CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

The canonical home for this skill is post-merge-scan in cobusgreyling/loop-engineering

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.

A lean, well-structured instruction-only skill whose reporting format and triage rules are fully actionable. Its one real weakness is workflow clarity: the multi-merge scan sequence is implicit and no validation step confirms findings before they are reported or acted on.

Suggestions

Add an explicit ordered workflow (1. list merges from the last 7 days, 2. scan each diff for the listed items, 3. triage per the rules, 4. emit the output template).

Include a validation checkpoint such as "confirm each TODO/FIXME was introduced by this merge's diff, not pre-existing" before reporting, since this is a batch operation over many merges.

Show one concrete retrieval command (e.g., `git log --merges --since="7 days ago" origin/main`) to close the actionability gap.

DimensionReasoningScore

Conciseness

Every line is a directive or concrete enumeration — "Only scan merges from the last 7 days", "Large refactors → ticket, not auto-fix", "Medium+ risk paths → escalate-human" — with no explanation of concepts Claude already knows; the untrusted-input block states loop-specific behavioral rules rather than generic prompt-injection theory.

5 / 5

Actionability

Concrete, actionable guidance throughout: a copy-paste output template ("### PR #N — title (merged DATE)" with risk/effort/action enums) and explicit triage rules; the gap is that no example command shows how to retrieve recent merges (e.g., `git log --merges --since=7.days` or `gh pr list --merged`), leaving a minor execution gap.

4 / 5

Workflow Clarity

The sequence (retrieve merges → scan each → triage → report) is implicit in the section layout but never explicitly ordered, and this batch operation over multiple merges lacks an explicit validation checkpoint (e.g., confirming a TODO is newly introduced rather than pre-existing, or that a flagged link is actually broken); the batch-operation cap at 3 applies.

3 / 5

Progressive Disclosure

The body is under 50 lines with no bundle files and no content that belongs in separate references; sections ("Output per merge", "What to look for", "Rules", "Untrusted input") are well-organized, and the single background link is clearly signaled and one level deep, satisfying the simple-skill exception for a top score.

5 / 5

Total

17

/

20

Passed

Description

75%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.

A solid description that names a clear niche and four concrete scan targets with an explicit trigger clause. Its main weaknesses are a trigger clause limited to one narrow phrase and a small coverage gap versus the full set of checks documented in the body.

Suggestions

Broaden the 'when' clause with concrete triggers, e.g. "Use after merging PRs to main, or when the user asks for post-merge follow-ups, TODO cleanup, or stale-flag removal."

Add the missing scan categories from the body (e.g., "unused imports / dead code") so the description's capability list matches the skill's actual coverage.

Include a synonym users naturally say, such as "follow-up work" or "tech debt", to strengthen trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain and four concrete scan targets — "TODOs, deprecations, broken doc links, stale flags" — but the body adds "Unused imports or dead code clusters" as a category the description omits, leaving a minor coverage gap that keeps it below the comprehensive anchor 5.

4 / 5

Completeness

Both parts are present: a clear what ("Scan recent merges to main for follow-up cleanup: TODOs, deprecations, broken doc links, stale flags") and an explicit when ("Use in post-merge cleanup loops"), so it is not capped at 3; the when-clause is narrow and could name more concrete trigger situations, which is exactly the anchor 4 example pattern.

4 / 5

Trigger Term Quality

Good natural keywords users would say ("merges", "TODOs", "stale flags", "broken doc links", "post-merge cleanup"), but common variations like "follow-up work", "tech debt", or "post-merge review" are missing, matching anchor 4 rather than the synonym-complete anchor 5.

4 / 5

Distinctiveness Conflict Risk

"Scan recent merges to main" carves out a distinct post-merge triage niche with specific triggers, but it could still overlap with general code-review or cleanup skills in a shared library, fitting "mostly distinct; minor overlap risk".

4 / 5

Total

16

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository

cobusgreyling/loop-engineering

Path

starters/post-merge-cleanup/.codex/skills/post-merge-scan/SKILL.md

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.