signal-detector

Always-on ambient signal capture. Applies on every substantive inbound message to detect original thinking and entity mentions. Spawn as a cheap sub-agent where the harness supports it; otherwise run detection inline. Aim to never block the main response.

Quality

60%

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 ./skills/signal-detector/SKILL.md

Quality

Content

61%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 and gives concrete, executable guidance with specific commands, but it is held back by editorial padding and the absence of validation checkpoints for its batch page-writing operations.

Suggestions

Add an explicit validation/verification step after batch page writes and back-link creation (e.g., confirm the page exists and the back-link resolves before logging the signal).

Trim editorial framing such as 'Ideas are the intellectual capital. Entities are bookkeeping. Both compound over time.' and avoid repeating the harness-routing caveat in both the Contract and the following paragraph.

Make the auto-link post-hook behavior concrete with the actual call sequence rather than a narrative description.

Dimension	Reasoning	Score
Conciseness	Mostly efficient operational content, but includes unnecessary editorializing ('Ideas are the intellectual capital. Entities are bookkeeping. Both compound over time.') and repeats the harness-routing caveat that already appears in the Contract.	3 / 5
Actionability	Provides concrete commands and formats ('gbrain search "name"', 'gbrain timeline-add <slug> <date> "<summary>"', 'put_page', 'originals/{slug}') and an explicit back-link format, with only minor narrative gaps such as the auto-link post-hook description.	4 / 5
Workflow Clarity	The three phases are clearly sequenced with numbered steps, but the skill batch-writes/enriches pages and creates back-links (mutating, writes_pages) without any validation or verification checkpoint, which per the guideline caps workflow clarity at 3.	3 / 5
Progressive Disclosure	Well-organized into clear sections with a single clearly-signaled one-level reference (the blockquote pointing to skills/conventions/quality.md for Iron Law back-linking); no bundle files are present, and the structure is appropriate for a single-file skill.	4 / 5
	Total	14 / 20 Passed

Description

58%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 is reasonably specific and distinct, but it lacks an explicit user-facing trigger clause and leans on internal/harness terminology rather than natural user keywords.

Suggestions

Add an explicit 'Use when...' clause with natural user-facing trigger phrases (e.g., 'Use when the user shares an idea, observation, or mentions a person/company worth capturing').

Surface the concrete capabilities the skill actually performs (create/enrich people/, companies/, concepts/ pages and back-links) so the action list is more comprehensive.

Replace internal phrasing like 'ambient signal capture' and 'substantive inbound message' with terms a user would naturally say when they need this skill.

Dimension	Reasoning	Score
Specificity	Names the domain (ambient signal capture) and several concrete actions ('detect original thinking and entity mentions', 'Spawn as a cheap sub-agent', 'run detection inline', 'never block the main response'), with minor gaps in coverage such as the full write-set of brain pages.	4 / 5
Completeness	The 'what' is clear (capture ideas and entity mentions) but there is no explicit 'Use when...' clause; the 'when' is only weakly implied via 'every substantive inbound message', which per the guideline caps completeness at 3.	3 / 5
Trigger Term Quality	Includes some relevant keywords ('original thinking', 'entity mentions', 'every substantive inbound message') but the terms are largely internal/harness-oriented rather than phrases a user would naturally say, and common variations are missing.	3 / 5
Distinctiveness Conflict Risk	Occupies a distinct niche (ambient brain/notes capture of original thinking and entities) with only minor overlap risk against closely related note-taking or entity-extraction skills.	4 / 5
	Total	14 / 20 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: garrytan/gbrain
Path: skills/signal-detector/SKILL.md
Commit: 055ac6c

Reviewed: 40 minutes 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.