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.

69

Quality

84%

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

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.

A well-structured methodology skill with an explicit mission cycle, validation checkpoints, feedback loops, and properly externalized references. Its main weakness is verbosity — narrative framing and a redundant Consistency Contract that restates the Golden Rules inflate the body.

Suggestions

Merge the Consistency Contract into the Golden Rules (or vice versa) — they overlap on 'never assume', 'verify against current docs', 'capture discoveries in .notebook/', and 'match existing style', so one combined list removes ~12 lines of redundancy.

Trim motivational narrative such as 'You are the developer's companion — a methodical pathfinder' and 'You and the developer are on this quest together'; the methodology speaks for itself.

Consider moving the three full mission transcripts (Examples 1-3) into a references/examples.md file and summarizing one inline, keeping the overview lean.

DimensionReasoningScore

Conciseness

Mostly efficient and well-organized, but motivational framing ('You and the developer are on this quest together', 'no wasted effort, no guesswork, no collateral damage') and redundant rule lists (Golden Rules vs the 10-item Consistency Contract restate 'never assume', 'verify against docs', 'capture discoveries', 'match style') could be tightened.

3 / 5

Actionability

Provides a copy-paste-ready Plan template with per-step 'verify:' criteria, an ordered Knowledge Verification Chain, a prioritized Summon order, and concrete example transcripts with real file:function references — mostly executable guidance with only minor abstract steps like 'Trace the flow'.

4 / 5

Workflow Clarity

The BRIEFING→RECON→PLAN→EXECUTE→VERIFY→DEBRIEF cycle is clearly sequenced, each step has numbered substeps and an explicit Expected output, and the Verify step plus the Plan's mandatory verification criteria provide explicit checkpoints and a fix-before-declaring-success feedback loop.

5 / 5

Progressive Disclosure

The body is an overview that offloads detail to two clearly-signaled, one-level-deep references ('read references/coding-principles.md', 'read references/notebook-spec.md'), both of which exist as real files, with the methodology kept inline and split appropriately across well-organized sections.

5 / 5

Total

17

/

20

Passed

Description

91%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, third-person description that answers what, when, and when-not with concrete trigger phrases. Minor abstract phrasing in a few verbs and some breadth in positive triggers keep it just short of a perfect mark.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Investigates with precision', 'implements surgically', 'Maintains a .notebook/ knowledge base', 'Summons available skills, MCPs, and docs' — but 'surgically'/'precision' are somewhat abstract phrasing, leaving minor coverage gaps versus the anchor-5 example.

4 / 5

Completeness

Clearly answers what (navigate, investigate, implement, maintain notebook, summon allies) and when ('Use when fixing bugs... any development task in unfamiliar territory' plus concrete trigger phrases), and adds a 'Do NOT use for...' exclusion clause — explicitly covering both what and when.

5 / 5

Trigger Term Quality

Explicitly enumerates natural user phrases — 'Triggers on "fix this", "implement this", "how does this work", "investigate this flow", "help me with this code"' — alongside scenario terms like 'fixing bugs, implementing features, refactoring', giving comprehensive coverage of what users actually say.

5 / 5

Distinctiveness Conflict Risk

The 'unfamiliar codebases / navigation' framing plus the negative triggers ('Do NOT use for greenfield scaffolding, CI/CD, or infrastructure provisioning') carve a clear niche, but the positive triggers ('fixing bugs, implementing features, refactoring') are broad enough to overlap with general coding-assistant skills.

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.

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.