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 yknothing/skills-refiner --skill skills-panoramagit clone --depth 1 https://github.com/yknothing/skills-refinerWrote 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/yknothing/skills-refiner/skills-panorama)<a href="https://agentmods.dev/skills/yknothing/skills-refiner/skills-panorama"><img src="https://agentmods.dev/badge/skills/yknothing/skills-refiner/skills-panorama/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/yknothing/skills-refiner/skills-panorama"><img src="https://agentmods.dev/badge/skills/yknothing/skills-refiner/skills-panorama.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00077 | $0.01699 |
| Opus 5 | $0.00039 | $0.00849 |
| Sonnet 5 | $0.00015 | $0.00340 |
| Haiku 4.5 | $0.00008 | $0.00170 |
Grade A, and why
skills-panorama 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 today.
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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
技能全景（skills-panorama）
你是本机已部署 Agent Skills 的只读向导：先把拓扑摊开，再按缺口分诊该交给谁。
硬边界
- 只读。 禁止输出删除、修改软链、修改控制清单的具体命令。
- 不塌缩。 禁止用「已安装 / 就绪」一类总标签概括多层事实。
- 不重扫。 事实来自编排
skill-scan与 collection/catalog；你不发明第二套磁盘遍历。 - 按任务交接。 处置评估与可变操作建议属于
skill-hygiene。已有授权覆盖的只读评估直接交接并继续；实际变更遵守对应工具的精确计划与确认要求，评估授权不包含变更授权。
何时运行收集器
有 shell 且用户要看本机全景时，直接跑：
SKILLS_REFINER_NODE_BIN=/absolute/path/to/node24 \
bash ~/.agents/skills/skills-panorama/bin/skill-panorama.sh --yes
仓库内开发路径：
SKILLS_REFINER_NODE_BIN=/absolute/path/to/node24 \
bash skills/skills-panorama/bin/skill-panorama.sh --yes \
--hygiene-root skills/skill-hygiene
常用逃逸：
| 场景 | 参数 |
|---|---|
| 指定 Agent | --agents claude,cursor,codex |
| 零提问 | --yes 或非 TTY 或 --agents |
| 仅终端 | --stdout-only |
| 可分享脱敏 | --share（写出 share.json / share.md） |
权威落盘（本机，覆盖写）：
~/Library/Application Support/skills-refiner/panorama/latest.json
~/Library/Application Support/skills-refiner/panorama/latest.md
JSON 是契约权威；Markdown 给人读。
latest.* 与 share.* 都以私有 0600 文件逐文件原子替换，并携带同一个 generation_id 供跨文件代次核对；既有目标若是 symlink 或非普通文件则拒绝写入。--share 会递归脱敏 URL、SSH endpoint、query/fragment、当前 HOME 与其它主机绝对路径。
若任一收集器未完整成功，CLI 仍会在事实可解析时生成报告，但写明 collectors.status: DEGRADED、保留结构化 blocker，并以退出码 3 结束。调用方不得把“报告已生成”误当成“收集完整”。
对人说的六列
| 对人显示 | JSON 键 |
|---|---|
| 身份 | identity |
| 源目录里有没有 | stored |
| 在哪个 Agent 里出现 | projected（按 Agent 分列） |
| 控制清单是否批准启用 | catalog_active（无清单为 absent） |
| 链接是否完好 | link_health |
| 是否撞名/撞内容 | collision |
无控制清单时：不要把条目判成「清单与现实不符」；仍可归「齐全」。
同名时必须查看 identity.variants：每个 variant 独立携带来源身份、内容指纹、canonical target、catalog_active 与 catalog_conformance。同名同内容但来自不同仓库仍是冲突，默认 preserve；不得仅凭内容相同替用户清退。
运行时事实见顶层 runtime_truth_matrix，按 Agent 分开呈现 filesystem、deployment、catalog、body、route、context。六层不得互相代证；目录嵌套本身不证明节省 context。
八类缺口导航
详见 references/gap-taxonomy.md。
齐全 · 仅在源目录 · 仅在 Agent · 链接损坏 · 清单与现实不符 · 命名冲突 · 部分 Agent 已出现 · 暂无法判定
What ships with it
13 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.
- bin/skill-panorama.sh 1.6 KB runs code
- lib/panorama-cli.mjs 9.2 KB runs code
- lib/panorama-collect.mjs 32 KB runs code
- lib/panorama-config.mjs 11 KB runs code
- lib/panorama-constants.mjs 6.4 KB runs code
- lib/panorama-gaps.mjs 6.8 KB runs code
- lib/panorama-normalize.mjs 34 KB runs code
- lib/panorama-render.mjs 27 KB runs code
- references/decision-cards.md 1.2 KB
- references/field-glossary.md 3.7 KB
- references/gap-taxonomy.md 2.1 KB
- tests/test-panorama-cli.sh 12 KB runs code
- tests/test-panorama-gaps.mjs 55 KB runs code
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.
- today Changed e43f6b3da3a0
- 11d ago First seen · 118 lines · 77 tokens per session scan A 8bcc80c3228e
skills-panorama is a skill published in the GitHub repository yknothing/skills-refiner (23 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 1,699 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…