Defuddle
kepano/obsidian-skills
Uses the Defuddle CLI to pull clean, readable Markdown, JSON or metadata from web pages, stripping navigation, ads and clutter to save tokens.
Diagnose the local dev machine before any APC loop step — run apc env doctor, classify each failure into a fault domain, apc env up to auto-fix what is safe, then fingerprint.
MITAuto-check: notes
Install Env Doctor
$ npx skills add Prismer-AI/PrismerCloud --skill env-doctor -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Prismer-AI/PrismerCloud env-doctor --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/Prismer-AI/PrismerCloud.git skills-src && mkdir -p .claude/skills && cp -r skills-src/sdk/apc/skills/env-doctor .claude/skills/env-doctor && 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 "env-doctor" agent skill from https://github.com/Prismer-AI/PrismerCloud/tree/main/sdk/apc/skills/env-doctor into .claude/skills/env-doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "env-doctor", 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/Prismer-AI/PrismerCloud/tree/main/sdk/apc/skills/env-doctorType 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 Prismer-AI/PrismerCloud --skill env-doctor -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Prismer-AI/PrismerCloud env-doctor --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Prismer-AI/PrismerCloud.git skills-src && mkdir -p .agents/skills && cp -r skills-src/sdk/apc/skills/env-doctor .agents/skills/env-doctor && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "env-doctor" agent skill from https://github.com/Prismer-AI/PrismerCloud/tree/main/sdk/apc/skills/env-doctor into .agents/skills/env-doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "env-doctor", 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 Prismer-AI/PrismerCloud --skill env-doctor -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Prismer-AI/PrismerCloud env-doctor --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Prismer-AI/PrismerCloud.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/sdk/apc/skills/env-doctor .cursor/skills/env-doctor && 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 "env-doctor" agent skill from https://github.com/Prismer-AI/PrismerCloud/tree/main/sdk/apc/skills/env-doctor into .cursor/skills/env-doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "env-doctor", 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/Prismer-AI/PrismerCloud.git --path sdk/apc/skills/env-doctor--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 Prismer-AI/PrismerCloud --skill env-doctor -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Prismer-AI/PrismerCloud env-doctor --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Prismer-AI/PrismerCloud.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/sdk/apc/skills/env-doctor .gemini/skills/env-doctor && 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 "env-doctor" agent skill from https://github.com/Prismer-AI/PrismerCloud/tree/main/sdk/apc/skills/env-doctor into .gemini/skills/env-doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "env-doctor", 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 Prismer-AI/PrismerCloud env-doctorInstalls 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 Prismer-AI/PrismerCloud --skill env-doctor -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Prismer-AI/PrismerCloud.git skills-src && mkdir -p .github/skills && cp -r skills-src/sdk/apc/skills/env-doctor .github/skills/env-doctor && 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 "env-doctor" agent skill from https://github.com/Prismer-AI/PrismerCloud/tree/main/sdk/apc/skills/env-doctor into .github/skills/env-doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "env-doctor", 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 Prismer-AI/PrismerCloud --skill env-doctor -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Prismer-AI/PrismerCloud env-doctor --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Prismer-AI/PrismerCloud.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/sdk/apc/skills/env-doctor .opencode/skills/env-doctor && 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 "env-doctor" agent skill from https://github.com/Prismer-AI/PrismerCloud/tree/main/sdk/apc/skills/env-doctor into .opencode/skills/env-doctor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "env-doctor", 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.
Facts
- Skill name
env-doctor- GitHub stars
- 1.6k
- Token cost
- ~2.4k tokens
- SKILL.md length
- 678 words
- Files
- 2
- Skills in repo
- 88
- Repo updated
- First seen
- Licence
- MIT
At a glance
Diagnose the local dev machine before any APC loop step — run apc env doctor, classify each failure into a fault domain, apc env up to auto-fix what is safe, then fingerprint.
- Works in 4 steps: 诊断（doctor） → 分类（故障域） → 拉起可自动化项（up，dispatch 语境用 --safe） → …
- SKILL.md covers 工具契约（先记死，签名以此为准）, Procedure, 输出契约（机器判据按这个复验，别自由发挥格式） and 产出（副作用 oracle，报告里必须给）, plus 2 more sections
- Calls npx, rg and mysql; needs SKILL_CONFIG_ENC_KEY and IDENTITY_KMS_KEY
What it does
Env Doctor is an agent skill from Prismer-AI/PrismerCloud. Diagnose the local dev machine before any APC loop step — run apc env doctor, classify each failure into a fault domain, apc env up to auto-fix what is safe, then fingerprint. Keeps env faults out of SUT verdicts.
Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `skill.json`). Compatibility notes: ["claude-code","prismer-sdk"]
It works with npm. The licence is MIT.
Example prompts
- “/env-doctor”
Requirements
- Node.js
- Docker
- A credential in SKILL_CONFIG_ENC_KEY
- A credential in IDENTITY_KMS_KEY
- Compatibility (from SKILL.md): ["claude-code","prismer-sdk"]
- Pre-approved tools (allowed-tools): Bash
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit e5d9444. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
Bash
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
npxrgmysqlnodetsx
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
SKILL_CONFIG_ENC_KEYIDENTITY_KMS_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Compatibility
["claude-code","prismer-sdk"]
From compatibility in the SKILL.md frontmatter.
Context cost
Env Doctor loads about 2.4k tokens when it runs. Until then it costs about 56 tokens; SKILL.md has 678 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.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteMentions a .env fileSKILL.md:169
- `secrets` 域缺 key 读作"这台机的 `.env.local` 缺"，不读作"运行时一定拿不到"（Nacos 可能有）——按 `fixHint` 交人。 - NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Bash
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.
SKILL.md
The full file from Prismer-AI/PrismerCloud at commit e5d9444, republished under its MIT licence (© Prismer-AI). 678 words, ~2,423 tokens.
Download SKILL.mdSave it as
.claude/skills/env-doctor/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- env-doctor
- description
- Diagnose the local dev machine before any APC loop step — run apc env doctor, classify each failure into a fault domain, apc env up to auto-fix what is safe, then fingerprint. Keeps env faults out of SUT verdicts.
- allowed-tools
- Bash
- compatibility
- ["claude-code","prismer-sdk"]
- license
- MIT
- scope
- common
- metadata.category
- environment
env-doctor
诊断本机开发环境，把环境故障与**被测代码红（SUT red）**彻底分域——这是 APC 一切循环步骤的地基（apc/06 环境脚手架 · apc/00 §3 不变量 5）。
什么时候用：任何 APC 循环步骤开工前；或 test-runner 报出 env_blocked、dispatch 失败、诊断"为什么这台机器跑不起来"时。
铁律：apc env doctor 判红是环境红，不是产品 bug。你的产出是一份逐项 pass/fail 的诊断 + 每个红项的故障域分类 + 可自动化项已拉起的证据。绝不把环境红说成"代码坏了"。
工具契约（先记死，签名以此为准）
命令形态（承重，别猜）：
apc不在 PATH——它是package.json的 npm script（tsx sdk/apc/bin/apc.ts）。 在 agent 的 cwd（仓库根）里，一律用npx tsx sdk/apc/bin/apc.ts <sub>直接跑（stdout 是纯 JSON，不被 npm banner 污染）。下表用apc作简写，实跑请替换成npx tsx sdk/apc/bin/apc.ts。
| 命令 | 作用 | stdout | 退出码 |
|---|---|---|---|
apc env doctor | 只读跑完 env-manifest 四段，逐项 pass/fail + fix-hint | 结构化 JSON（消费者契约） | 0 全绿 · 78 env_blocked（存在环境红） |
apc env up --safe [--dry-run] [--only=a,b] | 幂等拉起可自动化的轻量项；--safe 下 heavy 步（colima / dev-stack / kind / npm ci / prisma / migrations）不自动跑，只归 manual[] 出 fix-hint | JSON 报告 | 0 ok · 1 有步骤 failed |
apc env fingerprint | 环境指纹（机器等价性证明） | JSON 指纹 | 0 |
