CtrlK
BlogDocsLog inGet started
Tessl Logo

knowledge-base

Create and maintain a Markdown knowledge base that any AI agent can read, search, and update. Use when the user wants to start a knowledge base, add or update notes, organize docs/notes for an agent or LLM to consume, build an index of notes, or run a cleanup/maintenance pass on an existing MD knowledge base. Triggers include "knowledge base", "KB", "notes for the agent", "index of notes", "second brain", "docs for AI context", "add a note", "update the KB".

77

Quality

98%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is knowledge-base in wonderwhy-er/DesktopCommanderMCP

SKILL.md
Quality
Evals
Security

Quality

Content

96%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 an outstanding instruction-only skill: lean, template-driven, and immediately executable, with well-sequenced workflows and explicit validation loops (existence checks, orphan detection, a final checklist) for the risky batch operations. The only notable weakness is that everything lives in one monolithic file, so content needed only for maintenance passes is always loaded.

Suggestions

Split the maintenance-pass section into a one-level-deep reference file (e.g., references/maintenance.md) and keep a brief inline summary plus a link in SKILL.md, so cleanup-only instructions load on demand rather than on every note edit.

Consider moving the full INDEX.md template into references/ (leaving a minimal skeleton inline) to reduce the always-loaded footprint for the common add-note and update-note flows.

DimensionReasoningScore

Conciseness

The body is dense and prescriptive — folder trees, YAML frontmatter spec, and markdown templates with no explanation of concepts Claude already knows; even justifications are single-clause ('Atomic notes are easier to find, link, and reuse'). Every section earns its place, matching the 'lean and efficient' anchor rather than the 'minor over-explanation' level 4.

5 / 5

Actionability

Fully executable guidance: copy-paste-ready frontmatter, note-body, INDEX.md, and _topic.md templates, plus named tool invocations ('write_file' the note, 'edit_block' both, "Use 'start_search' (ripgrep)", 'get_file_info'). Concrete examples cover the common cases, fitting the top anchor.

5 / 5

Workflow Clarity

Four clearly sequenced workflows (create KB, add note, update note, maintenance pass), with explicit validation for the batch/destructive maintenance pass ('a string existing doesn't mean the file does. Confirm each registry path… with get_file_info') and a closing checklist with per-edit gates ('Every new/changed note has complete, valid frontmatter'). Checkpoints are explicit, not merely present, so this is the anchor-5 pattern rather than level 4.

5 / 5

Progressive Disclosure

A single ~185-line file with no bundle: the maintenance-pass details and the full INDEX.md template are inlined and load into context even for a simple add-note run where they are irrelevant. Structure and section organization are genuinely good, so this sits at the 'minor organization gaps' level 4 rather than level 3 ('could be better organized'), but it falls short of anchor 5's well-signaled one-level-deep references since none exist.

4 / 5

Total

19

/

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.

The description is exemplary: it states concrete capabilities, an explicit 'Use when…' clause with specific scenarios, and a dedicated list of natural trigger phrases including synonyms and the MD extension term. It closely matches the strongest reference examples and has essentially no gaps.

DimensionReasoningScore

Specificity

Lists multiple concrete actions with comprehensive coverage: 'Create and maintain a Markdown knowledge base that any AI agent can read, search, and update', plus 'start a knowledge base, add or update notes, organize docs/notes…, build an index of notes, or run a cleanup/maintenance pass'. Matches the anchor for multiple specific concrete actions with comprehensive coverage; no coverage gaps that would justify a 4.

5 / 5

Completeness

Clearly answers both 'what' (create and maintain an agent-readable, searchable, updatable Markdown KB) and 'when' via an explicit 'Use when the user wants to…' clause enumerating concrete triggering scenarios. This is the anchor-5 pattern (cf. the good overall examples), not the weaker 'when could be more explicit' level 4.

5 / 5

Trigger Term Quality

Explicit natural trigger phrases users would actually say: 'knowledge base', 'KB', 'notes for the agent', 'index of notes', 'second brain', 'docs for AI context', 'add a note', 'update the KB', plus the 'MD' extension term. Comprehensive synonym coverage fits the top anchor rather than the 'a few natural terms missing' level 4 anchor.

5 / 5

Distinctiveness Conflict Risk

Clear niche — a Markdown KB designed for agent consumption via an index — with distinct triggers like 'second brain' and 'docs for AI context'. The qualifier 'for an agent or LLM to consume' keeps even the broadest 'organize docs' phrasing from overlapping with generic note-taking or organization skills, so it fits the 'clear niche, minimal conflict risk' anchor.

5 / 5

Total

20

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 3 missing, 1 suspicious

Warning

Total

14

/

16

Passed

Repository
wonderwhy-er/DesktopCommanderMCP
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.