CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/coverage-debt-tracker

Builds a per-file coverage-debt ledger by walking N runs of historical coverage data - flags files whose line% / branch% has slid more than M pp over the period (`falling`), files whose coverage hasn't moved while their churn has (`stale`), and files that lost their last covering test (`orphan`). Emits a sorted backlog the team can ratchet down: each PR fixes one or two debt items, the rest stays visible. Use when whole-repo coverage is "fine" but specific modules are eroding silently and the team needs a stack-ranked list to fix.

69

Quality

87%

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

Overview
Quality
Evals
Security
Files

Quality

Content

85%

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

The body is highly actionable with executable code and a well-sequenced workflow including a verification checkpoint, and it cleanly offloads rendering/CI detail to a real one-level reference. It would score higher on conciseness by trimming the narrative Overview and Limitations padding.

Suggestions

Tighten the Overview narrative (the 95% to 60% payment-module story) to a one-line motivation; the table already conveys the axes.

Compress the Limitations bullets into a compact list of constraints rather than explanatory prose.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes competence, but sections like the Overview's payment-module narrative and the verbose Limitations bullets carry explanatory padding that could be tightened without losing clarity.

2 / 3

Actionability

Provides complete, executable Python functions (detect_falling, detect_stale, detect_orphans) with real thresholds and a copy-paste ready CI YAML workflow, plus concrete shell verification commands.

3 / 3

Workflow Clarity

Six clearly sequenced steps with an explicit verification checkpoint in Step 1 ('assert coverage-history/ exists and holds at least 2 non-empty runs'), and the anti-patterns table supplies error-recovery guidance.

3 / 3

Progressive Disclosure

SKILL.md is a concise overview with detection logic inline; rendering and CI detail are split into one-level-deep, clearly signaled references (references/ledger-rendering-and-ci.md), which exists and is genuinely used.

3 / 3

Total

11

/

12

Passed

Description

85%

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 complete, with an explicit 'Use when' trigger and concrete multi-action capabilities. Its main weakness is trigger-term naturalness, which favors specialized jargon over the plain phrasing users would say.

Suggestions

Add plain-language trigger variants users would actually say, e.g. 'coverage is slipping', 'coverage going down over time', or 'which files lost coverage' alongside the specialized phrasing.

Consider naming the upstream data sources a user would mention (e.g. lcov, cobertura) as trigger terms so the skill surfaces on parser mentions.

DimensionReasoningScore

Specificity

Lists multiple concrete actions: 'walks N runs of historical coverage data', flags 'falling', 'stale', and 'orphan' files, and 'Emits a sorted backlog the team can ratchet down', matching the top anchor.

3 / 3

Completeness

Clearly answers what it does ('Builds a per-file coverage-debt ledger') and when to use it with an explicit 'Use when whole-repo coverage is "fine" but specific modules are eroding silently' clause.

3 / 3

Trigger Term Quality

Includes relevant terms like 'coverage', 'coverage-debt', and 'eroding silently' but leans on specialized phrasing ('stack-ranked list', 'ratchet down') over the common variations a user would naturally say, so it is not a full 3.

2 / 3

Distinctiveness Conflict Risk

A clear niche (per-file coverage-debt ledger from historical runs) with distinct triggers unlikely to overlap with sibling skills like the per-PR coverage comment tool.

3 / 3

Total

11

/

12

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

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Reviewed

Table of Contents