team-brief

Generate daily team intelligence brief by cross-referencing GitHub, Linear, Slack, PostHog, meetings, and braindumps with two-way Linear sync-back

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/team-brief/SKILL.md

Quality

Content

70%

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 a clearly sequenced multi-phase workflow and real safety checkpoints, but it is a monolithic ~885-line file with no progressive disclosure and notable redundancy. Splitting large reusable blocks into reference files and de-duplicating the Slack templates would materially improve it.

Suggestions

Move each agent's prompt block into its own reference file (e.g. references/github-analyst.md) and keep SKILL.md as an overview that links to them, enabling one-level-deep progressive disclosure.

De-duplicate the Monday and regular-day Slack message templates into a single parameterized template to cut substantial redundancy.

Extract the full metadata template and the 23 synthesis rules into a references file (e.g. references/synthesis-rules.md) so the main skill body stays lean.

Dimension	Reasoning	Score
Conciseness	The ~885-line body is mostly concrete operational detail (not explanations of concepts Claude knows), but is padded with redundancy such as near-identical Monday vs. regular-day Slack templates and repeated 'If Monday' lines across every agent prompt.	2 / 3
Actionability	Provides executable gh CLI commands, concrete HogQL queries, exact Linear MCP tool names, and curl/Python HackMD snippets with clearly marked [CUSTOMIZE: ...] placeholders — largely copy-paste ready.	3 / 3
Workflow Clarity	Phases are clearly sequenced with timing, fallback, and error handling, and risky batch write operations (Linear sync-back, Slack posting) have explicit safety rules, duplicate-prevention, and confirm-before-post checkpoints.	3 / 3
Progressive Disclosure	No bundle files exist and the entire skill is one ~885-line monolith — full agent prompts, Slack templates, metadata templates, and 23 synthesis rules are all inline with no external references or navigation, matching the monolithic-wall anchor.	1 / 3
	Total	9 / 12 Passed

Description

67%

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 clearly conveys the skill's concrete capabilities and distinctive niche, but it omits explicit 'when to use' trigger guidance and the natural trigger phrases users would actually say (those live in the body instead). Adding a 'Use when...' clause with natural terms would lift the completeness and trigger-term dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks for a team brief, team update, standup prep, or wants to know what the team shipped.'

Include natural-language trigger terms ("team brief", "what did we ship", "standup prep") directly in the description rather than only in the body.

Keep the existing source enumeration but pair it with the when-to-use phrasing so both what and when are explicit in the description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and enumerates six specific data sources (GitHub, Linear, Slack, PostHog, meetings, braindumps) plus a concrete 'two-way Linear sync-back' action, matching the multi-action anchor.	3 / 3
Completeness	Clearly answers what the skill does, but lacks any 'Use when...' clause or equivalent explicit trigger guidance; per the rubric this caps completeness at 2.	2 / 3
Trigger Term Quality	Names relevant product keywords (GitHub, Linear, Slack, PostHog) but omits natural phrasings users would actually say ('team brief', 'what did we ship', 'standup prep'), which only appear in the body, not the description.	2 / 3
Distinctiveness Conflict Risk	The specific combination of a daily team intelligence brief across six named sources with two-way Linear sync-back is a clear, distinctive niche unlikely to conflict with other skills.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (893 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: huytieu/COG-second-brain
Path: .claude/skills/team-brief/SKILL.md
Commit: dfbf9e9

Reviewed: 2 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.