scout

File system watcher and AST parser. Detects changes in the watched repository, extracts AST structure using tree-sitter, and emits structured ChangeEvents for the Architect to process.

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 ./workspace/skills/scout/SKILL.md

Quality

Content

72%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 concise and well-structured with clean progressive disclosure to real bundle scripts, but it reads as a component manifest rather than actionable instructions — lacking executable examples, an explicit run sequence, and validation checkpoints.

Suggestions

Add a short runnable example showing how to instantiate and start RepoWatcher/ASTParser, or a command that launches the scout.

Make the processing pipeline explicit as numbered steps (watch → filter → debounce → parse → emit) so the sequence is unambiguous.

Include a verification step for confirming ChangeEvents are emitted to the MessageBus, since batch event processing benefits from a feedback checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-organized with no padding or explanation of concepts Claude already knows; even the 'zero LLM calls' note earns its place as a non-obvious fact.	5 / 5
Actionability	Concrete structural guidance is present (named files, classes RepoWatcher/ASTParser, libraries watchdog/tree-sitter, a 500ms debounce window, supported extensions) but there is no executable code or invocation example to act on directly.	3 / 5
Workflow Clarity	The capabilities bullet list implies a pipeline (watch → filter → debounce → parse → emit) but no explicit sequence, invocation steps, or validation checkpoints are given, and the skill is a multi-component pipeline rather than a single unambiguous action.	3 / 5
Progressive Disclosure	Under 50 lines with clear sections and a Scripts manifest pointing one level deep to real bundle files (watcher.py, parser.py, events.py, all present) each with a one-line description, giving easy navigation to implementation detail.	5 / 5
	Total	16 / 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 is specific and technically clear about what the Scout does, but omits any explicit 'when to use' trigger guidance, which limits completeness and trigger-term quality. It is reasonably distinctive within its multi-agent niche.

Suggestions

Add a 'Use when...' clause naming natural triggers, e.g. 'Use when monitoring a repository for file changes or when AST structure is needed for change events'.

Include common synonyms/extensions users might say ('watch files', 'repo changes', 'diff detection') to broaden trigger-term coverage.

Mention the supported file types (.py, .js, .ts) in the description to sharpen distinctiveness from generic watchers.

Dimension	Reasoning	Score
Specificity	Names the domain and three concrete actions — 'Detects changes in the watched repository, extracts AST structure using tree-sitter, and emits structured ChangeEvents' — with only minor coverage gaps (filtering/debouncing from the body are absent).	4 / 5
Completeness	The 'what' is clearly stated but there is no 'Use when...' or equivalent trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant terms like 'file system watcher', 'detects changes', and 'AST' are present but lean technical (tree-sitter, ChangeEvents) and lack common synonyms or extensions a user might naturally say.	3 / 5
Distinctiveness Conflict Risk	The combination of tree-sitter AST extraction and ChangeEvents 'for the Architect to process' is a clear niche with minor overlap risk against generic file-watching skills, though bare 'file system watcher' is somewhat broad.	4 / 5
	Total	14 / 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: tombrewsviews/repository-os-mvp
Path: workspace/skills/scout/SKILL.md
Commit: a30d1b4

Reviewed: ~20 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.