AGENT SKILL

confidential

Use when encrypting, decrypting, password-protecting, locking, unlocking, signing, or verifying confidential content. Routes across cryptoid (Hugo markdown), pagevault (HTML and files for the browser), and gpg (signing and offline archives).

License 许可
MIT
最近更新
2026-10-23
Stars
★ 0
Forks
0

01 前言 Front Matter

name
confidential
description
Use when encrypting, decrypting, password-protecting, locking, unlocking, signing, or verifying confidential content. Routes across cryptoid (Hugo markdown), pagevault (HTML and files for the browser), and gpg (signing and offline archives).

02 资源文件 3

03 SKILL.md 正文

Confidentiality Toolkit

Pick the right tool for what needs protecting, apply it, and optionally sign the result.

Tool Selection

Signal Tool Why
Hugo site, markdown under content/, _index.md cascade, .cryptoid.yaml cryptoid Multi-user/group whole-page encryption integrated with the Hugo build
HTML files, built site output, PDFs/images for web delivery, <pagevault> tags pagevault Section-level or whole-file encryption, self-contained HTML with viewers
Signing, signature verification, offline archives, .gpg/.sig files gpg Detached signatures, public-key encryption, passphrase archives

Decision Tree

Is the target Hugo MARKDOWN content (files under content/)?
  YES -> cryptoid
  NO  -> Is this HTML, built site output, or a file meant for browser viewing?
    YES -> pagevault
    NO  -> gpg

Hugo carve-out: cryptoid encrypts markdown only. Hugo assets (PDFs, images in static/) and built HTML go to pagevault, even on a Hugo site.

Override: if the user names a tool explicitly, use it.

Compound Workflows

  • Encrypt and sign: lock with pagevault (or build the cryptoid-encrypted site), then gpg --detach-sign the output.
  • Verify then decrypt: verify the signature against the expected signer's fingerprint (not just "Good signature"), then pagevault unlock. Recipe in gpg.md.
  • Web delivery plus archive: pagevault lock for browser access, gpg -e the original for offline backup.

Safety Rules (apply to every tool)

  • Secrets never on argv. Do not pass passwords with -p, --passphrase, or echo "pw" |: argv is visible in ps and literals land in shell history. Use the tool's prompt, its config file (.pagevault.yaml, .cryptoid.yaml), the PAGEVAULT_PASSWORD environment variable, or gpg's --passphrase-file/--passphrase-fd 3.
  • Config files hold cleartext credentials. .cryptoid.yaml and .pagevault.yaml must be in .gitignore.
  • Private source repo. cryptoid restores plaintext after each build and pagevault leaves the unlocked originals in place, so the source repo holds plaintext. It must be private, or the plaintext must never be committed.
  • Strong passphrases. Ciphertext is published and PBKDF2 (310,000 iterations) is the only brake on offline guessing. Use long random passphrases, not memorable words.
  • Deploy the locked files. pagevault never overwrites its input: HTML goes to _locked/ (or -d DIR), other files to a sibling .html (or -o FILE). cryptoid encrypts content/ in place until cryptoid decrypt. Confirm the deployed files are the locked ones.

Tool References

Read the reference for exact commands before running anything:

  • cryptoid (config, cascade rules, build workflow, user/group management): ${CLAUDE_PLUGIN_ROOT}/skills/confidential/references/cryptoid.md
  • pagevault (lock/unlock/mark, output paths, multi-user sync, Hugo integration): ${CLAUDE_PLUGIN_ROOT}/skills/confidential/references/pagevault.md
  • gpg (signing, pinned verification, offline archives): ${CLAUDE_PLUGIN_ROOT}/skills/confidential/references/gpg.md

04 同仓库更多 Skills

Abdulqudduz
Abdulqudduz/claude-anvil

worldsmith-methodology

Use when working in a project with a worldbuilding documentation ecosystem (docs/ or lore/ directory). Provides the documentation-first methodology: canonical hierarchy, doc roles (timeline, lore, characters, systems), propagation discipline, and the dual canonical and exploratory workflow.

★ 0
Abdulqudduz
Abdulqudduz/claude-anvil

prose-craft

Use when writing fiction, editing fiction prose, reviewing chapters, or drafting scenes. Covers prose craft, dialogue mechanics, scene structure, and common failure modes in AI-assisted fiction. Trigger phrases: "write fiction", "edit chapter", "prose review", "scene draft", "dialogue check", "fiction craft", "edit this scene", "review my prose".

★ 0
Abdulqudduz
Abdulqudduz/claude-anvil

vista

This skill should be used when the user asks about research directions, open problems, future work, or follow-up research from the academic literature. Trigger phrases include "open problems in X", "what's next for Y", "future work for paper Z", "research directions on T", "salient follow-up research", "what should I work on next in", "find me follow-up research unrelated to my prior work", "broad survey of W", "neglected directions in V". Routes the request to the right Vista MCP tool, reads back the structured paper sections, and synthesizes research directions in the conversation.

★ 0
Abdulqudduz
Abdulqudduz/claude-anvil

synthesize

Make a research-agent run conclude and write synthesis.md (outcome, key findings, failed approaches, open questions, recommendations). Signals a live researcher to wrap up, or launches one in synthesis mode when none is running. Use when results are good enough or the agent is stalling.

★ 0
Abdulqudduz
Abdulqudduz/claude-anvil

status

Show the current state of a research-agent run from .research/: liveness, cycles and budget, sub-problem and hypothesis statuses, eval trend, current focus, and branches. Read-only.

★ 0
Abdulqudduz
Abdulqudduz/claude-anvil

resume

Resume an interrupted research-agent run from .research/. Re-launches the researcher to reload its structured state and continue from the current focus, optionally on a named branch or with a new budget. Use after a session restart, crash, or explicit pause.

★ 0