CtrlK
BlogDocsLog inGet started
Tessl Logo

define-icp

Use when deriving an account and contact ideal customer profile from supplied market, customer, qualification, or exclusion evidence.

64

Quality

76%

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/define-icp/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 a tight, well-structured instruction skill with an actionable workflow, an explicit output template, and guardrails. It would benefit from a worked example filling the output template and tighter dedup of the guardrail/quality-check overlap.

Suggestions

Add one worked example that fills the output template end-to-end (e.g., a short Northstar Relay trace showing Inclusion, Exclusion, Evidence, Unknowns, and Decision rule populated).

Collapse the Guardrails and Quality check sections so protected-trait rejection and traceability are stated once rather than restated.

DimensionReasoningScore

Conciseness

Lean and instruction-focused with no over-explanation of ICP concepts Claude already knows; minor redundancy between the Guardrails and Quality check sections keeps it just below the top anchor.

4 / 5

Actionability

Concrete numbered workflow steps, an explicit missing-evidence rule (return INELIGIBLE), and a copy-paste markdown output template give mostly executable guidance; no worked example populates the template, which is the gap to the top anchor.

4 / 5

Workflow Clarity

A clear 7-step sequence with a Quality check checkpoint and explicit missing-evidence handling; this is an analytical single-record decision, not a destructive/batch operation, so the workflow-cap does not apply, but there is no validate-fix-retry feedback loop for the top score.

4 / 5

Progressive Disclosure

Under 50 lines, single-purpose, with well-organized labeled sections (Purpose, Required inputs, Workflow, Output format, Guardrails, Quality check, Example invocation) and no need for external reference files.

5 / 5

Total

17

/

20

Passed

Description

73%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, third-person, and uses an explicit 'Use when' trigger tied to concrete evidence types. It is distinctive but merges the what and when into one clause and lists only one primary action.

Suggestions

Split the trigger from the action so the 'what' and 'when' read as distinct clauses, e.g. 'Derive an account and contact ideal customer profile. Use when supplied market, customer, qualification, or exclusion evidence for ICP work.'

Add the abbreviation 'ICP' alongside 'ideal customer profile' to broaden natural trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain (account and contact ICP) and one concrete action ('deriving an ... ideal customer profile'), then enumerates input evidence types rather than multiple distinct actions, matching the anchor for naming a domain with 1-2 concrete actions.

3 / 5

Completeness

Both 'what' (deriving an ICP) and 'when' ('Use when ... from supplied ... evidence') are present, but they are fused into a single clause rather than the separately explicit what-then-when phrasing of the top anchor.

4 / 5

Trigger Term Quality

Strong natural keywords a user would say ('ideal customer profile', 'account and contact', 'qualification ... or exclusion evidence') with good coverage, though it omits some common synonyms and abbreviations like 'ICP' itself.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (evidence-based ICP definition) with distinct trigger language and minimal overlap risk with other skills.

5 / 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
llaskin/AI-SDR-Skill-Pack
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.