CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-maintenance

Editing conventions for files under `.claude/skills/**` (markdown style, frontmatter format, SKILL.md vs `references/` split, upstream-vendored skills). Use when creating a new skill, editing any `SKILL.md` or `references/*.md` file, refactoring a skill description, or after adding/removing a skill.

70

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

72%Weight 40%Scale 1-3

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

A strong, actionable conventions skill with concrete rules and clear organization. It loses points on conciseness for restated/reinforced material and on workflow clarity for lacking tight numbered sequences with explicit validation feedback loops.

Suggestions

Remove redundant reinforcement such as the restated em-dash ban and the 'Canonical guidelines (Anthropic)' re-summary, or collapse them into single lines, to tighten conciseness.

Convert the 'After Editing a SKILL.md Body' and 'Validating a skill change' sections into explicit numbered workflows with validation checkpoints (e.g., validate -> if mismatch -> fix -> re-validate) to raise workflow clarity.

Where rules restate each other across sections, cross-reference a single source of truth instead of duplicating the explanation.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes Claude's competence on repo-local conventions Claude would not know, but includes restating/reinforcement ('This line restates it because they slip in through copy-paste and autocorrect') and a 'Canonical guidelines (Anthropic)' section that re-states upstream guidance, so it could be tightened.

2 / 3

Actionability

Concrete, specific, executable rules (wrap at 100 chars, ASCII only, folded >- scalar, 1024-char ceiling, name <= 64), a worked YAML example, and a concrete validation procedure (prompt an opus subagent with a trigger phrase and confirm the skill loads).

3 / 3

Workflow Clarity

Checklists and a validation procedure are present ('After Editing a SKILL.md Body' decision list, 'When to refactor', 'Validating a skill change'), but they are prose/bullet form rather than a numbered sequence with explicit validate->fix->retry checkpoints and error-recovery feedback loops.

2 / 3

Progressive Disclosure

Well-organized into clearly headed sections (Markdown style, Frontmatter, SKILL.md vs references/, upstream skills, Validation) with easy navigation and no nested-reference chains; as a single coherent conventions doc it is appropriately self-contained with no bundle files needed.

3 / 3

Total

10

/

12

Passed

Description

100%Weight 40%Scale 1-3

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: third-person voice, explicit WHAT + 'Use when' WHEN structure, multiple concrete actions, and natural maintainer-facing triggers scoped to a clear niche. No marketing fluff or hedging.

DimensionReasoningScore

Specificity

Lists multiple concrete actions/topics (markdown style, frontmatter format, SKILL.md vs references/ split, upstream-vendored skills) and a concrete action list (creating a skill, editing SKILL.md or references/*.md, refactoring a description, adding/removing a skill), matching the 'multiple specific concrete actions' anchor.

3 / 3

Completeness

Clearly answers WHAT ('Editing conventions for files under .claude/skills/** ...') and WHEN via an explicit 'Use when...' clause enumerating concrete triggers, satisfying the top anchor.

3 / 3

Trigger Term Quality

Triggers like 'creating a new skill', 'editing any SKILL.md or references/*.md file', 'refactoring a skill description', and 'after adding/removing a skill' are natural phrasings a maintainer would type, giving good coverage; the .claude/skills/** glob adds scoping without crowding out natural terms.

3 / 3

Distinctiveness Conflict Risk

Scoped narrowly to .claude/skills/** with triggers specific to skill files, giving a clear niche unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
SRombauts/SQLiteCpp
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.