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/.
91
88%
Does it follow best practices?
Impact
98%
1.40xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly articulates what the skill does (builds person dossiers from communication history), when to use it (when discussing a person for strategy, follow-up, opportunities, etc.), and how it works (pulling from specific named sources and writing to a specific location). It uses third person voice correctly and provides enough specificity to be clearly distinguishable from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Build and update person dossiers', 'pull evidence from Front email, Granola meetings, memory recall, and event logs', 'write/update a structured dossier in Vault/Resources/'. Names specific tools and output locations. | 3 / 3 |
Completeness | Clearly answers both what ('Build and update person dossiers from communication history... pull evidence... write/update a structured dossier') and when ('Use when a person is discussed for strategy, follow-up, opportunities, relationship context, or decisions') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'person', 'dossier', 'strategy', 'follow-up', 'opportunities', 'relationship context', 'decisions'. Also includes specific source names (Front email, Granola meetings) that users would reference. Good coverage of when someone is discussing a contact or relationship. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: person dossiers built from specific sources (Front email, Granola meetings) stored in a specific location (Vault/Resources/). The combination of person-focused intelligence gathering from named tools makes this unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill with clear workflow sequencing, concrete CLI commands, and robust error handling. Its main weakness is length—some content is duplicated (quick command set vs. workflow steps, required sections vs. template) and the entire skill could benefit from splitting into a concise overview with referenced detail files. The evidence provenance system (Verified/Inferred) and blocker handling are particularly well-designed.
Suggestions
Remove the 'Required Sections' list (lines duplicated by the template) and the 'Quick Build Command Set' (duplicates workflow commands) to reduce redundancy.
Consider extracting the dossier template into a separate `DOSSIER_TEMPLATE.md` file and referencing it, to keep the main skill leaner and improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with concrete commands and structured sections, but includes some redundancy—the 'Quick Build Command Set' at the end largely duplicates commands already shown in the workflow steps. The 'Required Sections' list is also redundant with the template. Some tightening possible. | 2 / 3 |
Actionability | Fully actionable with specific, copy-paste-ready CLI commands for every data source (Front, Granola, memory, events). The dossier template is concrete with exact field names and formats. Update rules are specific and unambiguous. | 3 / 3 |
Workflow Clarity | Clear 10-step sequence with explicit validation (step 1 for auth), blocker handling with fallback strategy (step 10), deduplication rules, and update-in-place logic with merge semantics. The feedback loop for blocked states includes recording errors, attempting fallbacks, and producing explicit gap documentation. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and logical sections, but it's a long monolithic file (~170 lines) with no references to external files. The dossier template, quick command set, and detailed workflow steps could be split into separate referenced files for better organization. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- joelhooks/joelclaw
- Commit
03f0a59
- Reviewed
Table of Contents
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.