CtrlK
BlogDocsLog inGet started
Tessl Logo

benchmark-methodology

Use after competitive-platform-analysis has produced a tiered competitor set. Scores each competitor across nine weighted dimensions (positioning, voice, visual craft, offer packaging, evidence, enterprise-readiness, thought leadership, pricing, client's strategic tension) with explicit 1–5 rubrics and a tension-plot. Precedes competitive-report-structure.

71

Quality

86%

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

The canonical home for this skill is benchmark-methodology in affaan-m/ECC

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 highly actionable methodology skill with a concrete output template, ordered data-collection steps, and explicit calibration/validation checkpoints. Its main weakness is token efficiency: the critical 'do not average the tension poles' rule is repeated many times and the tension concept is re-explained across overlapping sections.

Suggestions

State the 'score both tension poles separately, never average them' rule once in dimension 9 and reference it from other sections rather than restating it verbatim in the positioning brief, 'Why these dimensions', tension axes, and Anti-Patterns.

Collapse the overlapping framing in 'When to Activate', 'Client positioning brief', and 'Why these dimensions' into a single concise section so the strategic-tension concept is explained once.

Consider moving the full competitor profile card template and the generic 1–5 rubric anchors into a reference file (e.g. references/profile-card.md) and summarizing them in SKILL.md to improve progressive disclosure and reduce inline length.

DimensionReasoningScore

Conciseness

Mostly efficient and free of basic-concept padding, but the 'never average the tension poles' point is restated five or more times (description, positioning brief, 'Why these dimensions', dimension 9, tension axes, and Anti-Patterns) and the tension concept is re-explained across several sections, so it could be tightened.

3 / 5

Actionability

Provides a fully specified, copy-paste-ready competitor profile card template, a concrete ordered data-collection list with six named sources, explicit 1–5 rubric anchors, and a precise per-dimension recording format (score + one-line justification + source link).

5 / 5

Workflow Clarity

Sequences the work clearly (establish positioning brief → collect data in cheapest-signal-first order → record evidence per score → calibrate side-by-side → adjust outliers → hand off) with explicit validation checkpoints ('No score without evidence') and a feedback loop (re-read and adjust outliers before finalizing).

5 / 5

Progressive Disclosure

Well-organized into clearly headed sections with only one-level references (to sibling skills, not nested files) and no bundle files to mismanage, but the 180-line body keeps the rubric anchors and the full profile-card template inline when they could live in separate reference files.

4 / 5

Total

17

/

20

Passed

Description

92%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, specific description that names the task, the nine dimensions, the scoring method, and its workflow neighbors. It uses third-person voice and provides explicit trigger guidance. Minor improvement would come from adding user-natural synonyms like 'benchmark' or 'rate competitors'.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — scoring across nine explicitly named dimensions with 1–5 rubrics and producing a tension-plot — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both what ('Scores each competitor across nine weighted dimensions... with explicit 1–5 rubrics and a tension-plot') and when ('Use after competitive-platform-analysis has produced a tiered competitor set', 'Precedes competitive-report-structure').

5 / 5

Trigger Term Quality

Includes natural terms like 'competitor', 'scores', 'rubrics', and 'tension-plot', but leans on internal skill-name triggers and omits common synonyms a user might say ('benchmark', 'rate', 'compare competitors').

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (competitor benchmarking across nine specific dimensions) anchored to a defined prerequisite/next-step workflow chain, giving it distinct triggers and minimal overlap risk.

5 / 5

Total

19

/

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
affaan-m/ECC
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.