CtrlK
BlogDocsLog inGet started
Tessl Logo

review-changes

Perform a structured code review using change detection and impact

57

Quality

65%

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 ./skills/review-changes/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 content is a tight, highly actionable workflow with concrete tool calls and a defined output format, well-organized for a simple read-only analysis skill. Its main gap is the absence of an explicit validation/checkpoint step in the review sequence.

DimensionReasoningScore

Conciseness

The body is lean, names concrete tools, and avoids explaining concepts Claude already knows; only the opening "Perform a thorough, risk-aware code review using the knowledge graph" restates the description and could be trimmed, fitting the efficient-with-minor-over-explanation anchor.

4 / 5

Actionability

Each step names a concrete, parameterized tool call (e.g., `query_graph_tool` with pattern="tests_for", `get_minimal_context_tool(task=...)`) and the output format is specified, matching the fully executable, copy-paste-ready anchor.

5 / 5

Workflow Clarity

Steps 1–5 are clearly sequenced with a defined output format, but there is no explicit validation checkpoint or feedback loop confirming the analysis is complete; as a read-only (non-destructive) skill the destructive/batch cap does not apply, fitting the clear-sequence-with-minor-validation-gaps anchor.

4 / 5

Progressive Disclosure

The skill is under 50 lines, has no external references (no references/scripts/assets bundle files), and is organized into clear sections (Steps, Output Format, Token Efficiency Rules), qualifying for the simple-skill exception at the top anchor.

5 / 5

Total

18

/

20

Passed

Description

45%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 clearly conveys the skill's purpose but lacks any trigger guidance and relies on abstract capabilities rather than concrete actions or natural trigger phrases. Adding a "Use when…" clause with concrete triggers would materially raise its completeness and trigger-term scores.

Suggestions

Append a "Use when…" trigger clause naming concrete natural phrases users would say (e.g., "Use when reviewing a staged diff, checking change risk, or auditing impact of a pull request").

Replace abstract terms ("change detection", "impact") with concrete actions the skill performs (e.g., "detects changed functions, scores their risk, and traces affected execution paths").

Add a distinguishing keyword or file-type/trigger anchor (e.g., "knowledge-graph-based code review") to reduce overlap with generic review skills.

DimensionReasoningScore

Specificity

It names the domain ("structured code review") and references "change detection" and "impact", but these are abstract concepts rather than concrete actions, matching the anchor where actions are minimal or generic.

2 / 5

Completeness

It clearly states the "what" but provides no "when" or explicit trigger guidance, and the missing "Use when…" clause caps completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

"code review" is a natural user term, but "change detection" and "impact" lean technical and there are no synonyms, variations, or "Use when…" trigger phrases, fitting the anchor for some relevant keywords with missing variations.

3 / 5

Distinctiveness Conflict Risk

The "change detection and impact" qualifier adds some specificity, but "code review" alone is broad and could overlap with other review skills, fitting the anchor for somewhat specific but still overlapping.

3 / 5

Total

11

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
tirth8205/code-review-graph
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.