CtrlK
BlogDocsLog inGet started
Tessl Logo

repo-visuals-retro

Retrospective meta-skill for the `repo-visuals` skill. Reads accumulated evaluation logs from past runs, spots patterns (recurring low-score criteria, repeated iteration failures, unsatisfied requests), consults other expert skills (skill-creator, frontend-design, etc.) where relevant, and proposes concrete edits to `repo-visuals/SKILL.md` as a reviewable diff. Runs on-demand, not per run.

69

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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 tight, well-organized meta-skill with concrete actionable guidance, a clearly sequenced workflow gated by an explicit user-approval checkpoint, and clean section-based navigation with no need for external references.

DimensionReasoningScore

Conciseness

The body is lean and well-sectioned (When to invoke, Inputs, Workflow, Outputs, What this skill does NOT do) and avoids explaining concepts Claude already knows; every section earns its place, matching the 'lean and efficient; assumes Claude's competence' anchor rather than the padded 2.

3 / 3

Actionability

Gives concrete, specific guidance — exact paths like './evaluations/runs/processed/', per-skill instructions ('Feed it the final HTML + screenshots from low-scoring runs; ask for specific design-rule violations'), and a worked diff example; per the instruction-only scoring note, the absence of code is not penalized because the guidance is actionable.

3 / 3

Workflow Clarity

Five clearly numbered steps form a clean sequence with an explicit validation checkpoint ('Wait for user approval before applying' / 'On user approval'), matching the 'clear sequence with explicit validation steps' anchor; not a 2 because the approval gate is an explicit checkpoint rather than an implicit one.

3 / 3

Progressive Disclosure

With no bundle files present, the single SKILL.md is organized into clear, navigable sections with no nested references — only input-path mentions — satisfying the 'well-organized sections, no need for external references' case for a self-contained skill.

3 / 3

Total

12

/

12

Passed

Description

67%

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 conveys a specific, distinctive niche with concrete actions, but its trigger guidance is implicit rather than an explicit 'Use when...' clause and its keywords skew technical over natural user language.

Suggestions

Add an explicit 'Use when...' trigger clause naming natural user phrasings (e.g., 'Use when the user asks to review or improve repo-visuals after several runs, do a retro, or analyze past evaluation results').

Soften jargon toward terms users actually say — pair 'retrospective meta-skill' with plain-language triggers like 'retro', 'review past runs', or 'improve the skill based on logged evaluations'.

Move the 'Runs on-demand, not per run' timing note into a clearer when-to-use statement so the 'when' is explicit rather than implied.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Reads accumulated evaluation logs', 'spots patterns (recurring low-score criteria, repeated iteration failures, unsatisfied requests)', 'consults other expert skills', 'proposes concrete edits ... as a reviewable diff' — matching the 'multiple specific concrete actions' anchor; not a 2 because the actions are comprehensive rather than partial.

3 / 3

Completeness

The 'what' is explicit, but 'when' is only the weak temporal clause 'Runs on-demand, not per run' with no 'Use when...' trigger, so per the guidelines completeness is capped at 2 rather than reaching the explicit-both anchor of 3.

2 / 3

Trigger Term Quality

Contains relevant keywords ('retrospective', 'patterns', 'evaluation logs') but leans on technical jargon ('meta-skill', 'reviewable diff') and omits the natural phrasings a user would actually say ('do a retro', 'review past runs'), matching the 'some relevant keywords but missing common variations' anchor rather than the full-coverage 3.

2 / 3

Distinctiveness Conflict Risk

Occupies a clear, narrow niche as a retrospective meta-skill specifically for the `repo-visuals` skill, making it unlikely to trigger for or conflict with unrelated skills; not a 2 because the scoping to one named sibling skill is unambiguous.

3 / 3

Total

10

/

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
livlign/claude-skills
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.