using-glean-productivity

Synthesize the user's own work activity, priorities, and recent context using Glean — use when the user asks about their recent work, what they accomplished, what is urgent, what needs their attention, or wants help with status updates, 1:1 prep, or weekly summaries. Trigger phrases include what have I been working on, what did I do last week, what should I focus on, summarize my week, help me with my status update, what's blocking me, morning briefing, what happened while I was out. Do not use for general enterprise queries (use the using-glean skill), for someone else's activity, or for project-status questions where the user is not the subject (use a project-awareness skill).

Quality

86%

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

72%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.

A concise, well-structured router skill with genuinely specific tool-level guidance, but it delegates nearly all workflow detail to reference files that are missing from the bundle, and it offers no explicit step sequence for the synthesis itself. Restoring the referenced files and adding a minimal inline example would lift the two mid-range dimensions.

Suggestions

Ship the referenced files (reference/activity.md, reference/priorities.md) or inline a minimal version of their guidance, since the body currently routes to paths that do not exist in the bundle.

Add a short numbered workflow (e.g., 1. classify the question shape, 2. query user_activity for the date range, 3. filter views vs. edits, 4. group by memory themes, 5. cite sources) so the sequence is explicit rather than implied.

Include one worked example (input question → tool calls → summary output) to make the synthesis pattern concrete and copy-adaptable.

Dimension	Reasoning	Score
Conciseness	The ~40-line body is lean and assumes Claude's competence — it spends zero tokens on what Glean or activity feeds are, and every line carries workflow-relevant instruction ("Surface creates / edits / decisions; demote pure views", "activity is retrospective, priorities are prospective"). Nothing is padded and no known concepts are re-explained.	5 / 5
Actionability	Concrete, executable guidance is present: named tools (`user_activity`, `meeting_lookup`, `search` with `from:me` / `owner:me`, `memory` with `RolesAndResponsibilities` and `ActiveProjects`) and specific rules ("A status update of 5 real accomplishments beats a list of 20 trivial activities"). It stops short of 5 because there are no example queries or a worked input/output example showing the synthesis in action.	4 / 5
Workflow Clarity	The two-shape taxonomy (activity vs. priorities) plus five cross-cutting rules imply a flow — classify the ask, consult the shape's reference, apply the rules — but no explicit step sequence is given and there are no checkpoints (e.g., how to verify a timeframe covers "last week"). It is above 2 because the classification and rules are clearly defined, but below 4 because the sequence remains implicit.	3 / 5
Progressive Disclosure	References are well-signaled and one level deep, but scored against the actual bundle structure, every referenced path — [reference/activity.md], [reference/priorities.md], and the five ../using-glean/reference/*.md links — is absent from the bundle, leaving the body a router over broken links. Not 4: the disclosure chain does not resolve to real files; not 2: the signaling and structure themselves are good.	3 / 5
	Total	15 / 20 Passed

Description

95%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.

An exemplary description: it answers what and when explicitly, includes a rich set of natural trigger phrases, uses third person, and proactively fences off adjacent skills with negative triggers. The only minor gap is that the "what" rests on a single composite verb rather than multiple enumerated actions.

Suggestions

Consider enumerating the concrete operations performed (e.g., "pulls user_activity, searches with from:me/owner:me, reads memory") to raise specificity from a composite verb to multiple distinct actions.

Dimension	Reasoning	Score
Specificity	"Synthesize the user's own work activity, priorities, and recent context using Glean" names the tool, concrete data objects, and deliverables ("status updates, 1:1 prep, or weekly summaries"), which is several specific actions with minor coverage gaps. It falls short of 5 because there is one primary verb rather than a comprehensive list of distinct concrete actions like the top anchor.	4 / 5
Completeness	Both halves are explicit: the what ("Synthesize the user's own work activity, priorities, and recent context using Glean") and the when ("use when the user asks about their recent work, what they accomplished, what is urgent…") with concrete trigger phrases. It even adds negative triggers, exceeding the anchor's requirement.	5 / 5
Trigger Term Quality	"what have I been working on, what did I do last week, what should I focus on, summarize my week, help me with my status update, what's blocking me, morning briefing, what happened while I was out" provides comprehensive natural-language phrasing users would actually say, plus task-category synonyms (status updates, 1:1 prep, weekly summaries).	5 / 5
Distinctiveness Conflict Risk	"Do not use for general enterprise queries (use the using-glean skill), for someone else's activity, or for project-status questions where the user is not the subject (use a project-awareness skill)" explicitly disambiguates against the nearest competing skills, establishing a clear personal-activity niche with minimal conflict risk.	5 / 5
	Total	19 / 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
relative_links	Relative link issues: 3 missing, 5 suspicious	Warning

	Total	15 / 16 Passed

Repository: gleanwork/claude-plugins
Path: plugins/glean/skills/using-glean-productivity/SKILL.md
Commit: a549de6

Reviewed: 5 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.