update-knowledge-base

Maintain and update product knowledge base from releases, features, and project changes with optional wiki sync

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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-sequenced, highly actionable workflow with strong validation checkpoints, but it carries verbosity in large placeholder templates and keeps all reference-worthy content inline in a single file rather than splitting it into bundle files.

Suggestions

Move the large markdown templates (new KB entry, update log) and the agent prompt blocks into reference files (e.g. references/templates.md, references/agent-prompts.md) with one-level-deep signaled links to improve progressive disclosure.

Trim the placeholder scaffolding in the inline templates (e.g. repeated [Detail 1]/[Detail 2]/[Detail 3] rows and full frontmatter blocks) to reduce token cost.

Consolidate the overlapping Linear/GitHub scanning instructions between the 'release-scanner' and 'tracker-feature-collector' agent prompts to reduce duplication.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational with little concept-explanation padding, but the large placeholder-heavy markdown templates and somewhat duplicated agent prompts could be tightened, matching the level-2 'mostly efficient but could be tightened' anchor rather than a lean level-3.	2 / 3
Actionability	Provides concrete executable guidance throughout — Glob patterns, gh/CLI commands, named MCP tools (e.g. mcp__claude_ai_Linear_2__list_projects, mcp__claude_ai_Notion__notion-create-pages), a decision menu, and copy-paste-ready templates — matching the level-3 anchor for fully executable, specific guidance.	3 / 3
Workflow Clarity	A clearly sequenced six-phase workflow with explicit checkpoints ('Wait for user approval before making changes', 'NEVER auto-publish'), timestamp/validation pre-flight steps, and error-recovery feedback (present both versions on conflict), satisfying the level-3 anchor for clear sequence with validation and feedback loops.	3 / 3
Progressive Disclosure	No bundle files exist and the skill is a single ~360-line SKILL.md; while it is well-organized with clear headers, substantial content (large templates, full agent prompts, KB-organization spec) that could live in one-level-deep reference files is inline, matching the level-2 'content that should be separate is inline' anchor.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 conveys a clear what and a fairly specific niche, but it omits explicit when-to-use trigger guidance and natural trigger keywords, leaving every dimension at the mid-level anchor.

Suggestions

Append a 'Use when...' clause listing explicit natural triggers, e.g. 'Use when updating the knowledge base after a release, syncing product docs, or when the user says update KB / sync knowledge.'

Surface the natural trigger phrasing ("update knowledge base", "update KB", "sync knowledge", "update product docs") that already appears in the body directly in the description.

Add a concrete action verb or two (e.g. 'audit', 'flag stale entries') to lift specificity from generic 'maintain and update'.

Dimension	Reasoning	Score
Specificity	Names the domain ('product knowledge base') and several sources/actions ('maintain and update', 'from releases, features, and project changes', 'optional wiki sync'), but the verbs are abstract rather than a comprehensive list of concrete actions, matching the level-2 anchor.	2 / 3
Completeness	Clearly states what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance; per the rubric a missing explicit when clause caps completeness at 2.	2 / 3
Trigger Term Quality	Contains relevant natural terms a user might reference ('knowledge base', 'wiki sync'), but lacks the explicit natural trigger phrasing users would say; the common trigger variants live in the body's 'When to Invoke' section rather than the description.	2 / 3
Distinctiveness Conflict Risk	The product-knowledge-base-with-wiki-sync niche is reasonably specific, but it could still overlap with general documentation/update skills and lacks distinct explicit triggers.	2 / 3
	Total	8 / 12 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: huytieu/COG-second-brain
Commit: 5e9851c

Reviewed: 14 days 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.