CtrlK
BlogDocsLog inGet started
Tessl Logo

codebase-walkthrough

Deep codebase walkthrough before implementation — trace the full flow, explain architecture, and build understanding.

58

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/codebase-walkthrough/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 well-structured, actionable walkthrough workflow with strong sequencing and explicit verification checkpoints. Its main weakness is conciseness — motivational framing and repeated diagram-rendering instructions inflate the token count without adding guidance Claude couldn't infer.

Suggestions

Trim motivational restatements (e.g. 'they are not obvious to someone learning the codebase', 'Visual learners need the map before the details') that restate the surrounding instruction.

Consolidate the rendering instructions: Step 2 already gives the full procedure, so Step 7 and the callout can reference it instead of repeating the Read-the-PNG/ASCII-fallback details.

Move the detailed diagram-rendering command sequence into a bundled reference file and link to it, keeping SKILL.md as an overview pointer.

DimensionReasoningScore

Conciseness

The body is mostly efficient and assumes Claude's competence (it skips explaining what a service or diagram is), but several passages are padded with motivational framing ('they are not obvious to someone learning the codebase', 'Visual learners need the map before the details') and repeated diagram-rendering instructions across Steps 2, 7, and the callout that could be tightened.

3 / 5

Actionability

Provides concrete, executable guidance — specific recall/retain snippets, exact CLI commands ('devflow visualizations render <path>.excalidraw'), and a checklist — with only minor gaps such as placeholder templates ('<project>: <topic from ticket>') that the model must fill in.

4 / 5

Workflow Clarity

A clear 8-step sequence with explicit validation/verification checkpoints (the 'Walkthrough Quality Checklist', 'Verify it against the ticket', 'If you can't verify, say I need to verify this'), and feedback loops for the riskiest steps (render failure → ASCII fallback, asking the user if anything is unclear before proceeding).

5 / 5

Progressive Disclosure

Well-organized into Steps, a checklist, and an Important section with clear section headers; no bundle files are provided so there are no external references to navigate, and the inline diagram-complexity callout and reference to the render-diagram skill are clearly signaled, though some content (e.g. the full rendering procedure) is repeated inline rather than split out.

4 / 5

Total

16

/

20

Passed

Description

63%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 specific and mostly distinct, naming the domain and concrete actions with a clear 'When to use' signal available in the body. Its main weakness is trigger-term coverage, which leans on a few planning verbs rather than the natural phrases and synonyms users would actually invoke.

Suggestions

Add explicit trigger phrases users would naturally say, e.g. 'Use when the user wants to understand, explain, or get a walkthrough of a codebase before changing it.'

Include common synonyms such as 'onboarding', 'architecture review', or 'explain the code' to broaden natural-language recall.

Mirror the 'when' clause into the frontmatter description field rather than relying only on the body's 'When to use' line.

DimensionReasoningScore

Specificity

Names the domain (codebase walkthrough) and several concrete actions ('trace the full flow, explain architecture, and build understanding'), but these are still somewhat high-level planning activities rather than a comprehensive list of discrete operations like extracting or merging.

4 / 5

Completeness

Clearly states what it does (deep walkthrough tracing flow, explaining architecture, building understanding) and gives an explicit 'When to use' clause in the body; however the frontmatter description itself only carries the 'what' and lacks an explicit trigger clause in that field, so 'when' is present but only weakly/implicitly in the description line.

4 / 5

Trigger Term Quality

Includes some natural phrases a user might say ('walkthrough', 'understand', 'before implementation'), but is missing common synonyms a user would naturally invoke (e.g. 'explain the codebase', 'onboarding', 'architecture review') and has no file extensions or technical trigger terms.

3 / 5

Distinctiveness Conflict Risk

The niche (pre-implementation codebase understanding, explicitly NOT implementation) is fairly distinct from sibling skills, though it could mildly overlap with general architecture/explanation skills that also 'explain the codebase'.

4 / 5

Total

15

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
AndreJorgeLopes/devflow
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.