CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

dyl-mode

Dylan's agent style on top of pstack: concise verified delivery, root causes over symptom patches, The Algorithm before design, plain /bro replies, live UI proof, reuse/simplify, and hard merge gates. Use for Dylan, /dyl-mode, or his style. "Get PR green" → /dyl-ready-pr. "Review this PR like me" → /dyl-review. Figma URL → /build-figma.

Quality

91%

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

93%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.

An exceptionally disciplined router skill: every token is actionable, shared content is delegated rather than restated, and references resolve one level deep to real files. The only gap is the absence of an explicit output-validation/feedback loop in the main sequence.

DimensionReasoningScore

Conciseness

Lean and dense throughout: tables of gates and leaf pointers, terse directives ('Scratch never ships', 'Do not copy their contents into this file'), and explicit delegation of all shared machinery to pstack. No padding and no explanation of concepts Claude already knows; every clause carries new information.

5 / 5

Actionability

Fully concrete, executable guidance: exact subagent type ('Task subagent_type: "dyl-agent"'), a real linked requirements file with plugin-check and '/add-plugin <name>' remediation, exact todo formats ('Root cause: <X> because <Y>', 'skip: <reason>'), and an enumerated list of concrete symptom-fix markers ('as any', ts-ignore, retries, weakened assertions).

5 / 5

Workflow Clarity

The numbered non-negotiables give a clear sequence (todolist -> read Principles -> match playbook with skip reasons -> apply triggers -> apply gates) with real checkpoints (requirements check before work, root-cause todo before any fix, hard-stop acknowledgment). Falls short of 5 because there is no explicit validate/verify feedback loop on outputs and the playbook match itself is not verified.

4 / 5

Progressive Disclosure

The body is a genuine overview: a verified one-level-deep reference (references/requirements.md), a pointer table delegating shared machinery to pstack poteto-mode, playbooks/<name>.md, and principle leaves, plus an explicit resolution rule for local overlays. References are well-signaled, shallow, and the bundle structure matches what the body claims.

5 / 5

Total

19

/

20

Passed

Description

87%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, concrete behavior list, and an explicit 'Use for' clause with quoted natural trigger phrases mapped to sibling skills. Trigger coverage could add a few more phrasing variations, and some capability descriptors are mildly abstract.

DimensionReasoningScore

Specificity

Lists several concrete named behaviors ('root causes over symptom patches', 'plain /bro replies', 'live UI proof, reuse/simplify, and hard merge gates'), but some are abstract style descriptors rather than literal actions, so it falls short of comprehensive concrete coverage.

4 / 5

Completeness

Explicitly answers both: what ('Dylan's agent style on top of pstack: ...' with a concrete principle list) and when ('Use for Dylan, /dyl-mode, or his style') with concrete quoted trigger phrases mapped to sub-skills.

5 / 5

Trigger Term Quality

Includes natural quoted phrases a user would actually say ('Get PR green', 'Review this PR like me', 'Figma URL') plus name and slash-command triggers, but misses common synonyms or variations of those phrases.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear personal-style niche keyed to a specific name and slash commands, with distinct quoted triggers routing to each sub-skill; minimal overlap with generic skills.

5 / 5

Total

18

/

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.

Validation — 15 / 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

cursor/plugins

Path

dyl-stack/skills/dyl-mode/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.