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.

67

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

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 is a strong, self-contained decision skill: lean, highly actionable with templates and a worked example, and a clearly sequenced procedure with an explicit decision gate. The main gap is that verification is delegated to companion skills rather than embedded, and no bundle files are used to split the long content.

DimensionReasoningScore

Conciseness

The body is efficient and largely assumes Claude's competence, presenting a spine, manifestations, a procedure, templates, a ladder, and a worked example without explaining known concepts. A few philosophical guardrail sentences ("This is not arithmetic and not a quota", "The rule is evidence-seeking, not dramatic") could be trimmed, keeping it just below the lean/5 anchor.

4 / 5

Actionability

For a decision skill it gives concrete, fill-in-ready guidance: a 6-step procedure, a decision template, a UI refactor template, a 5-rung artifact ladder with when-to-use conditions, and a fully worked social sign-in example with specific deletion-prize entries. The guidance is specific and covers the common case.

5 / 5

Workflow Clarity

The Procedure is a clear numbered sequence with an explicit decision gate (steps 5-6) and a keep-when-load-bearing checkpoint, so validation is present rather than absent. It is a 4 rather than 5 because hard pre/post-execution verification is delegated to companion skills (refactoring counts callers; greenfield executes the break) rather than contained as an explicit validate-fix-retry loop here.

4 / 5

Progressive Disclosure

The file is well-organized with clear section headers and one clearly-signaled, one-level-deep external reference (the narrative article path at the end), with no nested references. It is a 4 rather than 5 because everything lives in a single ~200-line file with no bundle splitting; the worked example or detailed templates could arguably move into reference files.

4 / 5

Total

17

/

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.

The description cleanly answers what the skill does and when to use it, with a strong explicit trigger list and a distinct central concept. Its only weak spot is specificity, since it frames a single refusal decision rather than enumerating several concrete actions.

Suggestions

Add one or two more concrete actions to the 'what' clause (e.g., '...write the refusal into the spec and hand the breaking change to greenfield-clean-breaks') to lift specificity toward a multi-action description.

Add a synonym or two to the trigger list (e.g., 'removing a feature to simplify', 'collapsing duplicate code paths') to broaden natural-keyword coverage and reduce overlap ambiguity with generic refactoring skills.

DimensionReasoningScore

Specificity

It names the domain and one or two concrete actions ("refusing a small promise", "eliminate disproportionate complexity") but describes essentially a single refusal move rather than a comprehensive list of distinct actions. It sits above the minimal/generic anchor (2) yet below the several-specific-actions anchor (4).

3 / 5

Completeness

It explicitly answers both: the "what" ("Identify an asymmetric win by refusing a small promise that would eliminate disproportionate complexity") and the "when" ("Use when the user asks about..."), with concrete trigger phrases. This matches the anchor that requires both with explicit triggers.

5 / 5

Trigger Term Quality

The "Use when..." clause lists several natural trigger phrases users would say — "asymmetric wins", "pixel perfect fidelity", "compatibility", "fallbacks", "modes", "duplicate paths" — giving good keyword coverage. It is not a 5 because synonym coverage is limited and no file-extension-style terms apply to this concept.

4 / 5

Distinctiveness Conflict Risk

The core concept "asymmetric wins" is a distinct niche, but several triggers ("compatibility", "fallbacks", "modes") are broad and overlap with closely related refactoring/cleanup skills the body itself composes with. It is mostly distinct with minor overlap risk, below the minimal-conflict anchor (5).

4 / 5

Total

16

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.