person-dossier

Build and update person dossiers from communication history. Use when a person is discussed for strategy, follow-up, opportunities, relationship context, or decisions. Automatically pull evidence from Front email, Granola meetings, memory recall, and event logs; then write/update a structured dossier in Vault/Resources/.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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.

The content is a well-structured, actionable multi-step workflow with executable commands, validation at auth, and a blocker-handling feedback loop. It loses points mainly for the redundant "Quick Build Command Set" section and placeholder-only command examples rather than worked ones.

Suggestions

Remove or fold the "Quick Build Command Set" section into the workflow, since it duplicates commands already shown in steps 3-6, to recover conciseness.

Add at least one worked example with concrete values (a sample person name, a real-looking cnv_id, a sample query) so the commands are copy-paste ready rather than placeholder-only.

Add an explicit post-write validation step (e.g. re-read the dossier and confirm the stable-key dedupe merged correctly) to close the workflow_clarity checkpoint gap for this batch/multi-source operation.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean — commands and short directives with no concept over-explanation — but the "Quick Build Command Set" repeats commands already shown in the workflow, adding some redundancy; not a 5 because of that duplication, not a 3 because the rest is efficient and assumes Claude's competence.	4 / 5
Actionability	Provides concrete, executable commands throughout (e.g. `joelclaw email inbox -q "<person name>" -n 200`, `granola meetings --range this_month`) with flags and a full template; not a 5 because several commands use unfilled placeholders ("<person name>", "<cnv_id>") rather than worked examples.	4 / 5
Workflow Clarity	Ten clearly numbered steps with an auth validation checkpoint ("secrets status" plus fallback) and a blocker-handling feedback loop (record error, try fallback, surface gaps); not a 5 because the dossier update step lacks an explicit post-write validation/re-read loop, leaving a minor checkpoint gap in a batch/multi-source operation.	4 / 5
Progressive Disclosure	A single self-contained SKILL.md with well-organized sections and an inline template appropriate for this scope; no references/ or scripts/ bundle files exist (only asset logos), so content is appropriately placed, though the sizable template block is inline rather than split out.	4 / 5
	Total	16 / 20 Passed

Description

92%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 strong: it states concrete capabilities, provides explicit "Use when..." triggers covering natural user phrasings, and carves out a distinct niche with named data sources. The only minor gap is trigger-term synonym coverage, which keeps it just short of a perfect trigger-term score.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Build and update person dossiers", "Automatically pull evidence from Front email, Granola meetings, memory recall, and event logs", "write/update a structured dossier") with comprehensive coverage of the skill's behavior.	5 / 5
Completeness	Explicitly answers both what ("Build and update person dossiers from communication history") and when ("Use when a person is discussed for...") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural triggers a user would say ("a person is discussed for strategy, follow-up, opportunities, relationship context, or decisions"), with good keyword coverage but missing some synonym variations; not a 5 because the trigger list, while natural, is not exhaustive of phrasings.	4 / 5
Distinctiveness Conflict Risk	A clear niche (person dossiers) with named sources (Front, Granola, memory recall, event logs) and distinct triggers, giving minimal conflict risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: joelhooks/joelclaw
Path: skills/person-dossier/SKILL.md
Commit: d952451

Reviewed: 4 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.