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 an excellent skill description that clearly articulates what the skill does (builds person dossiers from multiple communication sources), when to use it (when discussing a person for strategy, follow-up, opportunities, etc.), and where outputs go (Vault/Resources/). It uses third person voice correctly, includes natural trigger terms, and occupies a distinct niche that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple 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/'. Specific data sources and output location are named. | 3 / 3 |
Completeness | Clearly answers both what ('Build and update person dossiers from communication history... pull evidence from Front email, Granola meetings, memory recall, and event logs; write/update a structured dossier') and when ('Use when a person is discussed for strategy, follow-up, opportunities, relationship context, or decisions'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'person', 'dossier', 'strategy', 'follow-up', 'opportunities', 'relationship context', 'decisions', 'communication history'. Also names specific tools (Front email, Granola meetings) that users would reference. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: person dossiers built from specific communication sources (Front, Granola) stored in a specific location (Vault/Resources/). Unlikely to conflict with other skills due to the unique combination of person-focused intelligence gathering and structured output. | 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 commands, and good validation/error handling. Its main weaknesses are moderate redundancy (the quick build command set duplicates workflow commands) and the monolithic structure that could benefit from splitting the template and reference material into separate files. The evidence provenance system and blocker handling are particularly well-designed.
Suggestions
Remove or consolidate the 'Quick Build Command Set' section since it duplicates commands already present in the workflow steps, or move it to a separate quick-reference file.
Consider extracting the Dossier Template into a separate file (e.g., DOSSIER_TEMPLATE.md) and referencing it from the main skill to improve progressive disclosure and reduce file length.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but has some redundancy—the 'Quick Build Command Set' at the end repeats commands already shown in the workflow steps. Some sections like 'Resolve identifiers' and 'Normalize extracted data' could be tightened. However, it avoids explaining concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides fully concrete, executable bash commands for every data-gathering step, specific flags and parameters, a complete markdown template for the output, and clear update rules with deduplication logic. Everything is copy-paste ready. | 3 / 3 |
Workflow Clarity | The 10-step workflow is clearly sequenced with explicit validation (step 1 checks auth/secrets), blocker handling with fallback strategies (step 10), update rules that prevent data loss (step 8), and evidence/confidence tracking (step 9). The feedback loop for blocked states is well-defined with 'no silent partials' as a clear constraint. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and headers, but it's a long monolithic file (~150 lines of content) that could benefit from splitting the dossier template and quick reference commands into separate files. No external references are used despite the complexity warranting them. | 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
ce9ca8e
- 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.