apc env doctor的 exit 78 是承重信息：它表示"存在环境红"，不是崩溃。一项探针崩了也不塌全轮——doctor 逐项try/catch，其它项照常给结论。- stdout 是纯 JSON，人读摘要走 stderr。解析结果一律从 stdout 的 JSON 取，不要从人读摘要正则抠。
- dispatch 语境铁律（apc/11 §0.17 缺口1）：你是被一次 dispatch 拉起跑诊断的，不是人坐在终端做环境自举。绝不跑不带
--safe的apc env up——它的 docker 步会colima start（可耗时数分钟），在非交互 agent 环境里会 block 直到被 reaper abort，本次运行就白跑了。要拉起环境只用apc env up --safe（heavy 步只出 fix-hint 不执行）。
Procedure
1. 诊断（doctor）
npx tsx sdk/apc/bin/apc.ts env doctor > /tmp/apc-doctor.json
echo "doctor exit=$?"从 /tmp/apc-doctor.json 读结构化结果，真实 schema（字段名以此为准）：
- 顶层：
{ envStatus, exitCode, summary:{pass,fail,skip,total}, failed:[<itemId>...], undetected:[<itemId>...], items:[...] }。 - 每个
items[]元素：{ item(id,如 "toolchain.node"), label, section(infra|toolchain|secrets), status(pass|fail|skip), detail, fixHint, strength }。 failed[]= 所有status:fail的 item id；undetected[]= 所有status:skip的 item id。
判据：summary.total == summary.pass + summary.fail + summary.skip == items.length——一项崩不塌全轮。
exit 0→ 环境全绿，产出"逐项 pass"的诊断，收工。exit 78→ 存在环境红（failed[]非空），进第 2 步分类。
2. 分类（故障域）
故障域 = item 的 section 字段（不是另算的）。把每个 status:fail 的 item 按 section 归组，逐项列出 { item, section, detail, fixHint }：
| 故障域（section） | 典型 item | 处置 |
|---|---|---|
infra（本机基础设施） | infra.mysql-3307 / infra.redis-6380 / infra.nacos / infra.kind-<cluster> / infra.cloud-dev-server 未起 | apc env up 可拉起 |
toolchain（工具链版本） | toolchain.node major / 锁定 claude binary 版本不符 / 网关口径 | apc env up 装锁定 binary；node 需人手 |
secrets（凭据/密钥） | secrets.env-local-required-keys 缺 SKILL_CONFIG_ENC_KEY / IDENTITY_KMS_KEY 等 | 不代办——只报 fixHint，等人按提示补 |
project（工程态） | project.node-modules-lockfile / project.prisma-clients / project.mysql-migrations-pending / project.version-alignment | 多数是 heavy 步，--safe 下归 manual[] 出 fix-hint |
段是四段不是三段：
sdk/apc/env/manifest.ts的四段清单是infra/toolchain/secrets/project（ENV_MANIFEST由这四组拼成）。分类只认 item 的section字段，别把project项硬塞进前三域。
判据：secrets 域的红永远不自动修（apc env up 只出 fix-hint，凭据不代办，apc/00 §3）。别声称已修一个 secrets 项。
3. 拉起可自动化项（up，dispatch 语境用 --safe）
npx tsx sdk/apc/bin/apc.ts env up --safe
echo "up exit=$?"--safe是 dispatch 语境的强制形态：heavy 步（colima / dev-stack / kind / npm ci / prisma / migrations）不自动跑，只归manual[]出 fix-hint。轻量幂等步（配置目录 / bare 替身）照跑。这样本步永不 block。apc env up是幂等的：第二次跑对已就绪项全skip。- 只对
infra/toolchain里可自动化的项生效；secrets域只出 fix-hint。 - 修完回到第 1 步重跑
apc env doctor确认红项减少（红→绿可逆才算真修，恒红是没修）。heavy 步落在manual[]属预期——它们要人在交互终端跑不带--safe的 up，不由本次 dispatch 代办。
4. 指纹（fingerprint）
npx tsx sdk/apc/bin/apc.ts env fingerprint > /tmp/apc-fingerprint.json
echo "fingerprint exit=$?"指纹是机器等价性证明——同一环境两台机器指纹应等价。收工时附上它。
Show full SKILL.md (341 more words)Show less
输出契约（机器判据按这个复验，别自由发挥格式）
本 skill 的验收判据不再是「报告里出现了 infra / fail: 2 这些词」——旧判据里 \b(infra|toolchain|secrets?)\b 一个词就能让「故障域已分类」变绿，(pass|fail|skip)…\d+ 一个数字就能冒充「逐项报告」。现在判据找的是每一个 item 自己那一行，并把该行的引用读回磁盘复核（structured-criteria.ts 的 dimension-coverage）。
逐项作答（每个 item 独占一行 + 用它的 item id 当 key，值给：真实 status → 故障域 → 关键 detail/fixHint → 该 item 在 manifest 里的声明行）：
