upgrade

Apply plugin knowledge base updates to an existing generated system. Consults the Ars Contexta research graph for methodology improvements, proposes skill upgrades with research justification. Never auto-implements. Triggers on "/upgrade", "upgrade skills", "check for improvements", "update methodology".

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 thorough, well-sequenced meta-skill with strong actionability and validation checkpoints, but the single-file presentation is longer than it needs to be: a conceptual rationale section, repeated invariant restatements, and inline material that could move to reference files limit conciseness and progressive disclosure.

Suggestions

Move the 'Why Consultation, Not Hashing' rationale and any repeated 'never auto-implements' restatements into a single consolidated invariant note to tighten conciseness.

Split large inline material — output-format templates, the edge-case catalog, and the knowledge-base-tier reference table — into one-level-deep reference files (e.g. references/templates.md, references/edge-cases.md) to improve progressive disclosure for this 380-line skill.

Consider trimming or relocating the long present-plan and final-report template blocks so the core 6-step workflow reads leaner in the main SKILL.md.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete bash, tables, and templates, but the ~380-line body includes a conceptual 'Why Consultation, Not Hashing' rationale and restates 'never auto-implements' across Step 4, the INVARIANT section, and edge cases, so it is not the lean 3-anchor and not the padded 1-anchor.	2 / 3
Actionability	Provides executable bash (inventory loops, archive cp, validation grep), named file paths, a finding-classification taxonomy, and copy-paste output templates; per the instruction-skill note, the reasoning steps carry concrete actionable guidance, matching the 3-anchor rather than the pseudocode/incomplete 2-anchor.	3 / 3
Workflow Clarity	A clear 6-step sequence culminates in explicit Step 6 validation (kernel, context-file, vocabulary, pipeline-compat checks) with a feedback loop (validation fail -> warning plus rollback archive) and an approval gate, satisfying the 3-anchor's explicit validation and checkpoints rather than the 2-anchor's checkpoint gaps.	3 / 3
Progressive Disclosure	Internally well-organized with headers, tables, and code, but it is a monolithic 380-line single file with no bundle/reference files, and content such as output templates, the edge-case catalog, and the knowledge-base-tier reference could be split out, fitting the 2-anchor rather than the 3-anchor's one-level-deep references.	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 well-crafted description that is third-person, names several concrete actions, supplies an explicit trigger clause, and carves out a distinct niche. No meaningful weakness across the four dimensions; voice and trigger guidance both meet the rubric's top anchors.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete actions ('Apply plugin knowledge base updates', 'Consults the Ars Contexta research graph', 'proposes skill upgrades with research justification', 'Never auto-implements'), matching the 3-anchor for multiple specific concrete actions rather than the 2-anchor's domain-plus-some-actions.	3 / 3
Completeness	Explicitly answers what (first three sentences of capabilities) and when ('Triggers on ...'), satisfying the 3-anchor for both with explicit triggers rather than the 2-anchor's implied-only when.	3 / 3
Trigger Term Quality	Provides four trigger phrases — '/upgrade', 'upgrade skills', 'check for improvements', 'update methodology' — most of which a user would naturally say, giving good coverage beyond the 2-anchor's sparser example.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (upgrading generated skills via knowledge-base consultation) with distinct triggers unlikely to fire for unrelated skills, matching the 3-anchor rather than the 2-anchor's overlap-prone phrasing.	3 / 3
	Total	12 / 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/upgrade/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.