CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gitnexus-refactoring

Use when the user wants to rename, extract, split, move, or restructure code safely. Examples: "Rename this function", "Extract this into a module", "Refactor this class", "Move this to a separate file"

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

77%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.

Highly actionable and exceptionally well-sequenced content, with concrete tool calls, explicit validation gates for a destructive operation, and per-error recovery guidance — among the clearest safety workflows for refactoring. Its weaknesses are repetition of the repo-binding rule and the absence of any progressive disclosure: edge-case detail (error table, token lifecycle, semantic-layer internals) that belongs in a reference file is inlined in SKILL.md.

Suggestions

Move the 17-row rename error-recovery table and the plan_token lifecycle details (expiry, eviction at 16 plans/64 MiB, read-only mode) into a references/RENAME-ERRORS.md file, linked one level deep from the rename section, keeping only the 3-4 most common error codes inline.

State the repo-binding rule once in 'Bind the repository first' and reference it from the checklists with a short '- [ ] Bind repo (see above)' item instead of restating the full guidance in every checklist and the risk table.

Trim the semantic-layer paragraph ('Rename uses the indexed graph...') to the operationally relevant facts (fail-closed behavior, no regex fallback, coverage scope), dropping explanatory prose about providers and declaration families that a caller does not act on.

DimensionReasoningScore

Conciseness

The body is operationally dense and explains no basic concepts, but repo-binding guidance is restated in roughly six places (intro, workflow, every checklist, risk table, example), and roughly 100 lines cover rare edge cases (plan eviction at 16 plans/64 MiB, duplicate_file/missing_snapshot) that could be tightened or offloaded. Not 4: the repetition and edge-case depth go beyond minor trim instances; not 2: nearly everything is non-obvious, tool-specific fact rather than padding.

3 / 5

Actionability

Calls are copy-paste ready with exact parameters and expected outputs ("rename({symbol_name: "validateUser", new_name: "authenticateUser", repo: "my-app", dry_run: true})"), plus a concrete cypher query and a full worked example. Not 4: specific examples cover the common rename case end-to-end including apply and verification.

5 / 5

Workflow Clarity

A numbered workflow with per-task checklists, explicit validation gates (preview with dry_run, confirm bound repository, apply only with plan_token, detect_changes, run tests), and a 17-row error-recovery table with per-code next steps. Feedback loops for the destructive write operation are explicit and thorough. Not 4: checkpoints and recovery paths are explicit, not merely present.

5 / 5

Progressive Disclosure

The file is well-sectioned (When to Use, Workflow, Checklists, Tools, Risk Rules, Example), but there are no bundle files at all — content that clearly belongs in a one-level-deep reference (the full error-code recovery table, rename semantic-internals, token lifecycle and read-only behavior) is inlined. Not 4: no references exist and ~100 lines of edge-case API detail sit in the main file; not 2: structure is strong, not minimal.

3 / 5

Total

16

/

20

Passed

Description

88%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.

A strong description: concrete action verbs, explicit 'Use when...' triggers, and verbatim example phrases users would naturally say. The only gap is the absence of any differentiator (e.g., GitNexus or the indexed-graph approach) that would set it apart from a generic refactoring skill.

DimensionReasoningScore

Specificity

"rename, extract, split, move, or restructure code safely" lists multiple specific concrete actions with comprehensive coverage of the refactoring domain. Not 4: the action list has no meaningful coverage gaps for this task type.

5 / 5

Completeness

Explicitly answers both what (rename/extract/split/move/restructure code safely) and when, opening with "Use when the user wants to..." followed by concrete example trigger phrases. Not 4: the 'when' clause is fully explicit with concrete triggers, matching the anchor-5 example pattern.

5 / 5

Trigger Term Quality

Natural user phrases like "Rename this function", "Extract this into a module", and "Refactor this class" are quoted verbatim, giving good keyword coverage. Not 5: common variations such as "inline", "simplify", or "clean up this code" are missing, so coverage falls short of comprehensive synonyms.

4 / 5

Distinctiveness Conflict Risk

The trigger phrases carve out a clear refactoring niche with low conflict risk against unrelated skills. Not 5: the description never mentions GitNexus or graph/index-based operation, so it overlaps fully with any generic 'refactoring' skill and cannot be distinguished from one on description alone.

4 / 5

Total

18

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

abhigyanpatwari/GitNexus

Path

gitnexus-claude-plugin/skills/gitnexus-refactoring/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.