- infra.docker-daemon: pass | domain=infra | sdk/apc/env/manifest.ts:165
- infra.mysql-3307: pass | domain=infra | MySQL 8.0.46 真握手 | sdk/apc/env/manifest.ts:178
- toolchain.node: fail | domain=toolchain | node 23.9.0 major 23 ≠ pin 20 | fixHint: nvm use 20 | sdk/apc/env/manifest.ts:318
- toolchain.hermes-gateway-models: skip | domain=toolchain | 未检测（无凭据）| sdk/apc/env/manifest.ts:408
- secrets.env-local-required-keys: fail | domain=secrets | 本地凭据缺失，只出 fixHint 不代办 | sdk/apc/env/manifest.ts:449
- project.mysql-migrations-pending: fail | domain=project | 1 条 pending | fixHint: npm run db:migrate | sdk/apc/env/manifest.ts:603判据钉住的 21 个 item id（= ENV_MANIFEST 除 infra.kind-<cluster>）：infra.docker-daemon · infra.mysql-3307 · infra.mysql-migration-ledger · infra.redis-6380 · infra.nacos · infra.cloud-dev-server · toolchain.node · toolchain.docker-compose · toolchain.kubectl · toolchain.kind-cli · toolchain.claude-code-binary-pin · toolchain.hermes-binary · toolchain.hermes-gateway-models · secrets.env-local-required-keys · secrets.ota-ui-signing-key · project.node-modules-lockfile · project.prisma-clients · project.mysql-migrations-pending · project.version-alignment · project.claude-config-dir · project.bare-repo-mirror。
infra.kind-<cluster>的 id 由CLUSTER_NAME拼（manifest.ts:249），不进固定判据（否则改环境变量会让如实报告变红）——但它照样要出现在你的逐项表里。
故障域汇总（四段各独占一行，引用该段清单在 manifest 里的起始行）：
- domain-infra: 7 项 → pass 7 / fail 0 / skip 0 | sdk/apc/env/manifest.ts:163
- domain-toolchain: 7 项 → pass 5 / fail 1 / skip 1 | sdk/apc/env/manifest.ts:316
- domain-secrets: 2 项 → pass 1 / fail 1（凭据永不自动修，只出 fixHint）| sdk/apc/env/manifest.ts:447
- domain-project: 6 项 → pass 5 / fail 1 | sdk/apc/env/manifest.ts:569判据强制三条：
- 每个 key 必须有自己那一行——「报告里别处提过
toolchain.node」不算作答（漏一项判红）。 - 每行的值必须带至少一条能在磁盘上复核的
path:line（文件存在、行号在范围内、该行非空）——rg -n "id: 'toolchain.node'" sdk/apc/env/manifest.ts出来的行号，别猜。 - 只有真不适用的行才写
N/A — <理由 ≥20 字符>；真 item 不许以无/N/A开头（会被当成"这项不适用"），一律以真实pass/fail/skip开头。
引用写法：必须 repo-root-relative（sdk/apc/env/manifest.ts:318，不要简写、不要绝对路径）；rg -c 出的 path:12 是命中计数不是行号，要写就写 count=12。
诚实边界（dimension-coverage 这条判据管到哪）：它复核的是「每项都作答了 + 引用真实存在」，不复核 status 本身。把 ← 已由下面的 ③ 收窄（2026-07-26）。fail 写成 pass 骗不过重跑 doctor 的人，但骗得过这条判据。
③ 原始产物 + 七行判定声明（json-claim 复核；这条是本 skill 的承重判据）
把 apc env doctor 的 stdout 原样贴进一个 fenced JSON 块（别摘录、别改写），并给出七行：
DOCTOR-EXIT: 78
DOCTOR-VERDICT: env-blocked
DOCTOR-PASS: 16
DOCTOR-FAIL: 5
DOCTOR-SKIP: 1
DOCTOR-TOTAL: 22
DOCTOR-FAILED-IDS: toolchain.node,secrets.env-local-required-keys,project.mysql-migrations-pending
DOCTOR-UNDETECTED-IDS: toolchain.hermes-gateway-modelschecker 重新解析产物并核对：
- 五个计数与退出码必须逐字等于产物字段（
exitCode/summary.pass|fail|skip|total）。这条直接管住了本文档自己犯过两次的错：apc/12 §0 的 doctor 计数先写「20 pass / 2 fail」、更正为「18 pass / 3 fail / 1 skip」、今天实测又是16/5/1—— 报计数而不报全、且不与产物对账，账就会漂。 DOCTOR-VERDICT由exitCode派生，只有两个合法值：0 ⇒ all-green、78 ⇒ env-blocked。exitCode只允许0|78—— 任何别的值意味着 doctor 自己崩了（"一项崩不塌全轮"这条不变量的机器化）。DOCTOR-FAILED-IDS/DOCTOR-UNDETECTED-IDS必须逐字列出产物里的真实 id 集合（逗号分隔、保持产物顺序）。把某一项的fail写成pass会与这份清单直接冲突。- 三条 implication：
