CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

dyl-review

Review one or more PRs in Dylan's style: up to 7 copy-pasteable asks and one 🟢/🟔/šŸ”“ call. Quick by default; "deep" adds thermos and Bugbot. Use for /dyl-review, "review this PR like me", or terse design/correctness comments. Never posts to the PR.

Quality

87%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 dense, highly actionable workflow skill: explicit main-thread rules, concrete git/gh commands, a skeptical synthesis filter, and an exact output format. It respects the reader's intelligence with no filler. The only structural nit is that all guidance lives inline with no progressive-disclosure path if the skill grows.

DimensionReasoningScore

Conciseness

The body is lean and prescriptive throughout — numbered rules, a marks table, and an output template with zero padding and no explanation of concepts Claude already knows ('Complexity is the enemy', 'Chesterton's fence' are directives, not tutorials). Every token earns its place (anchor 5).

5 / 5

Actionability

Concrete, copy-pasteable commands ('gh pr view <n> --json baseRefName', 'git diff origin/<base>...HEAD', 'git worktree add /tmp/dyl-review-<pr> origin/<branch>') plus an exact review-block template and example clauses ('🟢 Nits only', 'šŸ”“ Blocker on silent fallback'). Minor gaps: the Dylan-lens worker's prompt is scoped but not given verbatim, and its lenses depend on external skills (anchor 4, not 5).

4 / 5

Workflow Clarity

The sequence is fully explicit — requirements pre-check with a stop-and-recover path ('Missing → stop and tell the user to run /add-plugin'), gather-once-then-fan-out, numbered synthesis with a skeptical filter, and re-review handling that passes prior context to workers. The skill is read-only and never posts, so no destructive-operation validation cap applies (anchor 5).

5 / 5

Progressive Disclosure

No bundle files exist; the single-file body is well-sectioned (Depth, Main-thread rules, Worker, Synthesis, Review block, Hard rules) and its one external reference is well signaled ('Check first with [../dyl-mode/references/requirements.md]') and one level deep. Minor gaps: the Dylan voice rules and marks table could live in a reference file if the skill grows (anchor 4).

4 / 5

Total

18

/

20

Passed

Description

83%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 strong description: third-person voice, concrete capabilities, an explicit 'Use for' trigger clause, and a clear boundary ('Never posts to the PR'). The only weakness is unexplained internal jargon ('thermos', 'Bugbot') and a few missing natural trigger variants.

Suggestions

Briefly gloss 'thermos' and 'Bugbot' (e.g., 'deep adds parallel bug and code-quality subagent passes') so the capability is legible without plugin context.

Add one or two common trigger variants such as 'code review' or 'PR feedback' alongside the existing phrases.

DimensionReasoningScore

Specificity

Concrete actions are stated ('up to 7 copy-pasteable asks and one 🟢/🟔/šŸ”“ call', 'Quick by default; "deep" adds thermos and Bugbot'), but 'thermos' and 'Bugbot' are opaque to a cold reader, so coverage is not comprehensive (anchor 4, not 5).

4 / 5

Completeness

Explicitly answers both what ('Review one or more PRs in Dylan's style: up to 7 copy-pasteable asks and one 🟢/🟔/šŸ”“ call') and when ('Use for /dyl-review, "review this PR like me", or terse design/correctness comments') with concrete trigger phrases — anchor 5. It also adds a boundary ('Never posts to the PR').

5 / 5

Trigger Term Quality

Natural trigger phrases ('review this PR like me', 'terse design/correctness comments') plus the slash command '/dyl-review' give good coverage, though common variants like 'code review' or 'PR feedback' are missing (anchor 4, not 5).

4 / 5

Distinctiveness Conflict Risk

'Dylan's style', '/dyl-review', and the thermos/Bugbot references carve a distinct niche, but 'terse design/correctness comments' leaves minor overlap risk with generic PR-review skills (anchor 4, not 5).

4 / 5

Total

17

/

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

relative_links

Relative link issues: 1 suspicious

Warning

Total

14

/

16

Passed

Repository

cursor/plugins

Path

dyl-stack/skills/dyl-review/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.