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

75%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/person-dossier/SKILL.md

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 content is a well-structured, largely actionable workflow with genuine validation and error-recovery checkpoints. Its weaknesses are a triplicated recall/session-search paragraph that hurts conciseness and abstract (non-executable) guidance in the Granola and Brain-recall steps.

Suggestions

De-duplicate the "Use recall and the current session-search contract…" paragraph: state it once (e.g., in step 5) and reference it from step 4, and either give the Quick Build Command Set actual commands or remove it.

Make the Granola (step 4) and Brain-backed recall (step 5) steps executable by providing concrete recall/session-search command invocations or MCP argument examples instead of only abstract guidance.

Add an explicit output-verification checkpoint before finalizing the dossier (e.g., confirm every section has a Verified/Inferred provenance label and that open items all have an owner), turning the Quality Bar into a final validation step.

Dimension	Reasoning	Score
Conciseness	Most of the body is lean with concrete commands and no conceptual padding, but the recall/session-search paragraph is duplicated verbatim in steps 4, 5, and the Quick Build Command Set, and that final section contains no commands—just the repeated paragraph.	3 / 5
Actionability	Most steps give concrete, executable commands (secrets lease, joelclaw email inbox/read, granola meetings, joelclaw events) plus a full dossier template, but the Granola-detail and Brain-recall steps offer only abstract "use recall" guidance with no runnable command.	4 / 5
Workflow Clarity	The 10-step sequence is clear with explicit validation (auth check in step 1), an error-recovery branch (secrets service down), and blocker handling with explicit gaps and next-run commands, though there is no explicit output-verification checkpoint before finalizing the dossier.	4 / 5
Progressive Disclosure	The body is well-organized into clear sections (Trigger, Output Path, Workflow, Dossier Template, Quality Bar) and the bundle contains only logo assets with no nested references, but the ~190-line single file inlines the full template rather than splitting detail into one-level-deep reference files.	4 / 5
	Total	15 / 20 Passed

Description

83%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 clearly states both what the skill does and when to use it, with concrete trigger phrases and specific named evidence sources. Its main limitation is that several trigger terms are broad enough to risk overlap with adjacent planning/relationship skills.

Dimension	Reasoning	Score
Specificity	Lists concrete actions ("Build and update person dossiers", "write/update a structured dossier") and four named evidence sources (Front email, Granola summaries, scoped memory, event metadata), giving several specific actions with only minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what ("Build and update person dossiers…write/update a structured dossier in Vault/Resources/") and when ("Use when a person is discussed for strategy, follow-up, opportunities, relationship context, or decisions") with concrete trigger phrases.	5 / 5
Trigger Term Quality	The "Use when" clause surfaces natural terms a user would say ("strategy", "follow-up", "opportunities", "relationship context", "decisions"), with good keyword coverage but missing common synonyms or domain file extensions.	4 / 5
Distinctiveness Conflict Risk	The person-dossier niche and named sources (Front, Granola) are distinctive, but broad trigger terms like "strategy", "follow-up", and "decisions" create minor overlap risk with general planning or CRM-like skills.	4 / 5
	Total	17 / 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: 7094ced

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.