people-crm

Turn LinkedIn connections (or any contact export) into a queryable personal CRM using the agent database.

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/personal/people-crm/SKILL.md

Quality

Content

82%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 highly actionable with executable SQL and clear workflow checkpoints for a database skill, and is well-structured and concise with only minor padding. Main gap is the absence of an explicit write-verification feedback loop and the lack of any reference files that could offload the longer example blocks.

Suggestions

Add an explicit write verification step (e.g. re-query the row after an UPDATE/INSERT to confirm the change landed) to form a validate->fix->retry loop for destructive operations.

Consider moving the larger SQL example collections (relationships graph queries, the ISO-date migration) into a references/ file referenced one level deep to keep SKILL.md an overview.

Trim the justificatory opener ('This is the right tool because ...') or fold it into the When to Use section to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	Largely lean and assumes Claude's SQL/database competence, with only minor over-explanation ('This is the right tool because ...' rationale and the optional LinkedIn-date Tip block) that could be trimmed; not a 5 because of those small padded spots.	4 / 5
Actionability	Provides fully executable, copy-paste-ready db_import / db_query / db_execute commands and complete SQL covering import, querying, person tracking, and relationship graphs across the common cases.	5 / 5
Workflow Clarity	Clear sequenced sections with real checkpoints for a destructive/batch database skill (db_schema confirm, truncated->LIMIT/OFFSET, ambiguous-name disambiguation, confirm before bulk update); not a 5 because there is no explicit write verify->fix->retry feedback loop.	4 / 5
Progressive Disclosure	No bundle files exist, yet the body is well-organized into clearly-signaled sections (When to Use / Not, Getting data in, Querying, Tracking, Relationships, Rules) with no nested references; not a 5 because the ~100-line single-file body is longer than the under-50-line simple-skill threshold that would auto-qualify for 5.	4 / 5
	Total	17 / 20 Passed

Description

53%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 clearly states what the skill does and carves out a distinct niche, but it omits an explicit 'Use when...' trigger clause and lacks common synonyms, which caps completeness and trigger-term quality at 3.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when the user wants to remember, query, or track their contacts/network, or asks who do I know at X'.

Broaden trigger terms with synonyms users naturally say: 'contacts', 'network', 'who do I know', 'introductions', in addition to 'LinkedIn connections'.

List 1-2 more concrete actions (e.g. 'track who people are over time', 'map who-knows-whom') to lift specificity from one action toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ('Turn LinkedIn connections ... into a queryable personal CRM') but lists no further capabilities, matching 'names domain and 1-2 concrete actions, not comprehensive'; not a 4 because only a single action is given.	3 / 5
Completeness	Gives a clear 'what' but provides no 'Use when...' trigger clause, so per the missing-trigger-guidance rule completeness is capped at 3 ('clear what, when missing or weakly implied').	3 / 5
Trigger Term Quality	Includes natural terms 'LinkedIn connections', 'contact export', and 'personal CRM', but misses common synonyms users would say like 'contacts', 'network', or 'who do I know'; not a 4 because keyword coverage has clear gaps.	3 / 5
Distinctiveness Conflict Risk	Targets a clear niche (personal CRM built from contact exports via the agent database) with low conflict risk; not a 5 because of minor possible overlap with general memory/database skills.	4 / 5
	Total	13 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: Open-Curiosity/gini-agent
Path: skills/personal/people-crm/SKILL.md
Commit: 6c5d85e

Reviewed: 3 days 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.