CtrlK
BlogDocsLog inGet started
Tessl Logo

asymmetric-wins

Identify an asymmetric win by refusing a small promise that would eliminate disproportionate complexity. Use when the user asks about asymmetric wins, pixel perfect fidelity, compatibility, fallbacks, modes, duplicate paths, or what would delete disproportionate complexity.

64

Quality

80%

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 ./.agents/skills/asymmetric-wins/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 delivers an unusually actionable decision procedure: concrete steps, two fill-in templates, an artifact ladder, and a fully worked example, with clear navigation and only one-level-deep cross-references. Its main cost is repetition of the same load-bearing/keep-it caveat across sections, which inflates token usage without adding guidance.

Suggestions

Consolidate the repeated 'keep the feature when the loss is load-bearing' caveat (currently in the intro, Procedure, and both template sections) into one authoritative statement and reference it elsewhere.

Move the worked social-sign-in example and possibly the Domain Manifestations into a references/ file, keeping SKILL.md as a tighter overview with clearly signaled links.

Add an explicit final checkpoint that re-evaluates remaining candidates after a keep/refuse decision, closing the workflow-clarity gap.

DimensionReasoningScore

Conciseness

The body is dense and mostly free of filler, but the core caution ('keep it when the loss is load-bearing', 'this is not a quota') is restated four or more times across the opening, Procedure, and template sections. It could be tightened to one canonical statement, which places it at 'mostly efficient but could be tightened' rather than merely minor trimming.

3 / 5

Actionability

For an instruction-only skill the guidance is fully concrete: a 6-step procedure, a fill-in Decision Template, a UI Refactor Template, an artifact ladder with use conditions, and a complete worked social-sign-in example. A practitioner can apply the templates directly, covering the common case.

5 / 5

Workflow Clarity

The Procedure is clearly sequenced with an explicit conditional checkpoint (step 6: 'If the loss is load-bearing, keep the feature... Otherwise, refuse...') and a required output ('write that refusal into the spec'). It falls short of the top anchor only in lacking a feedback loop that revisits remaining candidates after a decision.

4 / 5

Progressive Disclosure

A flat, well-sectioned single file whose outbound links (the rethink skill and its clean-breaks reference, plus the docs article) are one level deep and clearly signaled in 'Compose With'. It is not top-tier because all ~210 lines are inline; the worked example and domain manifestations could plausibly live in reference files.

4 / 5

Total

16

/

20

Passed

Description

78%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: it states a specific capability, uses third-person imperative voice, and pairs it with an explicit, trigger-rich 'Use when' clause. Its only weaknesses are a single-action what-statement and a few overly broad trigger terms that invite overlap with general simplification skills.

DimensionReasoningScore

Specificity

The description names its domain and one concrete action ('Identify an asymmetric win by refusing a small promise that would eliminate disproportionate complexity') but does not list several distinct actions. It sits at the 'domain plus 1-2 concrete actions' anchor rather than the several-actions anchor.

3 / 5

Completeness

It explicitly answers both questions: the what ('Identify an asymmetric win by refusing a small promise that would eliminate disproportionate complexity') and a concrete when ('Use when the user asks about asymmetric wins, pixel perfect fidelity, compatibility, fallbacks, modes, duplicate paths...'). This matches the top anchor.

5 / 5

Trigger Term Quality

'asymmetric wins, pixel perfect fidelity, compatibility, fallbacks, modes, duplicate paths' gives good natural keyword coverage. It is not comprehensive: 'asymmetric wins' is a coined term, and common phrasings like 'simplify' or 'scope down' are absent, so it falls just below the top anchor.

4 / 5

Distinctiveness Conflict Risk

The niche is mostly distinct (asymmetric wins, pixel perfect fidelity, duplicate paths are unusual triggers), but broad terms like 'compatibility, fallbacks, modes' could overlap with refactoring or simplification skills, leaving minor overlap risk rather than a fully clear niche.

4 / 5

Total

16

/

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

relative_links

Relative link issues: 2 suspicious

Warning

Total

15

/

16

Passed

Repository
EpicenterHQ/epicenter
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.