CtrlK
BlogDocsLog inGet started
Tessl Logo

improve

Survey a codebase as a senior advisor and turn the highest-value findings into implementation plans for other agents to execute — strictly read-only on source code, never implements anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, architecture, migrations, DX), suggest features or roadmap direction, or generate handoff plans for another agent to implement.

73

Quality

90%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 body is a tight, well-sequenced advisor workflow with strong validation checkpoints and clean single-level progressive disclosure. It earns high marks across conciseness, workflow clarity, and structure; actionability is strong but procedural rather than copy-paste.

DimensionReasoningScore

Conciseness

Lean throughout, assumes Claude's competence, never explains basic concepts; every line carries load (recon checklist, vetting mandate, effort table, handoff contract).

5 / 5

Actionability

Concrete and executable for an instruction-only skill — specific recon items, subagent prompt contents, finding-table columns, and what to feed writing-plans; held at 4 because guidance is procedural rather than copy-paste-ready code.

4 / 5

Workflow Clarity

Four clearly sequenced phases with explicit validation ("Vet before presenting", confirm cited code yourself, disclose what was not audited), enumerated failure classes, and dependency-ordering plus STOP-condition references.

5 / 5

Progressive Disclosure

A single well-signaled one-level reference to the real references/audit-playbook.md ("read it now"); all overview content stays in SKILL.md and navigation is unambiguous.

5 / 5

Total

19

/

20

Passed

Description

88%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, trigger-rich, and fully answers both what and when, with an explicit read-only boundary that distinguishes it from implementer skills. Its only weak spot is a touch of insider phrasing rather than pure user-natural language.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ("Survey a codebase", "turn the highest-value findings into implementation plans", "generate handoff plans") plus a read-only constraint and a comprehensive category list — comprehensive coverage.

5 / 5

Completeness

Explicitly answers both what (survey + convert to plans, read-only) and when via a concrete "Use when asked to audit a codebase, find improvement opportunities..." clause.

5 / 5

Trigger Term Quality

Strong natural triggers ("audit a codebase", "suggest features or roadmap direction", "generate handoff plans") with the full category enumeration; slightly jargon-flavored phrasing keeps it just below the comprehensive-synonym anchor.

4 / 5

Distinctiveness Conflict Risk

A read-only advisor that hands off to a writing-plans skill is a distinct niche with clear boundaries; minor overlap risk with general code-review skills keeps it at 4 rather than 5.

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
joshuadavidthomas/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.