CtrlK
BlogDocsLog inGet started
Tessl Logo

post-merge-scan

Scan recent merges to main for tech debt, TODOs, debug code, and small cleanup opportunities. Produces a prioritized fix list.

70

Quality

86%

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

72%

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

The body is admirably concise and well-organized with a concrete output schema and triage rules. It underspecifies the detection mechanics and lacks explicit sequencing/verification checkpoints for the batch scan, which caps actionability and workflow clarity at 2.

Suggestions

Add the concrete git commands to enumerate recent merges (e.g., `git log --merges --since='7 days ago'`) and diff for introduced TODOs, so the detection step is executable rather than implied.

Add an explicit numbered workflow (enumerate merges → diff each → classify findings → emit output) with a verification checkpoint confirming each finding was actually introduced by that merge.

Include a brief verification pass for flagged items (e.g., re-checking that a doc link is truly broken or a flag is genuinely marked for removal) before assigning risk/effort, since this is a batch operation.

DimensionReasoningScore

Conciseness

Lean ~30-line body with no concept explanations or padding; every section (output template, scan targets, rules) earns its place, fitting the lean-and-efficient anchor rather than the mostly-efficient-but-tightenable anchor at 2.

3 / 3

Actionability

The output template and risk→action triage rules are concrete, but the detection mechanics are missing — no commands for enumerating recent merges or identifying TODOs *introduced* in a merge, leaving key how-to details unspecified, so it is not the fully-executable anchor at 3.

2 / 3

Workflow Clarity

The scan→find→triage→output sequence is implied via the template and rules, but steps are not explicitly sequenced and there are no verification checkpoints for this batch operation, matching the steps-present-but-checkpoints-implicit anchor at 2.

2 / 3

Progressive Disclosure

Under 50 lines with no need for external references, organized into three clear labeled sections, satisfying the simple-skill allowance for a top score.

3 / 3

Total

10

/

12

Passed

Description

100%

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 concise, concrete, and covers both capability and an explicit use-trigger. It carves a distinct post-merge niche with natural trigger terms and contains no fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete scan targets — 'TODOs, deprecations, broken doc links, stale flags' — matching the multi-action anchor, not the single-domain anchor at 2.

3 / 3

Completeness

Explicitly states both what ('Scan recent merges... for follow-up cleanup: TODOs, deprecations, broken doc links, stale flags') and when ('Use in post-merge cleanup loops'), satisfying the both-what-and-when anchor; it is not a 2 because the when is explicit, not merely implied.

3 / 3

Trigger Term Quality

Natural developer vocabulary ('merges to main', 'post-merge cleanup', 'TODOs', 'deprecations', 'stale flags') gives good coverage of terms a user would say when needing this skill.

3 / 3

Distinctiveness Conflict Risk

The 'recent merges to main' / 'post-merge cleanup' scoping carves a clear niche unlikely to trigger general code-review or TODO-scanning skills.

3 / 3

Total

12

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
cobusgreyling/loop-engineering
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.