project-awareness
Quick project context — surface a project's status, owner, recent activity, and key links. Use when the user wants a fast situational read on a project, not a deep handoff document.
55
62%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/glean-project/skills/project-awareness/SKILL.mdQuality
Discovery
75%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 solid description that clearly communicates both what the skill does and when to use it, with a helpful negative boundary that aids disambiguation. Its main weaknesses are moderate specificity in the actions listed and missing some natural trigger terms users might employ when requesting project overviews or summaries.
Suggestions
Add more natural trigger term variations users might say, such as 'project summary', 'project overview', 'catch me up on [project]', or 'what's the status of'.
Make the concrete actions slightly more specific — e.g., 'pull latest commits, summarize open issues, list team members and roles, and compile relevant links' instead of the more abstract 'surface status, owner, recent activity, and key links'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (project context) and lists some actions (surface status, owner, recent activity, key links), but these are somewhat general and not deeply concrete operations like 'generate reports' or 'query databases'. | 2 / 3 |
Completeness | Clearly answers both what ('surface a project's status, owner, recent activity, and key links') and when ('when the user wants a fast situational read on a project'), and even includes a negative boundary ('not a deep handoff document') to distinguish scope. | 3 / 3 |
Trigger Term Quality | Includes some natural terms like 'project's status', 'owner', 'recent activity', 'key links', and 'situational read', but misses common variations users might say such as 'project summary', 'project overview', 'what's happening with', 'catch me up on', or 'project update'. | 2 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche by specifying 'quick project context' and explicitly distinguishing itself from deeper handoff documents, making it unlikely to conflict with more comprehensive project documentation skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable framework for project awareness queries via Glean, with useful query patterns and output templates. Its main weaknesses are the overly verbose skepticism section that reads more like a policy document than actionable guidance, and the lack of a clear sequential workflow tying the various query approaches together. The tool call examples are helpful but their parameter accuracy is uncertain without the referenced Glean core documentation.
Suggestions
Condense the 'BE SKEPTICAL' section into a compact checklist (e.g., 3-4 bullet points) rather than four separate multi-line tests — Claude can apply judgment without this level of scaffolding.
Add an explicit sequential workflow: e.g., '1. Start with chat query → 2. Evaluate freshness of results → 3. If insufficient, use targeted search/employee_search → 4. Cross-reference and format output.'
Confirm that tool parameters like 'updated', 'sort_by_recency', and 'app' match the actual Glean MCP tool schema, or note them as illustrative examples.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill has some unnecessary verbosity, particularly the extensive 'BE SKEPTICAL' section with its multi-tiered evaluation framework (Currency/Authority/Ownership/Cross-Reference tests) which is overly detailed for what Claude can reasonably assess. The trigger examples ('What's the status of...', 'Who owns...') are somewhat redundant. However, the query patterns and output formats are reasonably tight. | 2 / 3 |
Actionability | The query patterns provide concrete examples of tool calls (chat, search, employee_search), and the output format templates are copy-paste ready. However, the tool call syntax is not fully specified — parameters like 'updated' and 'sort_by_recency' are shown without confirming they match the actual Glean MCP tool schema, and the skill defers full param documentation to another skill's reference files. The skepticism framework is conceptual rather than executable. | 2 / 3 |
Workflow Clarity | There's a reasonable progression from quick chat queries to deeper investigation combining multiple tools, but the workflow lacks explicit sequencing and validation checkpoints. There's no clear 'first do X, then check Y, then proceed to Z' structure — it's more of a menu of options. The skepticism section acts as a validation framework but isn't integrated into a step-by-step workflow. | 2 / 3 |
Progressive Disclosure | The skill references the 'using-glean' skill's reference files for tool details and mentions related commands at the end, which is good progressive disclosure. However, the inline content is somewhat long — the extensive skepticism framework and dual output format templates could potentially be split out. The cross-references to related commands at the bottom are well-signaled. | 2 / 3 |
Total | 8 / 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
- gleanwork/claude-plugins
- Commit
39a5c99
- 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.