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. Use relevant authorized evidence from Front email, Granola summaries, scoped memory, and event metadata; then write/update a structured dossier in Vault/Resources/.

Quality

81%

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

67%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 skill body is a well-structured, largely executable 10-step workflow with explicit auth validation, provenance rules, and blocker handling — rare discipline around evidence labeling and "no silent partials." Its weaknesses are the triple-repeated recall/session-search boilerplate (including a "Quick Build Command Set" section with no commands), missing concrete syntax for the recall source, and a dead-end in step 4's per-meeting instructions.

Suggestions

State the recall/session-search contract once (e.g., in a short "Evidence access rules" section) instead of repeating the identical paragraph in steps 4, 5, and Quick Build Command Set.

Add the concrete per-meeting Granola command after "For each candidate meeting ID:" and show an example recall/session-search invocation with argument structure so the recall steps are executable rather than descriptive.

Either populate "Quick Build Command Set" with the actual command sequence or remove the section; move the 44-line dossier template to a references/ file (e.g., references/dossier-template.md) to slim the main SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean command-driven prose, but the identical paragraph "Use `recall` and the current `session-search` contract. Keep private queries in structured MCP arguments. Raw evidence requires a scope-bound `evidenceDrilldownReceipt`…" is repeated verbatim three times (steps 4, 5, and "Quick Build Command Set"), and the "Quick Build Command Set" section contains no commands at all — noticeable tightening opportunities that fit "mostly efficient but includes some unnecessary explanation or could be tightened."	3 / 5
Actionability	Most steps are copy-paste ready (e.g., "joelclaw email inbox -q \"<person name>\" -n 200", "secrets lease front_api_token --ttl 15m", "granola meetings --range this_week"), but the recall/session-search steps provide no concrete invocation syntax, and step 4 says "For each candidate meeting ID:" then never supplies the per-meeting command — minor gaps keeping it below fully executable anchor 5.	4 / 5
Workflow Clarity	The 10-step workflow is clearly sequenced with an upfront auth validation checkpoint ("secrets status", "secrets lease…") and a blocker-recovery step ("record exact technical error text… try authorized event metadata or scoped recall… produce a blocked dossier"), matching "clear sequence with most checkpoints present"; it falls short of anchor 5 only because there is no verification checkpoint after the dossier is written.	4 / 5
Progressive Disclosure	The body is well-sectioned and self-contained with no bundle references (the references/ and scripts/ directories don't exist and no paths are cited), but the ~44-line inline "Dossier Template" is content that could live in a separate reference file — good structure with a minor organization gap rather than the ideal split of anchor 5.	4 / 5
	Total	15 / 20 Passed

Description

87%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, names its evidence sources and output location, and includes an explicit "Use when…" clause with natural trigger terms. It is clearly distinct from other skills. The only improvement space is broader synonym coverage in the trigger terms and a slightly fuller enumeration of actions.

Dimension	Reasoning	Score
Specificity	"Build and update person dossiers from communication history" and "write/update a structured dossier in Vault/Resources/" are concrete actions, and the sources are named ("Front email, Granola summaries, scoped memory, and event metadata"), but the action list is less comprehensive than the anchor-5 example, so this sits at "several specific actions; minor gaps."	4 / 5
Completeness	It explicitly answers both what ("Build and update person dossiers from communication history… write/update a structured dossier in Vault/Resources/") and when ("Use when a person is discussed for…") with concrete trigger phrases, matching the anchor-5 example structure; there is no missing when-clause to cap it at 3.	5 / 5
Trigger Term Quality	"Use when a person is discussed for strategy, follow-up, opportunities, relationship context, or decisions" gives good natural keywords a user would say, but misses common variations/synonyms (e.g., "dossier", "background", "who is", person names), matching "good keyword coverage; a few natural terms missing" rather than the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	"Build and update person dossiers" from named personal sources (Front email, Granola summaries) is a clear niche with distinct triggers and minimal overlap with other skills, matching the anchor-5 "clear niche with distinct triggers" example.	5 / 5
	Total	18 / 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: aa0116c

Reviewed: 8 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.