본문으로 건너뛰기
cccskills
무료GitHub에 공개

grounded-vault

Build and maintain a Markdown knowledge store with source links for individual claims. Use Git checks to detect changes in the code a page describes, and archive outdated pages while preserving their history.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

원문원문 설명 보기

Use when maintaining a durable Markdown knowledge store that agents compile from sources, when every number or quote in a wiki page must trace back to an immutable source, or when compiled pages need cheap drift detection against the code they describe. Teaches the raw/wiki/archive layout, per-claim provenance links, and git fingerprints for zero-token staleness checks.

설치 방법 보기

이럴 때 유용합니다

  • Compile notes and papers into source-linked wiki pages
  • Verify numbers and quotations against original sources
  • Check whether code documentation needs updating
  • Archive outdated knowledge while preserving history

포함된 파일(2)

  • SKILL.md5.3 KB
  • references/details.md8.2 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Grounded Vault

A grounded vault is a three-layer Markdown store in which every compiled claim can be traced back to an immutable source and every page can be checked for staleness with one git diff. It needs a git repository and nothing else. The convention comes from the llm-wiki-loop project, which is a reference implementation rather than a dependency; this skill teaches the pattern so it works with plain files and whatever agent is in the session.

When to Use

  • An agent compiles notes, papers, transcripts, logs, or code into wiki pages that later sessions rely on.
  • A page cites numbers, dates, or quotes, and a reader must be able to verify each one against its source.
  • Pages describe code, and rereading the codebase every session to check whether they still hold is too expensive.
  • Knowledge must be corrected without losing history: superseded pages are archived, never deleted.

Session state, task queues, and conversation continuity are a different problem; use the context-management or conductor plugins for those. This skill is about provenance and drift on a durable knowledge store.

The three layers

LayerContentsWho writes itRule
raw/source material: notes, papers, transcripts, logs, exported datapeople and ingestion onlyimmutable once added; agents never edit a raw file
wiki/compiled pages built from raw/ and from codeagents and peopleevery number, date, and quote links to its source
archive/pages that drifted or were supersededagents, during garbage collectionmoved, never deleted; the header says why

Two files sit at the vault root. index.md is the map of every current page. log.md is an append-only record of what changed and why. Both change in the same commit as the page they describe.

Page header contract

Every wiki/ page opens with a header block:

# Authentication architecture

> Raw: [raw/notes/auth-v1.md](../raw/notes/auth-v1.md), [raw/adr/0007-jwt.md](../raw/adr/0007-jwt.md)
> Fingerprint: git:5b237fa
> Monitored: src/auth/jwt.ts, src/auth/session.ts, package.json
> Status: Current
  • Raw: lists every source the page was compiled from. Inline claims link to their specific source as well: Tokens expire after 15 minutes ([raw/adr/0007-jwt.md](../raw/adr/0007-jwt.md)).
  • Fingerprint: is the short commit hash the page was compiled against.
  • Monitored: lists the code paths the page describes. A change to any of them after the fingerprint means the page may be stale.
  • Status: is Current, Outdated (monitored code moved on), or Disputed (a newer source contradicts the page).

Grounding rule

A compiled page states only what a source supports, and every number, date, or quotation appears verbatim in the linked source. A synthesis says it is one and links its inputs. A gap in the sources is written into the page as a gap rather than filled by guessing.

Check it mechanically: for each linked claim, search the linked raw file for the exact figure or quoted phrase. A miss is a grounding error and blocks the commit. The script in references/details.md does this for a whole vault.

Drift detection

Compare the fingerprint with the current tree instead of rereading monitored code:

git diff --stat 5b237fa..HEAD -- src/auth/jwt.ts src/auth/session.ts package.json

Empty output means the page still describes the code it was compiled against. Any output means recompile: reread only the changed files, update the page, and stamp the new fingerprint. The check runs in milliseconds and spends no model tokens.

Workflow

  1. Ingest. Put new material in raw/ under a dated or sourced filename. Never rewrite an existing raw file; add a new one beside it.

  2. Compile. Write or update the wiki/ page with the header block, a source link on every claim, and the fingerprint of the commit the code was read at.

  3. Check. Run the grounding check and the drift check before committing. Fix misses at the source; do not weaken a claim to make the check pass.

  4. Garbage collect. When drift or a contradicting source appears and the page is not recompiled now, change its status, move it to archive/, and record the reason:

    > Status: Outdated
    > Reason: src/auth/session.ts changed after git:5b237fa; see log.md 2026-09-01
    
  5. Update the map. Every add, move, or archive updates index.md and appends one line to log.md in the same commit.

Commit gate

Run both checks from a pre-commit hook or a CI step so a page cannot land with an unverifiable number or a stale fingerprint:

python3 scripts/check_vault.py --strict   # exits 1 on any grounding miss or drifted page

Going deeper

references/details.md covers: the vault check script, batching the drift check across pages, templates for index.md and log.md, renamed or deleted monitored files, sources that are binary or live at external URLs, and the reference implementation.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Build and review interfaces against WCAG 2.2 accessibility guidelines. Covers keyboard navigation, screen readers that read interface content aloud, accessible forms, mobile support, and display preferences, helping identify and fix barriers to using a website or app.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Audit an interface for accessibility issues
  • Add keyboard navigation and focus management
  • Improve screen reader support for forms
wshobson/agents4.1만2026년 10월 19일 업데이트

Review AI-generated code for problems hidden behind successful runs. Check failure handling, resource cleanup, unusual inputs, nonexistent dependencies, and departures from project conventions to identify missing safeguards before merging or accepting the work as complete.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Audit code after an AI generation session
  • Review an AI-generated pull request before merging
  • Investigate brittle code that appears to work
wshobson/agents4.1만2026년 10월 19일 업데이트

Build Apache Airflow workflows for data pipelines and scheduled jobs. The skill guides task dependencies, retries, waiting for conditions, testing, and deployment, with patterns for tasks that can be safely rerun.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Building scheduled data pipelines
  • Designing task order and dependencies
  • Implementing custom tasks and condition checks
wshobson/agents4.1만2026년 10월 19일 업데이트

Plan and carry out an AngularJS to Angular migration, from choosing a rewrite strategy to converting components, services, and routes. Includes a hybrid approach that runs both frameworks together while individual features are migrated.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Planning an AngularJS to Angular migration
  • Moving a large app one feature at a time
  • Converting directives into Angular components
wshobson/agents4.1만2026년 10월 19일 업데이트

Identify software protections that hinder inspection, such as debugger detection and obfuscation that makes code harder to understand. Support authorized binary analysis and CTF security challenges with protection findings, bypass strategies, reports, and analysis scripts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Identify protections in an authorized malware sample
  • Plan analysis of a packed executable
  • Implement debugger detection for a CTF challenge
wshobson/agents4.1만2026년 10월 19일 업데이트

Design and review REST and GraphQL APIs with consistent naming, data structures, error responses, pagination for large result sets, and versioning strategies. Helps teams define shared standards and plan changes that existing clients can adopt gradually.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Designing a new REST or GraphQL API
  • Reviewing API specifications before implementation
  • Establishing shared API design standards
wshobson/agents4.1만2026년 10월 19일 업데이트

wshobson의 스킬 모두 보기

이 스킬의 문제 신고