find-personalization-angles

Use when deriving evidence-backed outreach angles for a supplied contact from verified account context and dated research.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/find-personalization-angles/SKILL.md

Quality

Content

75%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.

This is a well-structured, actionable instruction-only skill with a clear gated workflow and concrete output format. Main improvements are reducing guardrail/workflow redundancy and adding a re-research feedback loop after angle rejection.

Suggestions

Dedupe the Guardrails against Workflow steps 4–6 so each constraint lives in one place, cutting token cost without losing safety coverage.

Add an explicit feedback loop: when angles are rejected as weak/generic in step 6, direct the model back to step 2 to seek stronger evidence before finalizing.

Tighten the Required inputs and Guardrails into checklist-style bullets so the gating constraints scan faster.

Dimension	Reasoning	Score
Conciseness	The body is dense and well-sectioned without explaining concepts Claude already knows, though the Guardrails repeat constraints already stated in the Workflow (e.g., not turning company activity into personal action), which could be trimmed.	4 / 5
Actionability	Concrete, structured guidance is given throughout—specific labels (Account context/Personal knowledge), status values (READY/STOP/NEEDS VERIFICATION), evidence ratings, and a copy-paste output template—leaving only minor gaps in execution detail.	4 / 5
Workflow Clarity	A clear 7-step sequence opens with an explicit eligibility/opt-out validation gate and closes with a Quality check checklist, but the reject-weak-angles step does not loop back to re-research, so the feedback loop is partial.	4 / 5
Progressive Disclosure	The single-file skill is well-organized into clearly labeled sections with no need for external references; it sits just over the simple-skill line, so it earns strong but not maximal structure marks.	4 / 5
	Total	16 / 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 gives a clear what-and-when statement for a distinct niche, but relies on domain jargon rather than natural user trigger phrases and lists only one concrete action. Tightening trigger terms and naming more capabilities would lift it.

Suggestions

Add natural trigger phrases users would actually say, such as "personalize outreach," "find personalization angles," or "draft tailored outreach," rather than only technical phrasing.

Name additional concrete actions (e.g., verify eligibility, label fact types, rate evidence strength) so capability coverage reads as comprehensive rather than single-action.

Make the "when" clause more concrete by listing the situations that call for this skill (e.g., when preparing sales outreach for a named contact with available account context).

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ("deriving evidence-backed outreach angles"), but does not enumerate multiple specific capabilities, so coverage is not comprehensive.	3 / 5
Completeness	It answers both what (deriving evidence-backed outreach angles) and when (explicit "Use when..." clause), but the trigger condition could be more specific with concrete trigger phrases.	4 / 5
Trigger Term Quality	Relevant keywords like "outreach angles," "contact," and "account context" appear, but the phrasing is domain jargon and misses the natural variations a user would say (e.g., "personalize outreach," "personalization angles").	3 / 5
Distinctiveness Conflict Risk	The niche (evidence-backed outreach personalization from verified account context) is clearly distinct, with only minor overlap risk against generic outreach or research skills.	4 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

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: llaskin/AI-SDR-Skill-Pack
Path: skills/find-personalization-angles/SKILL.md
Commit: 56ebfd3

Reviewed: ~23 hours ago

Table of Contents

Discovery Implementation Validation

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.