post-merge-scan

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

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./starters/post-merge-cleanup-opencode/skills/post-merge-scan/SKILL.md

Quality

Content

72%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 admirably concise and well-structured for a simple skill, but its execution guidance is incomplete and it lacks the validation/verification checkpoints that a batch, auto-fixing workflow requires. Adding concrete scan commands, an output format, and a validate-before-write step would raise the two capped dimensions.

Suggestions

Add concrete scan commands, e.g. 'grep -rnE "TODO|FIXME|HACK" $(git diff --name-only HEAD~10)' and a lint invocation, instead of listing TODO/FIXME/HACK only as a category.

Specify the output format of post-merge-state.md (e.g. a prioritized markdown table with columns: item, file, class, suggested fix) and the prioritization rule.

Insert a validation checkpoint before writing results — e.g. confirm each auto-fix compiles/passes lint and revert on failure, given the 'Max 2 fix attempts' rule involves destructive changes.

Dimension	Reasoning	Score
Conciseness	Extremely lean: ~25 lines with no padding and no explanation of concepts Claude already knows; every line (scan sources, classification, output, rules) earns its place.	5 / 5
Actionability	Gives one concrete command ('git diff HEAD~10'), a clear classification taxonomy, and a named output file, but is missing key execution details — no grep/command for TODO/FIXME/HACK, no output format for post-merge-state.md, and no prioritization scheme.	3 / 5
Workflow Clarity	Sections imply a rough scan → classify → output sequence, but there are no validation/verification checkpoints and the skill performs batch scanning plus auto-fix attempts, so workflow clarity is capped at 3 per the destructive/batch guideline.	3 / 5
Progressive Disclosure	Under 50 lines with no need for external references, organized into clear labeled sections (Scan Sources, Classification, Output, Rules); the simple-skill exception allows a 5 on well-organized sections alone.	5 / 5
	Total	16 / 20 Passed

Description

66%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 and uses natural trigger terms, but it omits any explicit 'Use when…' guidance, which both caps completeness and slightly weakens distinctiveness. Adding a trigger clause would lift the two dependent dimensions.

Suggestions

Append a 'Use when…' clause naming explicit triggers, e.g. 'Use when reviewing recently merged code on main, or when the user asks to clean up tech debt, TODOs, or debug code after a merge.'

Add common synonyms/file extensions a user might say ('post-merge cleanup', 'lint warnings', 'code review follow-ups') to broaden trigger-term coverage.

Tighten distinctiveness by contrasting with general code review (e.g. 'focused on post-merge follow-up, not pre-merge review').

Dimension	Reasoning	Score
Specificity	Names the domain (recent merges to main) and lists several concrete scan targets — 'tech debt, TODOs, debug code, and small cleanup opportunities' — plus a concrete output ('prioritized fix list'), but the verbs are limited to 'scan' and 'produces' with minor coverage gaps.	4 / 5
Completeness	Has a clear 'what' (scan merges for debt/TODOs/debug code, produce a fix list) but no 'Use when…' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Includes several natural terms a user would say ('tech debt', 'TODOs', 'debug code', 'cleanup', 'recent merges'), but is missing common synonyms like 'code review', 'lint', or 'post-merge'.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear post-merge cleanup niche that is mostly distinct, with only minor overlap risk against general code-review or linting skills; not a 5 because triggers are implied by content rather than stated explicitly.	4 / 5
	Total	15 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: cobusgreyling/loop-engineering
Path: starters/post-merge-cleanup-opencode/skills/post-merge-scan/SKILL.md
Commit: 804a4e9

Reviewed: about 13 hours ago

Table of Contents

Discovery Implementation Validation

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.