reflect

Find connections between notes and update MOCs. Requires semantic judgment to identify genuine relationships. Use after /reduce creates notes, when exploring connections, or when a topic needs synthesis. Triggers on "/reflect", "/reflect [note]", "find connections", "update MOCs", "connect these notes".

Quality

83%

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

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 highly actionable and rigorously sequenced with strong validation gates, but it is overlong and monolithic. Motivational prose inflates the token budget and the absence of any bundle files leaves material that should be one level deep inline.

Suggestions

Trim philosophical and motivational prose (e.g., "The Network Grows Through Judgment", "The graph is not just storage") to reduce tokens without losing the actionable guidance.

Move large reference blocks — the full Output Format template, the RALPH Handoff block, and Pipeline Chaining details — into reference files under ./references/ and link to them from the body.

Keep only the core workflow (Phases 0–6 and Quality Gates) inline, pushing edge-case sections (Split Detection, Conflicting Notes, Orphan Discovery) to a referenced details file.

Dimension	Reasoning	Score
Conciseness	The ~740-line body is mostly useful but padded with motivational prose ("The network IS the knowledge", "The graph is not just storage. It is an external thinking structure") that explains perspective Claude already grasps, fitting the level-2 "mostly efficient but could be tightened" anchor.	2 / 3
Actionability	Provides concrete executable guidance — MCP tool calls (mcp__qmd__deep_search), bash snippets (qmd status, grep counts, jq phase advancement), and a copy-ready relationship-type table — meeting the level-3 anchor for executable commands and specific examples.	3 / 3
Workflow Clarity	Phases 0–6 are clearly sequenced with explicit validation checkpoints (index freshness check, Gates 1–5, link-target verification) and feedback loops (sync-then-continue, fix-and-revalidate), matching the level-3 anchor for batch/destructive operations.	3 / 3
Progressive Disclosure	No bundle files exist and the entire methodology, output templates, handoff format, and pipeline-chaining logic live inline in one monolithic body; content that should be split into references is not separated, fitting the level-2 "could be better organized" anchor.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 states concrete actions, gives explicit "Use when..." guidance with natural trigger terms, and carves out a distinct niche. Its only gap is action specificity, which lists the domain and two actions rather than a fuller enumeration.

Suggestions

Consider listing a few more concrete actions in the opening clause (e.g., evaluate candidate connections, add inline wiki-links, surface split candidates) to reach full action specificity.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ("Find connections between notes and update MOCs") but does not list a comprehensive set of multiple specific actions, stopping short of the level-3 anchor.	2 / 3
Completeness	Explicitly answers both what (find connections, update MOCs, semantic judgment) and when ("Use after /reduce creates notes, when exploring connections, or when a topic needs synthesis") with explicit triggers.	3 / 3
Trigger Term Quality	Includes good coverage of natural terms a user would say — "/reflect", "find connections", "update MOCs", "connect these notes" — matching the level-3 anchor for natural keyword coverage.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (knowledge-graph note connection within a note pipeline) with distinct triggers tied to /reflect and the /reduce predecessor, making conflict with other skills unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (747 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: agenticnotetaking/arscontexta
Path: skill-sources/reflect/SKILL.md
Commit: 2acfd5c

Reviewed: 3 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.