Skip to content
Skills Library
AI & agents · Review & audit

validate

/validate

This skill should be used when the user asks to "validate workspace", "check knowledge integrity", "run validation", "check for broken links", or "verify memories before promoting".

Repository
engy ↗
Licence
MIT
Last repository change
26.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 26.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

This skill should be used when the user asks to "validate workspace", "check knowledge integrity", "run validation", "check for broken links", or "verify memories before promoting".

Triggers from the description

validate workspacecheck knowledge integrityrun validationcheck for broken linksverify memories before promoting
Original author description

This skill should be used when the user asks to "validate workspace", "check knowledge integrity", "run validation", "check for broken links", or "verify memories before promoting".

How it works

  1. When to Use
  2. Process
  3. Output Format
  4. Key Principles
  5. Flow Position
Original SKILL.md headings · 86 lines, 472 words
SKILL.md preview
---
name: validate
description: This skill should be used when the user asks to "validate workspace", "check knowledge integrity", "run validation", "check for broken links", or "verify memories before promoting".
---

# Validate Workspace

Runs a comprehensive set of integrity checks on the workspace knowledge files and reports findings grouped by severity.

## When to Use

- Before promoting fleeting memories to permanent
- After a bulk import or reorganization
- Periodically as part of knowledge hygiene
- When search is returning unexpected results

## Process

### Step 1: Identify Workspace

Use `listWorkspaces` to find the target workspace. If the user specified one, match by name or slug.

### Step 2: Run Validation

Call the `validateWorkspace` MCP tool:

```
validateWorkspace({ workspaceId: <id> })
```

This runs all checks server-side:

- **Broken links** — every `linkedMemories` entry and `sources[]` reference must exist on disk. **Note:** broken-link checking covers DB-tracked `linkedMemories` and `sources` frontmatter only. Inline markdown links in document bodies are not checked.
- **Schema compliance** — memory files in `memory/{subtype}/` must have `title` and `subtype` frontmatter
- **Duplicate IDs** — same `filePath` cannot appear twice in `permanentMemories`
- **Orphaned content** — DB rows with no matching file on disk
- **Lifecycle consistency** — promoted fleeting memories must have a valid `promotedFromId`
- **Stale memory** — permanent memories whose `supersededById` points to a record that itself has been superseded (multi-hop stale chain)
- **Missing sources** — permanent memories whose `sources[]` array references paths that do not exist under `memory/sources/` or `memory/references/`
- **Commit-message conformance** — commits touching `memory/` should follow `memory(<op>):` convention
- **Index status** — files with `needsEmbedding > 0` are reported as awaiting embedding

### Step 3: Present Findings

Format the report by severity:

```
Workspace Validation: <workspace-name>

ERRORS (must fix)
  [broken-links] memory/facts/001.md → linkedMemory "memory/patterns/missing.md" not found
  [orphaned-content] memory/decisions/old.md — in DB but not on disk

WARNINGS (should fix)
  [schema-compliance] memory/insights/202501010042-insight.md — missing field: subtype
  [lifecycle-consistency] Fleeting memory id=17 promoted but missing promotedFromId

INFO
  [index-status] 3 file(s) awaiting embedding — run /engy:reindex to generate vectors
  [commit-message-conformance] Commit "add memory file" touches memory/ but skips convention

Summary: 2 errors, 2 warnings, 2 infos
```

### Step 4: Recommend Actions

For each severity group, suggest next steps:

- **Errors** — must be resolved before the knowledge graph is trustworthy. Fix links, re-index, delete orphaned DB rows, or restore missing files.
- **Warnings** — should be fixed. Add missing frontmatter fields, correct lifecycle references.
- **Info** — optional. Run `/engy:reindex` if embedding lag is reported.

If there are no findings: "Workspace is clean — no integrity issues found."

## Output Format

Findings grouped by severity (errors first), followed by a one-line summary.
Each finding includes: `[check-name] <path-if-applicable> — <message>`.

## Key Principles

- Read-only — validate never modifies state.
- Severity grouping — errors must be fixed; warnings are advisory.

## Flow Position

**Typical trigger:** user wants to verify knowledge graph integrity before promoting memories or after a bulk import.

**Next step:** address errors first, then run `/engy:reindex` if index status flagged embedding lag.

Versions

RepositoryScoreLicence
This page · zanderadam/engy100MIT
DiogoHSM/driver100MIT
boshu2/agentops100Apache-2.0
RemiPelloux/kill-my-idea100MIT
lalitmaganti/syntaqlite100Apache-2.0
hirogakatageri/hirokata-claude-marketplace100MIT
fabricio21x/fbs100MIT
Kiran-980/1ml100MIT
whawkinsiv/solo-founder-skills100MIT

Database snapshot: 13.11.2026 · package version b52b29ea1117 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100claude-docs-validate
    Check the health and freshness of locally-stored Claude documentation. Use this skill when the user asks about documentation health, broken links, stale docs, freshness checks, or wants to validate that their local install is up-to-date and all URLs are reachable. Triggers on:…
  • 100ctx-lint
    Validate @-imports across all ctx AGENTS.md files. Finds broken links, missing end markers. Supports auto-fix for trivial issues. Triggers on "/ctx-lint", "validate imports", "check AGENTS.md", "what broke in context".
  • 100mem0-scope
    Views or changes the default memory scope (project, session, or global) used when saving and searching memories. Use when the user wants to control whether memories are scoped to this repo, this run, or shared across all their projects.
  • 84broken-links
    Find and fix broken links on a website or in a codebase. Use when the user asks to "check broken links", "find dead links", "fix 404s", "link checker", "broken link audit", "find dead URLs", or wants to identify and repair links that lead to non-existent pages.
  • 100knowledge-health
    Run a read-only structural health check on a cogni-knowledge base — page/link/schema integrity plus entries-count and claim drift for the bound wiki. Use this skill whenever the user says 'check knowledge health', 'knowledge health', 'is my knowledge base healthy', 'audit the…
  • 100verify
    This skill should be used when the user asks to "verify protocols", "check consistency before commit", "validate definitions", "run pre-commit checks", "verify soundness", or wants to ensure epistemic protocol quality. Invoke explicitly with /verify for pre-commit validation.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.