CtrlK
BlogDocsLog inGet started
Tessl Logo

codenavi

Your pathfinder for navigating unknown codebases. Investigates with precision, implements surgically, and never assumes — if it doesn't know, it says so. Maintains a .notebook/ knowledge base that grows across sessions, turning every discovery into lasting intelligence. Summons available skills, MCPs, and docs when the mission demands. Use when fixing bugs, implementing features, refactoring, investigating flows, or any development task in unfamiliar territory. Triggers on "fix this", "implement this", "how does this work", "investigate this flow", "help me with this code". Do NOT use for greenfield scaffolding, CI/CD, or infrastructure provisioning.

67

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

70%

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

A well-structured process skill with a clear, checkpointed workflow and appropriately externalized references; its weaknesses are verbosity from redundant sections and actionability that leans on abstract process framing alongside its concrete templates.

Suggestions

Collapse the 'Consistency Contract' into the 'Golden Rules' (or a short 'What you can always expect' list) to remove the restated redundancy and reclaim tokens.

Tighten abstract Recon/Debrief directives like 'Note what you find — patterns, conventions, surprises, gotchas' into a concrete checklist of what to capture and where.

Consider moving the three full worked examples into a references/examples.md file, keeping only one compact example inline in SKILL.md.

DimensionReasoningScore

Conciseness

It avoids explaining basic concepts Claude already knows, but it is verbose and self-repetitive — the 10-item 'Consistency Contract' restates principles already established in the 'Golden Rules', and three lengthy worked examples pad the token budget without proportional new guidance.

2 / 3

Actionability

It offers concrete templates (the Plan format with per-step verification criteria, the 5-step Knowledge Verification Chain, explicit note-creation triggers) and worked examples, but much of the core guidance remains abstract process framing such as 'Investigate the relevant parts of the codebase' and 'Note what you find'.

2 / 3

Workflow Clarity

The Mission Cycle is a clearly sequenced BRIEFING → RECON → PLAN → EXECUTE → VERIFY → DEBRIEF flow, each step with an 'Expected output', and the Verify step provides explicit checkpoints plus a fix-before-declaring-success feedback loop.

3 / 3

Progressive Disclosure

SKILL.md functions as an overview while detailed material is externalized to real one-level-deep references clearly signaled in the body ('For detailed coding principles, read references/coding-principles.md' and 'For the .notebook/ format specification, read references/notebook-spec.md'), both of which exist in the bundle.

3 / 3

Total

10

/

12

Passed

Description

90%

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, specific description with explicit triggers, exclusions, and good natural-language keywords; its only flaw is the second-person 'Your pathfinder' opening, which violates the third-person-voice guideline and caps the specificity score.

Suggestions

Rephrase the opening in third person to avoid the second-person voice penalty — e.g., 'Pathfinder for navigating unknown codebases. Investigates with precision...' instead of 'Your pathfinder...'.

DimensionReasoningScore

Specificity

It lists multiple concrete actions ('Investigates with precision, implements surgically', 'Maintains a .notebook/ knowledge base', 'Summons available skills, MCPs, and docs'), which would score 3, but it opens with the second-person voice 'Your pathfinder for navigating unknown codebases', triggering the rubric's -1 voice penalty.

2 / 3

Completeness

It explicitly answers both 'what' (navigates unknown codebases, investigates, implements, maintains .notebook/, summons allies) and 'when' ('Use when fixing bugs, implementing features, refactoring... Triggers on...') with explicit triggers and explicit exclusions.

3 / 3

Trigger Term Quality

It includes natural phrasing users actually say — 'fix this', 'implement this', 'how does this work', 'investigate this flow', 'help me with this code' — alongside task nouns like 'fixing bugs', 'refactoring', 'investigating flows', giving strong coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

It carves a clear niche (unfamiliar codebases plus a persistent .notebook/ knowledge base) and adds a 'Do NOT use for greenfield scaffolding, CI/CD, or infrastructure provisioning' exclusion, making overlap with other skills unlikely.

3 / 3

Total

11

/

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
tech-leads-club/agent-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.