signal-capture

Detect and capture technical preferences, naming conventions, and architectural practices from user messages into Packmind standards. Trigger when user prescribes HOW to code through direct statements (e.g., "Use snake_case for columns", "Always use async/await") or suggestive patterns like questions ("Could we use X instead?"), code review feedback ("This would be clearer with X"), and comparative statements ("Use X instead of Y"). Does NOT trigger for feature requests, bug reports, or general implementation tasks without coding preferences.

Quality

86%

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

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 highly actionable with a clear, validated workflow and concrete copy-paste examples. Its main weakness is conciseness — repeated trigger listings and long inline worked examples inflate the token budget without proportional value.

Suggestions

Consolidate the trigger examples into a single canonical list; the checklist, 'When to Trigger', and example preambles currently restate the same triggers three times.

Move the four detailed worked-example scenarios (with full YAML + goodExample/badExample blocks) into a references file, keeping one compact representative example inline in SKILL.md.

Tighten the 'Failure Example' section to a few lines — the current annotated transcript restates behavior already covered by the workflow steps.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and instructional (no padding explaining what KISS/DRY are), but trigger examples recur across three sections (checklist, 'When to Trigger', and embedded examples) and the four full YAML scenarios add length that could be consolidated.	3 / 5
Actionability	Provides a concrete YAML schema with per-field requirements, exact validation-prompt wording, and four fully worked copy-paste-ready examples including goodExample/badExample code for ADDED, UPDATED, and DELETED operations.	5 / 5
Workflow Clarity	Steps 1–4 (Detection → Validation → Log → Confirmation) are clearly sequenced with an explicit mandatory validation checkpoint (user approval before logging), a trigger checklist, and a clarification sub-loop for abstract principles.	5 / 5
Progressive Disclosure	Well-organized with clear section headers and no nested references, but all content lives inline in a single ~320-line file with no overview/detail split or external reference files for the lengthy example scenarios.	4 / 5
	Total	17 / 20 Passed

Description

91%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.

A strong, well-structured description that clearly states what the skill does, when to trigger it, and when not to, using natural varied trigger phrases. Its only soft spot is a slightly limited set of concrete actions beyond detect/capture.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions ('Detect and capture technical preferences, naming conventions, and architectural practices ... into Packmind standards') with several specific capture targets, though the action set itself is limited to detect/capture rather than a comprehensive list.	4 / 5
Completeness	Explicitly answers both 'what' (detect and capture preferences into Packmind standards) and 'when' ('Trigger when user prescribes HOW to code through ...'), reinforced by concrete negative triggers ('Does NOT trigger for feature requests, bug reports ...').	5 / 5
Trigger Term Quality	Includes natural phrases users actually say across multiple synonym categories — direct statements ('Use snake_case for columns'), questions ('Could we use X instead?'), review feedback ('This would be clearer with X'), and comparative statements ('Use X instead of Y').	5 / 5
Distinctiveness Conflict Risk	Clear niche (capturing coding-preference signals into standards) with explicit non-trigger boundaries that reduce overlap risk; minor residual overlap with general code-review or coding-assistant skills.	4 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: cteyton/packmind
Path: .claude/skills/signal-capture/SKILL.md
Commit: e198635

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.