CtrlK
BlogDocsLog inGet started
Tessl Logo

wiki-ingest

Ingest any source into the Obsidian wiki by distilling its knowledge into interconnected wiki pages. Handles structured documents (PDFs, markdown, articles, papers, notes, folders), raw/unstructured text (chat exports, conversation logs, Slack/Discord threads, meeting transcripts, CSV/JSON data, journal entries, browser bookmarks, email archives, text dumps), AND web URLs. Use whenever the user wants to add new sources to their wiki: "add this to the wiki", "process these docs", "ingest this folder", "ingest this data", "process this export/logs", "import my chat history from X", "/ingest-url <url>", "add this URL", "save this page", or pastes a URL and says "add this" / "save this to my wiki". Also triggers when the user drops a file, or for raw mode: "process my drafts", "promote my raw pages", or any reference to the _raw/ staging directory. This is the general catch-all ingest skill for any document, text, or URL source not covered by a more specific ingest skill (claude-history-ingest, etc.).

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

73%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured, highly actionable ingest workflow with explicit guards, validation, fallbacks, and a checklist, and it makes good one-level-deep use of three real reference files. Its main weakness is conciseness — the length and several verbose procedural sections could be trimmed without losing clarity.

Suggestions

Tighten verbose sections — the _raw/ move-safety/source-inheritance rules and the academic-paper PyMuPDF extraction recipe each run long and could be condensed or moved to a reference file to improve token efficiency.

Consolidate the repeated GUARD-pattern framing across optional steps into a single shared convention note so each step can drop the boilerplate.

Consider extracting the academic-papers extraction branch (Step 1) into its own reference file alongside url-sources.md and pageindex.md, since it is already a large specialized procedure.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes Claude's competence (no explaining what PDF/CSV/markdown are), but the ~540-line body contains padded spots — repeated GUARD framing, verbose _raw/ move-safety and source-inheritance rules, and detailed academic-paper extraction mechanics — that could be tightened, matching the mostly-efficient-but-could-be-tighter anchor.

3 / 5

Actionability

Provides concrete executable bash commands (cache-check, ast-extract, batch-plan), real JSON schemas, frontmatter templates, and platform-specific fallbacks (sha256sum/shasum); minor gaps come from offloading several definitions (config resolution, templates, confidence formula, typed relationships) to an external llm-wiki/SKILL.md file.

4 / 5

Workflow Clarity

Clear Steps 0–8 sequence with explicit GUARDs gating optional steps, validation/feedback loops (cache-check skip logic, PageIndex and QMD fallbacks, batch subagent dispatch), explicit move-safety rules for the batch _raw/ operation, and a final Quality Checklist — matching the explicit-validation-and-feedback-loops anchor.

5 / 5

Progressive Disclosure

Points to three real one-level-deep reference files (url-sources.md, pageindex.md, ingest-prompts.md), all present and clearly signaled with 'Read X and follow it'; minor gaps because sizable inlined material (academic-paper extraction, AST-output handling) could arguably live in its own reference file.

4 / 5

Total

16

/

20

Passed

Description

96%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is comprehensive, concrete, and rich with natural trigger phrases, clearly answering both what the skill does and when to use it in third person. Its only weakness is the self-described 'catch-all' positioning, which slightly raises overlap risk with more specific sibling ingest skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'distilling its knowledge into interconnected wiki pages' — across an enumerated, comprehensive set of source types (structured documents, raw/unstructured text, web URLs), matching the comprehensive-coverage anchor.

5 / 5

Completeness

Explicitly answers both 'what' (distills sources into interconnected wiki pages; handles structured/unstructured/URL sources) and 'when' ('Use whenever the user wants to add new sources to their wiki' with concrete trigger phrases and additional trigger scenarios), matching the both-what-and-when anchor.

5 / 5

Trigger Term Quality

Extensive natural trigger phrases users would actually say ('add this to the wiki', 'process these docs', 'ingest this folder', 'import my chat history from X', '/ingest-url <url>', 'save this page') with synonyms and the _raw/ directory reference, matching the comprehensive-synonyms anchor.

5 / 5

Distinctiveness Conflict Risk

Has a clear niche with distinct triggers and explicitly disambiguates from sibling skills ('not covered by a more specific ingest skill (claude-history-ingest, etc.)'); the 'general catch-all ingest skill' framing introduces minor overlap risk with those related ingest skills, keeping it just below the minimal-conflict anchor.

4 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (559 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
Ar9av/obsidian-wiki
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.