CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

refactoring-team

Iterative code refactoring through progressive lenses via a worker-reviewer agent team.

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/refactoring-team/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

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

The body is an efficient, actionable orchestration guide: concrete commands, a clear launch sequence with an upfront validation checkpoint and a post-launch monitoring loop, and clean delegation to a well-structured reference bundle. Its few weaknesses — an unexplained STARTER_CHARACTER line, unspecified .refactoring-state location, and indirect navigation to the lens directories — keep individual dimensions at 4 rather than 5.

DimensionReasoningScore

Conciseness

The ~50-line body is lean and instructional throughout: prerequisites snippet, input gathering, a one-line ID command, a placeholder substitution table, and a monitoring rule — no padding and no explanation of concepts Claude already knows. Every token earns its place, though the stray "STARTER_CHARACTER = 💎" line is arguably wasted context.

5 / 5

Actionability

Mostly executable: a concrete env JSON snippet, the command `head -c 3 /dev/urandom | xxd -p | head -c 3`, explicit teammate naming examples, and a precise placeholder substitution table with real linked files. Minor gaps keep it from 5: `STARTER_CHARACTER = 💎` is never explained or used, and the location of `.refactoring-state` is not specified.

4 / 5

Workflow Clarity

Clear sequenced workflow (Prerequisites → Setup → Launch → After Launch → Monitor) with an explicit upfront checkpoint ("Verify the target path exists and tests pass before proceeding") and a monitoring feedback loop (skipped lens → reviewer goes back). Not 5 because there is no inline error-recovery guidance for what happens if tests fail after refactoring, and verification after changes is only delegated via the prompts.

4 / 5

Progressive Disclosure

The body is a genuine overview that delegates bulk content to real, well-organized one-level references (worker-prompt.md, reviewer-prompt.md) backed by a tidy parallel bundle of 23 lens files and 23 matching reviewer guides, all verified to exist. Minor gaps: the lenses/reviewer-guides directories are only reachable through LENSES_DIR/GUIDES_DIR placeholders rather than direct links, and guard-idle-worker.sh is referenced only in frontmatter hooks, leaving navigation slightly less direct than the anchor-5 ideal.

4 / 5

Total

17

/

20

Passed

Description

53%Weight 40%Scale 1-5

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 is concise, specific about its mechanism, and clearly distinguishable from other skills, but it entirely lacks a 'when to use' trigger clause and leans on internal jargon ("progressive lenses") instead of natural user vocabulary. It reads as a clear 'what' with no 'when', which limits its discoverability and completeness scores.

Suggestions

Add an explicit trigger clause, e.g., "Use when the user asks to refactor, clean up, or improve the structure of a codebase, especially when they want thorough, multi-pass improvement."

Replace or supplement jargon like "progressive lenses" with natural vocabulary (e.g., "23 progressive refactoring lenses: formatting, naming, duplication, coupling, error handling, and more") so users can recognize their need from the description alone.

Enumerate 2-3 representative actions or lenses to strengthen specificity (e.g., "renames, extracts methods, removes duplication") without significantly lengthening the description.

DimensionReasoningScore

Specificity

"Iterative code refactoring" names the domain and one core action, and "through progressive lenses via a worker-reviewer agent team" names a concrete mechanism, but no specific refactor actions (e.g., renaming, extracting, removing duplication) are enumerated. Matches anchor 3 (domain and 1-2 concrete actions, not comprehensive) rather than 4, which requires several specific actions.

3 / 5

Completeness

The description clearly answers 'what' (iterative code refactoring through progressive lenses via a worker-reviewer team) but contains no 'Use when...' clause or equivalent trigger guidance, capping completeness at 3 per the judging guidelines. It is not 2 because the 'what' is specific and clear, not vague.

3 / 5

Trigger Term Quality

"code refactoring" is a natural term users would say, but "progressive lenses" and "worker-reviewer agent team" are internal jargon, and common variations like "clean up code", "improve code quality", or "refactor" are absent. Some relevant keywords exist, but synonyms and variations are missing, matching anchor 3.

3 / 5

Distinctiveness Conflict Risk

The "worker-reviewer agent team" and "progressive lenses" mechanism carves out a clear niche distinct from generic refactoring skills, leaving only minor overlap risk with other code-quality skills. Not 5 because "code refactoring" alone could still overlap with simpler refactoring helpers absent the qualifying mechanism.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

saski/arnesto

Path

.agents/skills/refactoring-team/SKILL.md

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.