agentsclimarketplace

Personal api

Skill ed1son99/skills/skills/note-taking/personal-api

Collection of Hermes Agent skills — 255 reusable AI agent workflows across 39 categories

Install
npx -y skills add ed1son99/skills --skill personal-api

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Turn an Obsidian vault into an AI-readable personal identity layer. Use when setting up ME.md and AGENT.md, scaffolding the full Knowledge Palace v2 structure, onboarding AI assistants, or maintaining the vault contract. Default setup creates the complete 30.knowledge system; --minimal creates only the lightweight identity layer.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

5.0 KB, ~1.0k tokens by cl100k_base, as published. Nobody here has run it

Personal API

Personal API is a lightweight routing skill for creating and maintaining an AI-readable identity layer inside an Obsidian vault.

The skill has three core contracts:

  1. ME.md — identity contract.
  2. AGENT.md — behavior contract.
  3. 30.knowledge/00.system/methodology.md — Knowledge Palace v2 operating manual for the knowledge-production track.

Default setup creates the full Knowledge Palace v2 structure, including 30.knowledge/. Use --minimal only when the user explicitly wants the identity layer without the knowledge-production system.

Trigger Scenarios

Use this skill when the user wants to:

  • create a new AI-readable Obsidian vault structure;
  • install or refresh ME.md / AGENT.md;
  • set up Claude/Codex adapter files for a vault;
  • initialize the 30.knowledge/ Knowledge Palace v2 system;
  • explain how AI agents should read and operate inside the vault;
  • validate or package this skill for release.

Do not use this skill to invent or fill in the user's real identity content. AI may explain fields and provide examples, but the user must provide the actual personal answers.

Workflows

1. Install Personal API

Use when the user provides an Obsidian vault path and wants the scaffold installed.

Read:

  • scripts/setup.sh
  • templates/ME.md
  • templates/AGENT.md
  • templates/CLAUDE.md
  • templates/AGENTS.md
  • templates/methodology.md

Run:

export OBSIDIAN_VAULT_PATH="/path/to/vault"
bash scripts/setup.sh

Expected full-mode result:

  • identity layer files at vault root;
  • thin agent adapters CLAUDE.md and AGENTS.md;
  • Track A directories and stubs;
  • full 30.knowledge/ tree;
  • 30.knowledge/00.system/methodology.md.

For identity-only setup:

bash scripts/setup.sh --minimal

Minimal mode must not create 30.knowledge/.

2. Fill Identity And Behavior Contracts

Use when the user is ready to customize ME.md and AGENT.md.

Read:

  • templates/ME.md
  • templates/AGENT.md
  • references/operation-boundaries.md

Rules:

  • explain each placeholder in plain language;
  • ask the user for real identity facts when needed;
  • do not fabricate personal history, values, or preferences;
  • keep Track A identity files human-owned unless the user explicitly authorizes edits.

3. Start Knowledge Production

Use when the user wants AI-assisted knowledge organization under 30.knowledge/.

Read:

  • references/architecture.md
  • references/vault-layout.md
  • templates/methodology.md

Rules:

  • raw material enters 30.knowledge/10.capture/;
  • compiled notes go to 30.knowledge/40.notes/literature/;
  • permanent notes and frameworks require human review;
  • do not modify Track A core identity content without explicit authorization.

4. Validate And Package

Use before publishing or reviewing this skill.

Read:

  • scripts/validate_skill.py
  • scripts/package_skillhub.sh
  • CHANGELOG.md

Run:

bash -n scripts/setup.sh
python scripts/validate_skill.py
bash scripts/package_skillhub.sh
python scripts/validate_skill.py --dist dist/skillhub/personal-api-2.0.3-skillhub.zip

The source version, README badges, changelog, setup output, and release zip must agree.

Resource Routing

NeedRead
Product overviewREADME.md or README.zh-CN.md
Architecture and methodreferences/architecture.md
Expected vault treereferences/vault-layout.md
AI permission boundariesreferences/operation-boundaries.md
Health checks and maintenancereferences/maintenance.md
Install behaviorscripts/setup.sh
Release checksscripts/validate_skill.py

Version History

2.0.3 — 2026-05-14

  • Converted SKILL.md into a lightweight routing layer.
  • Moved long-form architecture and operating guidance into references/.
  • Added adapter templates for Claude and Codex/OpenAI agents.
  • Added validation and package scripts.
  • Aligned source files, setup output, changelog, and SkillHub release package.

2.0.0 — 2026-05-08

  • Added full Knowledge Palace v2 scaffold and --minimal setup mode.

1.0.0 — 2026-04-19

  • Initial identity-layer skill with ME.md, AGENT.md, and setup script.

What ships with it: 15 files

36.5 KB alongside SKILL.md, 3 of them executable

mounts/

references/

scripts/

templates/

Gives 0 of the 12 instructions most project setup skills give in ~1.0k tokens

Counted across 999 of the 1,637 authors here whose files we hold, read 2026-08-07

  • Ask one question at a timein 29 of 999, across 28 files
  • Detect the package manager from lockfilesin 28 of 999, across 9 files
  • Present findings to the userin 26 of 999, across 5 files
  • Explore current repo statein 24 of 999, across 3 files
  • Update the agent skills block in place if it existsin 24 of 999, across 3 files
  • Install husky lint-staged and prettierin 23 of 999, across 4 files
  • Create the lintstagedrc filein 22 of 999, across 3 files
  • Commit all changed filesin 22 of 999, across 3 files
  • Run lint-staged to verify it worksin 22 of 999, across 3 files
  • Create the husky pre-commit filein 21 of 999, across 2 files
  • Create a prettierrc file if missingin 21 of 999, across 2 files
  • Initialize huskyin 21 of 999, across 2 files

Said here and by no other author read

  • Ask the user for real identity facts when needed
  • Explain each placeholder in plain language
  • Keep identity files human-owned unless explicitly authorized
  • Place raw material in the capture directory
  • Put compiled notes in the literature directory
  • Require human review for permanent notes and frameworks

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,984. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.