CtrlK
BlogDocsLog inGet started
Tessl Logo

post-merge-scan

Scan recent merges to main for follow-up cleanup: TODOs, deprecations, broken doc links, stale flags. Use in post-merge cleanup loops.

60

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./starters/post-merge-cleanup/.claude/skills/post-merge-scan/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

80%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 content is concise and well-structured with a concrete output template and clear scan targets, but the batch workflow lacks validation checkpoints, which limits workflow clarity. Adding a verification step would meaningfully improve the skill.

Suggestions

Add an explicit validation/verification step to the workflow (e.g., cross-check that flagged TODOs are newly introduced in the merge, or verify broken-link hits before reporting) so the batch operation self-checks.

Provide one or two concrete executable commands or queries (e.g., a git log range or grep for TODOs in the diff) to lift actionability from instruction-only to copy-paste ready.

Clarify how 'state' overrides the 7-day window and where that state lives, since the rule references it without defining it.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — no padding, no basic-concept explanations, and every line (output template, look-for list, rules) earns its place.

5 / 5

Actionability

It provides a copy-paste output template, concrete scan targets with file:line expectations, and numeric thresholds (7 days, small-only dead code); minor gaps remain since it is instruction-only with no executable command examples.

4 / 5

Workflow Clarity

A rough sequence exists via the output template and rules, but this batch operation (scanning multiple merges) lacks any explicit validation or verification checkpoint, capping workflow clarity at 3.

3 / 5

Progressive Disclosure

A simple skill under 50 lines with well-organized sections and no need for external references; the structure is clear and easy to navigate.

5 / 5

Total

17

/

20

Passed

Description

63%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 distinct, clearly naming its scan targets, but its trigger guidance is weak and relies on jargon rather than natural user phrasing. Strengthening the 'Use when...' clause would lift completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause with natural user phrases (e.g., 'Use when reviewing recently merged PRs, doing post-merge cleanup, or auditing follow-up TODOs').

Include common synonyms and concrete trigger terms users would say, such as 'merged pull requests', 'merge follow-ups', or 'post-merge review'.

Clarify the 'when' by naming the triggering situation explicitly rather than only the loop context.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete actions — 'TODOs, deprecations, broken doc links, stale flags' — giving comprehensive coverage of what the scan looks for.

5 / 5

Completeness

The 'what' is clear, but the 'when' is only weakly implied by 'Use in post-merge cleanup loops' rather than an explicit 'Use when...' trigger clause, which caps completeness at 3.

3 / 5

Trigger Term Quality

Phrases like 'merges to main' and 'post-merge cleanup loops' are domain jargon; it lacks the natural trigger phrases a user would actually say and misses common synonyms.

3 / 5

Distinctiveness Conflict Risk

The post-merge-scan niche is distinct with specific triggers; minor overlap risk only with closely related cleanup or review skills.

4 / 5

Total

15

/

20

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.