CtrlK
BlogDocsLog inGet started
Tessl Logo

analysis-writing

Use when a business metric comparison must be written from structured evidence with explicit evidence references and limitations.

60

Quality

70%

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 ./skills/agently/assets/full-stack-reference/skills/local/analysis-writing/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 an exemplar of lean, non-padded instruction for a simple, non-destructive writing skill. The only real gap is actionability: it gives clear rules but no concrete example of the expected output format or how an evidence reference should be cited.

Suggestions

Add one short before/after or worked example showing the expected comparison output and the exact form an evidence reference should take (e.g., '[Evidence #2, FY2024]'), so the rules translate directly into executable output.

Optionally add a final 'Verify' bullet (e.g., 'Confirm every conclusion has a cited reference and every missing period is noted as a limitation') to give the single task an explicit self-check.

DimensionReasoningScore

Conciseness

Four one-line imperatives with zero padding and no explanation of concepts Claude already knows; every token earns its place, matching the 'lean and efficient; assumes Claude's competence' anchor.

5 / 5

Actionability

The rules are concrete directives ("Keep the metric name, period, value, and unit unchanged," "Bind each conclusion to the evidence reference"), but as an instruction-only skill it stops short of showing an example output or the exact reference syntax, leaving a key executable detail implicit; this fits 'some concrete guidance but incomplete.'

3 / 5

Workflow Clarity

For a simple single-purpose skill the four bullets give a clear, ordered set of writing rules with an implicit self-check (state missing periods as limitations instead of filling gaps); there is no explicit validate/verify step, but the task is non-destructive, so it sits just below the explicit-checkpoint anchor at 5.

4 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, has no bundle files (no references/, scripts/, or assets/ directories exist), and is organized as a titled heading plus a tight bullet list; per the simple-skill guidance this earns a 5 with no external references needed.

5 / 5

Total

17

/

20

Passed

Description

62%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 is concise, uses a proper third-person 'Use when' trigger, and clearly bounds a narrow, distinctive task. Its main weakness is trigger-term breadth: a single scenario phrase rather than a richer set of natural keywords and synonyms a user would actually say.

Suggestions

Broaden the trigger terms to the natural phrases users say, e.g., add 'compare metrics/KPIs,' 'write analysis from data,' or 'benchmark business metrics' so the skill surfaces for more query phrasings.

Clarify the 'what' slightly more concretely (e.g., 'write a structured comparison of two or more business metrics, citing the evidence row/period for each claim') so the output shape is unambiguous.

DimensionReasoningScore

Specificity

Names the concrete action ("a business metric comparison must be written from structured evidence") and adds specifics like "explicit evidence references and limitations," giving several concrete dimensions of the task; minor coverage gaps keep it just below a comprehensive 5.

4 / 5

Completeness

It states both what (write a metric comparison from structured evidence with references and limitations) and when ("Use when a business metric comparison must be written..."), but the 'when' is a single scenario rather than a broad set of explicit trigger phrases, fitting the 'both what and when, when could be more specific' anchor.

4 / 5

Trigger Term Quality

It includes a clear "Use when" trigger and the phrase "business metric comparison," but it lacks the common variations and synonyms a user might naturally say (e.g., "compare metrics," "KPI comparison," "write analysis from data"), matching the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

The narrow framing of "business metric comparison" from "structured evidence" with "evidence references and limitations" is a fairly distinct niche with only minor overlap risk against general data-analysis or writing skills, fitting 'mostly distinct; minor overlap risk.'

4 / 5

Total

15

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
AgentEra/Agently-Skills
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.