watch

Create a research watch baseline and optionally schedule follow-up checks when scheduling tools are visible. Use when the user asks to monitor a field, track new papers, watch for updates, or set up alerts on a research area.

Quality

82%

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

86%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.

A tight, well-structured delegation skill that tells Claude exactly what to run, where output lands, and how to handle the unavailable-scheduling case without any padding. The main limitation is that real execution detail lives inside the /watch workflow rather than in the body.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — every line (run /watch, agents used, output location, scheduling fallback) earns its place with no padding or concept explanation, matching the top anchor.	5 / 5
Actionability	Gives concrete, executable direction ('Run the `/watch` workflow', output to `outputs/`, condition on `schedule_prompt` visibility) but delegates the actual steps to the slash command rather than providing copy-paste-ready detail, so it sits below a 5.	4 / 5
Workflow Clarity	The sequence is clear (invoke workflow → baseline output → conditional follow-up) with a fallback checkpoint ('If scheduling is unavailable... records that block instead of claiming a recurring watch exists'); not a 5 because there is no explicit validation/feedback loop.	4 / 5
Progressive Disclosure	Under 50 lines with no need for external references, and the content is well organized into clear labeled sections (title, agents, output), qualifying for the top anchor under the simple-skill exception.	5 / 5
	Total	18 / 20 Passed

Description

78%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 well-formed description that clearly states both capability and trigger conditions with natural user phrasing. It is slightly light on the breadth of concrete actions and could risk minor overlap with adjacent research/scheduling skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('research watch baseline') and two concrete actions ('Create a research watch baseline', 'schedule follow-up checks'), matching the anchor that lists 1-2 concrete actions but is not comprehensive; it stops short of score 4's 'several specific actions'.	3 / 5
Completeness	Explicitly answers both what ('Create a research watch baseline and optionally schedule follow-up checks') and when ('Use when the user asks to monitor a field, track new papers...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural phrases users would say — 'monitor a field', 'track new papers', 'watch for updates', 'set up alerts' — giving good keyword coverage; not a 5 because no file extensions or additional synonyms are present.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (research watching/alerts) with distinct triggers and minimal overlap risk; not a 5 because 'monitor'/'track'/'alerts' could overlap with general research or scheduling skills.	4 / 5
	Total	16 / 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: companion-inc/feynman
Path: skills/watch/SKILL.md
Commit: 95c51d9

Reviewed: about 8 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.