exitCode=78 ⇒ envStatus='env_blocked'；exitCode=0 ⇒ failed 为空；envStatus='ok' ⇒ failed 为空。
仍未被判据覆盖的（诚实）：逐项 status 与汇总计数之间的自洽性没有自动交叉验证 —— checker 能确认
DOCTOR-FAIL: 5等于产物，也能确认 failed 清单，但不会去数你上面那 22 行里有几行写了fail。一个同时篡改逐项行、汇总行与清单的伪造者仍能自洽。skip 不是 pass：total == pass+fail+skip要自己核，别把 skip 并进 pass 报。
产出（副作用 oracle，报告里必须给）
- 逐项 pass/fail 诊断：从
apc env doctor的 stdout JSON 逐个 item 列{item, status, section}+summary；证明"一项崩不塌全轮"（summary.total == pass+fail+skip == items.length）。 - 故障域分类：每个
failed[]项按其section归到infra|toolchain|secrets，带detail+fixHint。 - up 幂等证据：
apc env up --safe退出码 + 已就绪项全 skip（heavy 未修项归manual[]，属预期）。 - fingerprint JSON：
apc env fingerprint产物。
不许：把 secrets 红当作已修；把 doctor 的 exit 78 当作 SUT 红上报；从人读摘要抠结论而非读 stdout JSON。
诚实边界
apc env doctor无 task 上下文（它不在一次 dispatch 的 task 里跑），所以下方调用回执的cloud skill ack会 exit 3（无 task 上下文）——这是契约限制，不是失败。本次运行没有回执，报告里不得声称已 ack。secrets域缺 key 读作"这台机的.env.local缺"，不读作"运行时一定拿不到"（Nacos 可能有）——按fixHint交人。
<!-- APC-ACK:v1 -->调用回执（APC 平台方运营纪律 · 自动注入，勿手改）
执行本 skill 的第一步，先落一条调用回执：
cloud skill ack env-doctor --task "$PRISMER_TASK_ID"按退出码分流（这条命令的退出码是承重信息，禁止用 || 兜底、; true、
set +e 或重定向把它抹掉）：
| exit | 含义 | 你要做的 |
|---|---|---|
0 | 回执已落库（im_task_logs.action='skill_ack'） | 继续执行本 skill |
3 | 无 task 上下文——本次运行没有 task，产不出回执 | 继续执行本 skill；但本次运行没有回执，任何报告里都不得声称已 ack |
4 | 你不是该 task 的 assignee，服务端拒绝 | 停下并上报：回执只能由执行该 task 的 agent 产生 |
1 | 其它失败（网络 / 服务端） | 重试一次；仍失败则继续执行，并在结果里显式标注「回执缺失」 |
回执只证明本 skill 被调度，不证明执行正确——效果证明由本 skill 自己的 acceptanceCriteria 副作用断言承担（apc/04 §2 层 1 诚实标注）。
<!-- /APC-ACK:v1 -->© Prismer-AI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in sdk/apc/skills/env-doctor of Prismer-AI/PrismerCloud.
- SKILL.md
- skill.json
Open the folder on GitHubat commit e5d9444
Compare with similar skills
Env Doctor 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 |
|---|---|---|---|---|---|---|
| Env Doctor this skillPrismer-AI/PrismerCloud | 1.6k | — | ~2.4k | Automated safety check: Notes | MIT | |
| Defuddlekepano/obsidian-skills | 49k | 11 repos | ~208 | Automated safety check: Pass | MIT | |
| Vercel Deploybytedance/deer-flow | 84k | 10 repos | ~797 | Automated safety check: Pass | MIT | |
| Knap Markdown Templateskepano/obsidian-skills | 49k | 2 repos | ~986 | Automated safety check: Pass | MIT | |
| MCP Server BuildershareAI-lab/learn-claude-code | 78k | 4 repos | ~1.2k | Automated safety check: Pass | MIT | |
| Nx Run Tasksnomcopter/react-mosaic | 4.8k | 8 repos | ~613 | Automated safety check: Pass | Custom licence |
Similar skills
Vercel Deploy
bytedance/deer-flow
Deploys a project to Vercel with one script and no login, then returns a live preview URL and a claim link for moving the deployment into your own Vercel account.
