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.
86
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
82%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 has strong completeness with explicit 'Use when' and 'Do NOT use' clauses, and good trigger term coverage with natural user phrases. However, it leans heavily on metaphorical/marketing language ('pathfinder', 'surgically', 'lasting intelligence') instead of concrete capability descriptions, and its very broad scope ('any development task') creates potential overlap with other coding skills.
Suggestions
Replace metaphorical language ('pathfinder', 'surgically', 'lasting intelligence') with concrete actions like 'traces code flows', 'identifies dependencies', 'maps call hierarchies' to improve specificity.
Narrow the scope or add clearer differentiators — 'any development task in unfamiliar territory' is too broad and will conflict with other coding skills. Consider specifying what makes this skill unique compared to general coding assistance.
Use third-person voice throughout — while most of the description avoids first/second person, phrases like 'Your pathfinder' use second person and should be rephrased.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (codebase navigation/development) and mentions some actions like investigating, implementing, and maintaining a .notebook/ knowledge base, but many phrases are vague or metaphorical ('pathfinder', 'surgically', 'lasting intelligence') rather than concrete specific actions. It doesn't list precise capabilities like 'traces function call chains' or 'maps dependency graphs'. | 2 / 3 |
Completeness | Clearly answers both 'what' (investigates codebases, implements changes, maintains .notebook/ knowledge base, summons skills/MCPs/docs) and 'when' (explicit 'Use when...' clause with trigger scenarios, plus explicit 'Do NOT use' exclusions). The explicit trigger guidance and negative boundaries are strong. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger phrases users would actually say: 'fix this', 'implement this', 'how does this work', 'investigate this flow', 'help me with this code'. Also includes broader terms like 'fixing bugs', 'implementing features', 'refactoring', 'investigating flows'. Good coverage of natural language. | 3 / 3 |
Distinctiveness Conflict Risk | The scope is quite broad — 'fixing bugs, implementing features, refactoring, investigating flows, or any development task' could overlap with many other coding-related skills. The 'unfamiliar territory' qualifier and the 'Do NOT use' exclusions help somewhat, but 'any development task' is very wide and could conflict with more specialized coding skills. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill that provides clear, actionable guidance for navigating unfamiliar codebases. Its main strength is the detailed mission cycle with explicit verification steps and excellent worked examples. Its primary weakness is moderate verbosity — the 'Expected output' annotations, the Consistency Contract (which largely restates the Golden Rules), and some explanatory text could be trimmed to save tokens without losing clarity.
Suggestions
Consolidate the Consistency Contract into the Golden Rules section — most items are restatements, and merging them would save ~20 lines of tokens.
Remove the 'Expected output' lines after each mission cycle step — they're largely redundant with the step descriptions themselves.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is well-structured but verbose in places. The Golden Rules, Consistency Contract, and mission cycle explanations contain some redundancy and over-explanation (e.g., 'Expected output' lines after each step, the detailed 'Adapting to Mission Scale' section). However, it avoids explaining basic programming concepts and most content is genuinely instructive. | 2 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: a specific mission cycle with clear steps, a plan template format, a knowledge verification chain with explicit priority ordering, specific triggers for note creation, and three detailed worked examples showing exactly how the cycle plays out in practice. | 3 / 3 |
Workflow Clarity | The six-step mission cycle (BRIEFING → RECON → PLAN → EXECUTE → VERIFY → DEBRIEF) is clearly sequenced with explicit validation checkpoints at each step. The Plan template requires verification criteria per step, the Verify step has explicit pass/fail handling, and the Knowledge Verification Chain provides a clear escalation path with feedback loops. | 3 / 3 |
Progressive Disclosure | The skill appropriately references external files for detailed content (`references/coding-principles.md` for coding details, `references/notebook-spec.md` for notebook format) keeping the main file as an overview. References are one level deep and clearly signaled. The content is well-organized with clear section headers and logical flow. | 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- tech-leads-club/agent-skills
- Commit
906a57d
- 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.