briefing

Compile daily briefing with meeting context, active deals, and citation tracking

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/briefing/SKILL.md

Quality

Content

75%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 body is highly actionable with concrete gbrain commands, a clear pull-then-compose workflow, and an explicit output contract, including a retry loop for stale google sources. Its main weaknesses are duplicated sections (Phases vs. GBrain-Native Context Loading, Tools Used vs. frontmatter) and the absence of a final output-verification step.

Suggestions

Merge the 'Phases' and 'GBrain-Native Context Loading' sections (attendee search and deal queries are described twice) and drop the 'Tools Used' section that restates the frontmatter tool list.

Add an explicit final validation step after composition, e.g., verify every fact carries a '[Source: slug, updated DATE]' citation and every uncited claim is removed before presenting the briefing.

Consider moving the detailed pre-briefing pull specifications (0a-0e) into a referenced file to keep SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	Commands are lean and domain-specific, but content is duplicated: the 'Phases' and 'GBrain-Native Context Loading' sections repeat the same attendee-search and deal-query instructions, and 'Tools Used' restates frontmatter tool declarations. Mostly efficient but could be tightened — anchor 3, not 4 because the redundancy is more than a minor instance.	3 / 5
Actionability	Fully executable copy-paste commands throughout ('gbrain salience --days 7', 'gbrain recall --since-last-run --supersessions --pending --rollup --json'), a concrete output template, and an example citation format cover the common briefing cases — anchor 5.	5 / 5
Workflow Clarity	Clear sequence: pre-briefing pulls 0a-0e, then Phases 1-6, then a fixed output format, with an explicit error-recovery loop for the 'waiting' refusal ('run the sync it names, then retry'). Missing a final end-of-run verification (e.g., checking every fact carries a citation) keeps it below anchor 5; the skill is read-only so no destructive-operation cap applies.	4 / 5
Progressive Disclosure	Well-organized sections with one-level-deep, clearly signaled references ('skills/_brain-filing-rules.md', 'skills/google-loops/SKILL.md') and no nested chains. The ~190-line body inlines the pre-briefing pull details and duplicates phases content that could partly live in separate files — good structure with minor organization gaps, anchor 4.	4 / 5
	Total	16 / 20 Passed

Description

53%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 concretely states what the skill compiles but omits any 'when to use it' guidance, capping its completeness and usefulness for triggering. Trigger term coverage rests almost entirely on the single phrase 'daily briefing'.

Suggestions

Add a 'Use when...' clause (e.g., 'Use when the user asks for a daily or morning briefing or what's happening today') to raise completeness.

Include natural synonyms in the description itself — 'morning briefing', 'daily digest', 'what's happening today' — instead of relying solely on the triggers block.

Name one or two more concrete actions (e.g., 'surfaces contradictions, open loops, and stale pages with inline source citations') to broaden specificity.

Dimension	Reasoning	Score
Specificity	Names the domain ('Compile daily briefing') plus 2-3 concrete deliverables ('meeting context, active deals, and citation tracking'), matching the anchor for naming domain and a couple of concrete actions without comprehensive coverage. It is not a 4 because it does not enumerate several specific actions, and not a 2 because it goes beyond a bare domain label.	3 / 5
Completeness	The description gives a clear 'what' but contains no 'Use when...' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3. It is above a 2 because the 'what' is concrete rather than vague.	3 / 5
Trigger Term Quality	'daily briefing' is a natural phrase a user would say, but the description misses common variations such as 'morning briefing' or 'what's happening today' (which appear only in the separate triggers block, not the description). Some relevant keywords exist but synonyms are missing, fitting anchor 3 rather than 4's 'good keyword coverage'.	3 / 5
Distinctiveness Conflict Risk	The daily-briefing framing with brain context is a fairly distinct niche, though 'meeting context' and 'active deals' could overlap with meeting-prep or deal-tracking skills — minor overlap risk with closely related skills (anchor 4), not the minimal-conflict clarity of anchor 5.	4 / 5
	Total	13 / 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: garrytan/gbrain
Path: skills/briefing/SKILL.md
Commit: e78f1c3

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.