Name: wiki-init
Rating: 68 (1 reviews)
Author: tdg-ninja

wiki-init

One-time, guided setup of a standalone LLM-maintained wiki — a Karpathy "LLM Wiki" style knowledge base for a problem domain and your general architecture best practices. Scaffolds an external wiki vault (its own git repo) with /ingest, /query, /lint commands and a conventions doc. Use when a developer wants to start, create, bootstrap, or initialize a wiki / second-brain / knowledge base to understand a problem space before building. The front of the Human Loop's Understanding phase.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

The canonical home for this skill is wiki-init in tdg-ninja/context-specs-factory-ai

Quality

Content

76%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, actionable guided flow with strong progressive disclosure (all referenced files exist) and excellent validation/feedback checkpoints. Its main weakness is verbosity in the philosophy and precondition sections that restates the same boundary conditions multiple times.

Suggestions

Condense the P1–P8 philosophy list to the disciplines that are not already enforced by the 'Hard nevers' or the command behaviors; several points (P1, P3) are restated verbatim later.

The 'Preconditions' and 'Hard nevers' sections overlap heavily on 'never write into the app codebase / own git repo / don't scan the codebase' — merge to remove triplication.

Give the exact git init + first-commit command sequence in Step 4 rather than only describing it, to make the one slightly hand-wavy step fully copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but the P1–P8 philosophy block and repeated restatements of 'outside the app codebase / its own git repo' add length Claude does not need; could be tightened without losing the load-bearing disciplines.	3 / 5
Actionability	Concrete and executable guidance throughout — named directory tree, exact asset templates to render, specific files to write, and git init/commit steps — with only minor gaps (no exact command for the git init/commit sequence).	4 / 5
Workflow Clarity	Clear sequenced Steps 0–5 with explicit confirm/validate checkpoints, a plan-pass approval gate (Step 2), confirm-before-commit (Step 4), and feedback-loop narration mandated for every disk/git step.	5 / 5
Progressive Disclosure	Clear overview pointing to one-level-deep references (references/llm-wiki-pattern.md, hardening-lessons.md, domain-discovery.md) and assets/ templates that all exist in the bundle, each clearly signaled with what to read it for and when.	5 / 5
	Total	17 / 20 Passed

Description

88%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 strong: it clearly states what the skill does, gives concrete actions, and provides explicit natural-language trigger phrases covering synonyms like 'second-brain' and 'knowledge base'. Its only weakness is mild verbosity and a few near-synonym triggers that could be tighter.

Suggestions

Trim the prose between 'Karpathy "LLM Wiki" style' and 'Scaffolds...' — the framing paragraph adds length without adding trigger value.

Consider adding the file/extension or noun synonyms a user might say (e.g. 'Obsidian vault', 'notes') to further widen trigger recall.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — scaffolds an external wiki vault, drops in /ingest, /query, /lint commands, conventions doc, own git repo — with minor gaps in coverage of the full setup surface.	4 / 5
Completeness	Explicitly answers both what (scaffolds an external wiki vault with commands and conventions doc) and when ('Use when a developer wants to start, create, bootstrap, or initialize a wiki...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including 'start, create, bootstrap, or initialize a wiki / second-brain / knowledge base' and 'to understand a problem space before building', the phrases a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (standalone LLM-maintained wiki, Understanding phase) that is mostly distinct; minor overlap risk with other knowledge-base or note skills, but the 'external wiki vault / own git repo' framing narrows it well.	4 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tdg-ninja/context-specs-claude-code
Path: skills/human-loop/wiki-init/SKILL.md
Commit: 3a7a725

Reviewed: about 19 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.