsonagainst the same roots (visualize CLI also embeds a short candidate block). - Present a short terminal summary only (see Output). Keep observed facts separate from inference.
- If delete/downgrade candidates were shown, end with the Output contract question (final line).
- Read
references/lifecycle-suggestions.mdonly when the user asks for detailed expansion of a candidate. - Never modify, delete, move, or merge skill files. No HTML or report-file flow.
Interpretation
- Exact
SKILL.mdreads are usage evidence, not complete invocation history. - Zero direct calls means current adapters found none; it does not prove no use.
- Broad scans, maintenance, and worker reads are not direct activation.
- Missing tests remain missing; never infer pass.
- Low frequency never authorizes deletion.
- Delete candidate ≠ delete now. It means: no usage, no tests, no owner signal — maybe removable after human check.
- Downgrade candidate ≠ bad skill. It means: mostly broad/worker noise; might be a piece of another skill, not a standalone.
Output
Default terminal response: compact all-skill frequency chart. Target ≤ inventory skill count + 14 non-empty lines. Expand only after the user asks for detail.
Required default shape:
- One summary line (inventory totals + key usage/test counts).
- Compact all-skill terminal bar chart — exactly one row per skill in inventory (include zero-call skills). Sort by direct desc, then indirect desc, then name. Each row: skill name, stacked bar (
█direct +░indirect), D/I counts. Include a short legend under the chart. - Suggestions block (plain words — do not say "lifecycle"):
- Delete candidates — up to 5 (
delete_candidate) - Downgrade candidates — up to 5 (
downgrade) - Optional one-liners for merge/projectize only if present
- If a bucket is empty, print
(none)for that bucket
- Delete candidates — up to 5 (
- One evidence-limit line.
- Final yes/no detailed-review question only when at least one delete or downgrade candidate was shown.
What ships with it
10 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.
- references/lifecycle-suggestions.md 2.1 KB
- scripts/_runtime/skill2/__init__.py 22 B runs code
- scripts/_runtime/skill2/cli.py 13 KB runs code
- scripts/_runtime/skill2/models.py 6.5 KB runs code
- scripts/_runtime/skill2/report.py 9.8 KB runs code
- scripts/_runtime/skill2/scan.py 7.3 KB runs code
- scripts/_runtime/skill2/suggest.py 9.3 KB runs code
- scripts/_runtime/skill2/usage.py 17 KB runs code
- scripts/.runtime-manifest.json 1.2 KB
- scripts/run 888 B
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 · 74 lines · 29 tokens per session scan A 9e7c1381537c
skill2-visualize is a skill published in the GitHub repository blackblue-labs/skill2 (33 stars, last pushed 21d ago), licensed MIT. It adds 29 tokens to every session and 912 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.