CtrlK
BlogDocsLog inGet started
Tessl Logo

match-icp

Use when applying supplied account and contact ICP gates to records or auditing eligibility decisions before scoring or outreach.

68

Quality

83%

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

92%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 content is a tight, well-structured audit procedure with explicit decision rules, a concrete output format, and a validation checklist for the batch operation. Only minor redundancy between the workflow and guardrails keeps conciseness from a perfect score.

Suggestions

De-duplicate the score-override rule: keep it in the guardrails and trim the restatement in workflow step 7 to recover a conciseness point.

Consider a one-line worked example row in the output format table to make the expected ledger fully unambiguous.

DimensionReasoningScore

Conciseness

The body is lean and procedural with no padding about what an ICP is or how matching works. Below 5 because there is minor redundancy between workflow step 7 and the guardrails (e.g. 'no score can qualify a record' vs 'Do not let ... any score override a failed gate'); above 3 because nearly every line is actionable instruction that earns its place.

4 / 5

Actionability

As an instruction-only skill it provides concrete, executable guidance: explicit gate categories, exact decision rules ('Return INELIGIBLE when any required gate is FAIL or MISSING'), a copy-paste output format with named columns, and PASS/FAIL/MISSING statuses. It is not 4 because the guidance fully specifies execution for the common case without gaps.

5 / 5

Workflow Clarity

The 7-step workflow is clearly sequenced and the batch operation includes an explicit validation checklist ('Quality check') and a 'list all failed checks rather than stopping' instruction, so the batch-cap does not apply. Not 4 because a concrete checklist and explicit validation are present; it is appropriately an audit (output, not mutate), so no fix-retry loop is required.

5 / 5

Progressive Disclosure

The body is well-organized into clearly labeled sections (Purpose, Required inputs, Workflow, Output format, Guardrails, Quality check) with no nested or buried references and no bundle files that need signaling. Not 4 because structure is clean and appropriately self-contained; nothing is inlined that belongs in a separate file.

5 / 5

Total

19

/

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 specific, distinct, and answers both what and when with an explicit Use-when clause. Its main weakness is modest action coverage and a "when" clause that partially restates the what rather than adding separate trigger phrases.

Suggestions

Add a couple more concrete actions (e.g. 'flag missing evidence' or 'return auditable PASS/FAIL/MISSING gate statuses') to lift specificity toward comprehensive coverage.

Separate the trigger from the action so the when reads as natural user phrasing, e.g. 'Use when qualifying accounts against an ICP, auditing lead eligibility, or preparing scoring/outreach lists.'

DimensionReasoningScore

Specificity

It names the domain ("account and contact ICP gates", "eligibility decisions") and two concrete actions (applying gates to records, auditing decisions), but coverage is not comprehensive. Below 4 because there are only ~2 actions rather than several; above 2 because both actions are domain-specific rather than generic.

3 / 5

Completeness

It states both what (applying ICP gates / auditing eligibility decisions) and when ("Use when ... before scoring or outreach"). Below 5 because the "when" largely restates the action rather than offering distinct concrete trigger phrases; above 3 because the when is explicit, not merely implied.

4 / 5

Trigger Term Quality

Natural domain terms like "records", "scoring", "outreach", and "eligibility decisions" appear and would be said by the target rev-ops audience. Below 5 because common synonyms/variations (e.g. "ideal customer profile", "qualifying leads") are absent; above 3 because the term set is relevant and reasonably natural, not just jargon.

4 / 5

Distinctiveness Conflict Risk

The ICP-gate / eligibility-audit framing is a clear niche with distinct triggers and minimal overlap risk with generic skills. It is not a neighboring-anchor 4 because the account/contact gate and hard-disqualifier language is highly specific rather than only "mostly distinct".

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.