cs-wiki-ingestor

Dispatched sub-agent that ingests a new source into an LLM Wiki vault. Reads the source, proposes TL;DR and key claims, identifies which entity/concept/synthesis pages will be touched, flags contradictions with existing pages, and — after user confirmation — writes the source summary, updates cross-references across 5-15 pages, regenerates the index, and appends a standardized log entry. Spawn when the user says "ingest this", "add this paper/article/book to the wiki", or drops a file into raw/.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%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.

A well-structured, highly actionable ingest workflow with concrete commands, a user-confirmation gate, and a clear stop-condition list. The main gaps are minor: a Rules section that partially restates the workflow, no explicit post-write verification for this batch operation, and external references that depend on a sibling skill.

Suggestions

Add an explicit post-write verification step to the workflow (e.g., re-read the touched pages and confirm the regenerated index lists them), so the batch operation has a feedback loop and workflow_clarity can reach 5.

Dedupe the Rules section against the Workflow steps — keep it as a terse invariant list ('raw/ immutable', 'min 5 touches', 'cite aggressively') and drop items already stated as numbered steps, to tighten conciseness.

If the ingest-workflow reference and templates are core to this skill, bundle them under a local references/ directory with clickable relative links; otherwise make the dependency on the llm-wiki skill explicit in Inputs so navigation is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, but the Rules section restates several workflow points ('raw/ is immutable', 'Discuss before writing', 'Flag contradictions', 'Update updated: frontmatter') that could be trimmed. Not a 5 because of this minor redundancy; not a 3 because no concepts Claude already knows are over-explained.	4 / 5
Actionability	Provides copy-paste-ready commands (ingest_source.py --vault . --source <path> --json, update_index.py --vault ., append_log.py --vault . --op ingest …), explicit required frontmatter fields, and concrete template usage — fully executable guidance covering the common cases.	5 / 5
Workflow Clarity	A clear 10-step sequence with an explicit pre-write checkpoint ('Wait for the user to confirm or redirect before writing') and a Red flags stop-list. Not a 5 because this batch operation (5-15 page touches) lacks an explicit post-write verification step that all writes and the regenerated index are consistent.	4 / 5
Progressive Disclosure	The workflow opens by clearly signaling a one-level-deep reference ('Follow …/references/ingest-workflow.md in the llm-wiki skill. Summary:') and the body is well sectioned. Not a 5 because the referenced files and templates live in a sibling skill rather than a bundled references/ directory, so navigation depends on that other skill being present.	4 / 5
	Total	17 / 20 Passed

Description

100%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.

A strong, third-person description that comprehensively enumerates concrete actions and pairs them with explicit, natural trigger phrases. It cleanly answers both what the skill does and when to invoke it with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions in third person ('Reads the source, proposes TL;DR and key claims, identifies which entity/concept/synthesis pages will be touched, flags contradictions… writes the source summary, updates cross-references across 5-15 pages, regenerates the index, and appends a standardized log entry'), giving comprehensive coverage of what the agent does.	5 / 5
Completeness	Explicitly answers both what (the full ingest pipeline) and when ('Spawn when the user says…') with concrete trigger phrases, matching the anchor for clearly answering both what AND when.	5 / 5
Trigger Term Quality	Includes natural phrases users would actually say with synonyms — 'ingest this', 'add this paper/article/book to the wiki', and 'drops a file into raw/' — giving comprehensive coverage of natural trigger terms.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (ingesting sources into an LLM Wiki vault) with distinct, specific triggers, so overlap with other skills is minimal.	5 / 5
	Total	20 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/cs-wiki-ingestor/SKILL.md
Commit: 19392f7

Reviewed: ~3 hours ago

Table of Contents

Discovery Implementation Validation

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.