Knap Markdown Templates
kepano/obsidian-skills
Renders Markdown notes from Knap templates and JSON data on the command line, including notes built from Defuddle web page output.
MCP Server Builder
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
Nx Run Tasks
nomcopter/react-mosaic
Helps with running tasks in an Nx workspace. An agent skill from nomcopter/react-mosaic.
OpenHarness End-to-End Evals
HKUDS/OpenHarness
Validates OpenHarness features by running real multi-turn agent loops with live LLM calls against an unfamiliar codebase, checking actual tool execution.
More from Prismer-AI/PrismerCloud
All 88 skills in this repoPrismer Google Workspace
Prismer-AI/PrismerCloud
Gives an agent account-scoped access to Gmail, Calendar, Drive, Contacts, Docs and Sheets through the gws CLI or a bundled Python client.
Prismer Skill Creator
Prismer-AI/PrismerCloud
Walks an agent through creating, importing, editing, validating, testing and publishing Prismer Skills with a fixed workflow and bundled scripts.
Himalaya Email CLI
Prismer-AI/PrismerCloud
Operates a mailbox from the terminal with the external Himalaya CLI over IMAP, SMTP, Notmuch or Sendmail, separate from any built-in email gateway adapter.
Prismer Image Generation
Prismer-AI/PrismerCloud
Generates one image from a text prompt with a bundled Node.js helper and delivers it once as the attachment to the current Prismer reply.
Manim Explainer Videos
Prismer-AI/PrismerCloud
Produces 3Blue1Brown-style explainer animations with Manim Community Edition for math, algorithms, equations and architecture diagrams, with planning and rendering references.
Prismer Role Builder
Prismer-AI/PrismerCloud
Creates or updates Prismer role templates from a persona, SOP or job description, and turns a role into a working agent that runs its first task through a bundled script.
Related
Works with
Questions about Env Doctor
What does Env Doctor do?
Diagnose the local dev machine before any APC loop step — run apc env doctor, classify each failure into a fault domain, apc env up to auto-fix what is safe, then fingerprint. Env Doctor is an agent skill from Prismer-AI/PrismerCloud. Diagnose the local dev machine before any APC loop step — run apc env doctor, classify each failure into a fault domain, apc env up to auto-fix what is safe, then fingerprint.
How do I install Env Doctor in Claude Code?
Run `npx skills add Prismer-AI/PrismerCloud --skill env-doctor -a claude-code`. Or copy the skill folder (sdk/apc/skills/env-doctor in Prismer-AI/PrismerCloud) into .claude/skills/env-doctor in your project. Claude Code loads it when a task matches its description.
How do I install Env Doctor in Codex?
Run `npx skills add Prismer-AI/PrismerCloud --skill env-doctor -a codex`. Or copy the skill folder (sdk/apc/skills/env-doctor in Prismer-AI/PrismerCloud) into .agents/skills/env-doctor in your project. Codex loads it when a task matches its description.
Can I use Env Doctor in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Prismer-AI/PrismerCloud --skill env-doctor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/env-doctor, .gemini/skills/env-doctor, .github/skills/env-doctor and .opencode/skills/env-doctor in your project.
What does Env Doctor need to run?
Going by SKILL.md and its folder, Env Doctor needs the command-line tools its instructions call (npx, rg, mysql, node and tsx) and credentials named SKILL_CONFIG_ENC_KEY and IDENTITY_KMS_KEY. Our summary lists: Node.js; Docker; A credential in SKILL_CONFIG_ENC_KEY; A credential in IDENTITY_KMS_KEY. Its frontmatter pre-approves these tools: Bash. Compatibility (from SKILL.md): ["claude-code","prismer-sdk"].
Does Env Doctor access the network?
SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Env Doctor safe to install?
Our automated static check of SKILL.md found notes only (mentions a .env file; pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Env Doctor use?
Env Doctor is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Env Doctor use?
About 2.4k tokens (SKILL.md is roughly 9.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Env Doctor?
Skills that share tags, products or a category with Env Doctor: Defuddle (kepano/obsidian-skills, 49k stars), Vercel Deploy (bytedance/deer-flow, 84k stars), Knap Markdown Templates (kepano/obsidian-skills, 49k stars) and MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Env Doctor?
Prismer-AI (a GitHub organization) maintains it in Prismer-AI/PrismerCloud, which has 1,555 GitHub stars. The repository holds 88 skills in this directory. The repository was last updated on September 30, 2026.
Source: Prismer-AI/PrismerCloud on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.