signal-detector

Opt-in ambient signal capture. After explicit enablement, applies on substantive inbound messages to detect original thinking and entity mentions. Use an authorized sub-agent where supported; otherwise detect inline. Aim to never block the main response.

Quality

65%

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/signal-detector/SKILL.md

Quality

Content

67%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 a well-structured, actionable operational guide with concrete commands, explicit gating rules, phased workflows, and verification steps. Its main weaknesses are redundant hedging about conventions vs. guarantees and repeated opt-in rules across three sections, plus a missing fix/retry loop around the readback verification for its mutating writes.

Suggestions

Collapse the convention-vs-guarantee paragraph to a single sentence and merge the opt-in rules stated in Contract, Enablement, and Per-User Storage Policy into one authoritative section, cutting roughly a quarter of the body's tokens.

Add an explicit fix/retry step after the readback verification (e.g., 'If the readback does not match the exact phrasing, rewrite the page and verify again') to close the feedback loop for mutating batch writes.

Define the notability check concretely (what makes an entity worth a page) and the format for recording an accepted capture choice, since both are currently left to judgment.

Dimension	Reasoning	Score
Conciseness	The body is mostly directive, but the convention-vs-guarantee paragraph states the same hedge twice ('not a mechanical guarantee' appears twice in one paragraph) and opt-in rules are repeated across the Contract, Enablement, and Per-User Storage Policy sections. Fits 'Mostly efficient but includes some unnecessary explanation or could be tightened'; more than the minor trims of level 4, far less padded than level 2.	3 / 5
Actionability	Concrete commands are given ('gbrain search "name"', 'gbrain timeline-add <slug> <date> "<summary>"'), concrete page paths ('originals/{slug}'), a copy-paste back-link format template, and signal-log output examples. Minor gaps (notability criteria and the format for recording an accepted scope are undefined) keep it below the fully-specified level 5.	4 / 5
Workflow Clarity	A clear phased sequence (Phase 1 detection → Phase 2 entities → Phase 3 logging) with real checkpoints: check the stored capture choice before writing, check page existence before enriching, and 'verify captured content with an actual readback'. Falls short of level 5 because there is no explicit fix/retry loop after the readback despite mutating batch writes.	4 / 5
Progressive Disclosure	No bundle files exist, and the single file is well organized with clear section headers and one clearly signaled external reference ('See skills/conventions/quality.md'). Level 4 ('Good structure; most content appropriately placed') fits best; not level 5 because the referenced path lies outside this bundle and the ~137-line body carries content that could be split.	4 / 5
	Total	15 / 20 Passed

Description

62%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 communicates an opt-in, non-blocking capture pass for ideas and entity mentions, with explicit trigger conditions. Its weaknesses are jargon-heavy phrasing ('ambient', 'substantive inbound messages') that users would not naturally say, and omission of the concrete downstream actions (page creation, back-linking, timeline entries) that define the skill's actual effect.

Suggestions

Add 1-2 concrete downstream actions to the description (e.g., 'creates and back-links brain pages for captured ideas and entities, and logs timeline entries') to lift specificity from naming the domain to listing what the skill actually does.

Include at least one natural user-facing trigger phrase (e.g., 'Use when the user asks to remember or capture an idea, person, or company') alongside the runtime opt-in condition.

Replace or supplement jargon terms like 'ambient signal capture' and 'substantive inbound messages' with everyday synonyms users would actually say.

Dimension	Reasoning	Score
Specificity	Names the domain ('ambient signal capture') and two concrete detection actions ('detect original thinking and entity mentions') but omits the downstream actions the body actually performs (page creation, back-linking, timeline logging). This matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive' rather than the level-4 anchor requiring several specific actions.	3 / 5
Completeness	The 'what' is clear ('detect original thinking and entity mentions') and explicit trigger guidance exists ('After explicit enablement, applies on substantive inbound messages'), so the missing-'Use when' cap does not apply. Not level 5 because the 'when' is a runtime condition rather than concrete user-facing trigger phrases.	4 / 5
Trigger Term Quality	'Original thinking' and 'entity mentions' are relevant keywords, but 'ambient signal capture' and 'substantive inbound messages' are internal jargon rather than phrases a user would naturally say. Matches 'Some relevant keywords but missing common variations or synonyms'; not level 4 because natural user phrasings like 'capture my ideas' or 'remember this' are absent.	3 / 5
Distinctiveness Conflict Risk	The opt-in ambient-capture niche with idea/entity detection is clearly distinguishable from generic document or memory skills, with only minor overlap risk with general memory/recall capabilities. Fits 'Mostly distinct; minor overlap risk with closely related 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: 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.