reports

Save and load timestamped reports. Keyword routing for fast lookup. Cron jobs save output as reports; the agent or user queries them by keyword. Includes the Actionability Gate: delivery-time link checks (Broken/Dead/Indirect/ Missing) for briefings, meeting digests, and research reports.

Quality

73%

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/reports/SKILL.md

Quality

Content

81%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 well-structured, actionable, and built around a clear validation feedback loop, with concrete templates and commands supporting the workflow. Its only real weaknesses are a couple of under-specified steps (latest-file lookup, keyword-routing mechanism) and slight verbosity in the retry-loop prose.

Suggestions

Specify the 'Load latest' step with a concrete mechanism (e.g. list/glob the category directory and pick the max-timestamped file) rather than 'find the most recent report file'.

Tighten the retry-loop section into a compact numbered checklist to trim the prose while preserving the validation steps.

Clarify how keyword routing resolves a query to a category (e.g. a lookup table or matching rule) so the actionability is fully executable.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence — it defines a domain-specific failure taxonomy Claude would not already know rather than padding with generic concepts, with only minor sections (e.g. the retry-loop prose) that could be trimmed.	4 / 5
Actionability	Provides concrete file-path templates, a frontmatter schema, real commands (`git status`, `gbrain get <slug>`), and a copy-paste gate snippet; minor gaps remain where 'find the most recent report file' and keyword routing lack exact mechanisms.	4 / 5
Workflow Clarity	The retry loop is an explicit 5-step sequence with validation checkpoints (scan links → fix → re-check → max 2 retries → deliver with warning), a clear feedback loop for error recovery on the delivery workflow.	5 / 5
Progressive Disclosure	Well-organized into clearly headed sections with one-level-deep external references signaled inline (`skills/_output-rules.md`, `skills/briefing/SKILL.md`); no bundle files exist, and the inline Actionability Gate is justified as core content, leaving only minor organization gaps.	4 / 5
	Total	17 / 20 Passed

Description

66%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 clearly conveys what the skill does and carves out a distinctive niche via the Actionability Gate, with solid trigger-term coverage. Its main weakness is the absence of an explicit "Use when..." trigger clause, which limits the completeness score.

Suggestions

Add an explicit 'Use when...' sentence naming concrete triggers (e.g. 'Use when saving or loading timestamped reports, routing keyword queries to report categories, or validating links in briefings, meeting digests, and research reports').

Include natural user-facing synonyms/file cues (e.g. 'latest report', 'morning briefing', 'report links') to lift trigger-term quality toward comprehensive.

Tighten 'Keyword routing for fast lookup' into more user-natural phrasing to reduce technical jargon.

Dimension	Reasoning	Score
Specificity	Names the report domain plus several concrete actions — "Save and load timestamped reports", "Keyword routing for fast lookup", and "delivery-time link checks (Broken/Dead/Indirect/Missing)" — with only minor gaps in coverage.	4 / 5
Completeness	The "what" is clearly stated, but there is no "Use when..." clause or equivalent explicit trigger guidance — the "when" is only weakly implied by "Cron jobs save output as reports", which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Good natural-term coverage ("briefings, meeting digests, and research reports", "save and load reports") though it leans on some technical phrasing like "Keyword routing" and omits a few common synonyms.	4 / 5
Distinctiveness Conflict Risk	The Actionability Gate link-checking niche plus timestamped report storage is a fairly distinct specialization, with only minor overlap risk against generic note/report skills.	4 / 5
	Total	15 / 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/reports/SKILL.md
Commit: 055ac6c

Reviewed: about 2 hours 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.