reweave

Update old notes with new connections. The backward pass that /reflect doesn't do. Revisit existing notes that predate newer related content, add connections, sharpen claims, consider splits. Triggers on "/reweave", "/reweave [note]", "update old notes", "backward connections", "revisit notes".

Quality

88%

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

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A methodologically rich, highly actionable skill with a clear phased workflow and concrete commands, templates, and decision tables. Its main weaknesses are conciseness — the five core actions are described three times with motivational padding — and the absence of any progressive disclosure into bundle files for a skill of this length.

Suggestions

Consolidate the three overlapping descriptions of the five reweave actions (the 'What Reweaving Can Do' table, workflow Phases 3-5, and 'The Five Reweave Actions') into a single authoritative section to remove redundancy and trim motivational prose.

Split the large reference material — Enrichment-Triggered Actions, Handoff Mode, and the detailed Five Actions examples — into separate files under references/ and link to them from the overview, enabling progressive disclosure for a skill well over 50 lines.

Move the 'Philosophy' and 'The Network Lives Through Evolution' sections to a reference file or cut them, keeping the main body focused on executable workflow guidance.

Dimension	Reasoning	Score
Conciseness	The ~650-line body restates the same five actions (add/rewrite/sharpen/split/challenge) across three separate sections — the 'What Reweaving Can Do' table, the workflow Phase 3-5, and 'The Five Reweave Actions' — plus motivational prose like 'Every note is a hypothesis. Every reweave is a test.'; not a 1 because it does not explain concepts Claude already knows, but not a 3 due to clear redundancy and philosophy padding.	2 / 3
Actionability	Provides executable commands (find -mtime, grep -rl backlinks, qmd with mkdir lockdir, jq queue advance), concrete markdown templates for proposals/output/handoff, and decision tables mapping findings to actions; not a 2 because the guidance is concrete and largely copy-paste ready, with template placeholders representing justified flexibility.	3 / 3
Workflow Clarity	Five sequenced phases with explicit checkpoints — five quality gates, an interactive approval-before-apply gate, and 'Verify all link targets exist' — give a clear feedback/checklist structure; not a 2 because validation steps are present for the note-modifying operations rather than missing.	3 / 3
Progressive Disclosure	No bundle files exist and the skill is a single monolithic ~650-line file with self-contained sections; content that could be split (Enrichment-Triggered Actions, Handoff Mode, the detailed Five Actions) is inline; not a 1 because internal sectioning and tables are well-organized rather than a disorganized wall of text, but not a 3 because a skill this size provides no one-level-deep reference files.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 concisely states multiple concrete capabilities and pairs them with explicit, natural-language trigger terms. It clearly differentiates itself from the sibling /reflect skill, leaving little ambiguity about when to invoke it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'add connections, sharpen claims, consider splits' — paralleling the score-3 example 'Extract text and tables, fill forms, merge documents'; not a 2 because the actions are specific and enumerated rather than a single domain mention.	3 / 3
Completeness	Explicitly answers what ('Revisit existing notes... add connections, sharpen claims, consider splits') and when ('Triggers on ...') with explicit triggers, matching the score-3 what-AND-when anchor; not a 2 because the 'when' is stated explicitly rather than merely implied.	3 / 3
Trigger Term Quality	Provides natural user phrasings ('update old notes', 'backward connections', 'revisit notes') alongside slash-command triggers, giving good coverage of terms a user would actually say; not a 2 because common variations are present rather than missing.	3 / 3
Distinctiveness Conflict Risk	Carves a clear niche ('The backward pass that /reflect doesn't do') with distinct triggers unlikely to fire for unrelated skills; not a 2 because the explicit /reflect distinction and backward-connection framing separate it from generic note-editing skills.	3 / 3
	Total	12 / 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 (657 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/reweave/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.