reseed

Re-derive your knowledge system from first principles when structural drift accumulates. Analyzes dimension incoherence, vocabulary mismatch, boundary dissolution, and template divergence. Preserves all content while restructuring architecture.

Quality

60%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/reseed/SKILL.md

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, actionable multi-phase workflow with strong validation and feedback loops, though it is somewhat long and its progressive-disclosure references point to files that are not present in the bundle.

Suggestions

Tighten repeated framing and collapse the example drift table into a brief schema reference to reduce length without losing guidance.

Resolve the internal inconsistency about kernel primitive count (the body cites 12, 15, and 11 in different places) so the validation steps are unambiguous.

Either include the referenced reference/*.md files in the bundle or note that they are external plugin-provided assets, so the progressive-disclosure pointers resolve to real files.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, tables, and output templates that earn their place, but at ~385 lines it includes repeated framing ('This is NOT starting from scratch', restated invariants) and example drift tables that could be tightened.	2 / 3
Actionability	It provides concrete, executable guidance throughout: exact bash inventory commands, file paths (ops/derivation.md, self/identity.md), specific MCP/CLI fallback chains, and copy-ready report templates.	3 / 3
Workflow Clarity	Seven phases are explicitly sequenced with numbered implementation steps, dedicated validation phases (Phase 4 coherence checks, Phase 7 validation), and a feedback loop ('If any kernel primitive fails, fix it before completing the reseed') for a destructive batch operation.	3 / 3
Progressive Disclosure	References are clearly signaled and grouped (Core, Configuration, Validation) and point one level deep to ${CLAUDE_PLUGIN_ROOT}/reference/*.md, but no reference/ bundle directory exists alongside SKILL.md, so the referenced paths cannot be verified and the body itself carries substantial detail that could live in those files.	2 / 3
	Total	10 / 12 Passed

Description

42%

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 clearly scopes a niche operation and lists concrete actions, but it relies on technical jargon rather than natural trigger terms, omits an explicit 'Use when' clause, and uses second-person voice.

Suggestions

Add an explicit 'Use when ...' clause with natural user-facing triggers (e.g. 'Use when your knowledge base feels misorganized, vocabulary no longer matches how you talk, or notes drift from their templates').

Replace jargon-heavy trigger terms ('dimension incoherence', 'boundary dissolution') with plain-language phrasing users would actually say.

Rewrite in third person ('Re-derives a knowledge system ...') to match the expected voice and avoid the specificity penalty.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('Analyze dimension incoherence, vocabulary mismatch, boundary dissolution, and template divergence'; 'Preserves all content while restructuring architecture'), which would warrant 3, but the second-person voice ('Re-derive your knowledge system') incurs the required specificity penalty of 1.	2 / 3
Completeness	It states clearly what the skill does, but the 'when' guidance is only implied via the clause 'when structural drift accumulates' and there is no explicit 'Use when...' clause, which caps completeness at 2.	2 / 3
Trigger Term Quality	The terms used ('structural drift', 'dimension incoherence', 'boundary dissolution', 'template divergence') are specialized jargon rather than the natural phrasing a user would say when they need this skill, and there are no common-sense variations of those terms.	1 / 3
Distinctiveness Conflict Risk	The niche is specific (restructuring an existing knowledge system via re-derivation) and the listed failure modes are distinctive, making it unlikely to trigger for the wrong skill.	3 / 3
	Total	8 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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	14 / 16 Passed

Repository: agenticnotetaking/arscontexta
Path: skills/reseed/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.