team-prd

Read and update the team's shared PRD in the team-prd AFS workspace. Trigger when the user asks about current/inflight/done work, wants to start a new work item, mark something complete, or add an open question to the team's spec. Enforces per-dev subdir isolation to avoid write conflicts between multiple developers' agents.

1.02x

Quality

93%

Does it follow best practices?

Impact

99%

1.02x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

93%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, highly actionable workflow doc with concrete paths and templates. The only weak spot is the absence of an explicit post-write/post-delete verification step in the destructive 'marking done' and shared-file edit workflows.

Suggestions

Add an explicit verification step after deleting the inflight file in 'Marking an item done' (e.g. confirm /done/<date>-<slug>.md was written before deleting, or re-list /inflight/<handle>/ to confirm removal).

Add a verify-before-replace checkpoint in the shared-file edit rule (e.g. confirm the target block still matches before running file_replace), since the workspace is live and state may have changed.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout; never explains what a PRD or a workspace is, and every section (layout, rules, identity, workflows) earns its place with no padding.	5 / 5
Actionability	Provides fully executable guidance: concrete file paths (/inflight/<handle>/<slug>.md, /done/<YYYY-MM-DD>-<slug>.md), copy-ready templates with owner markers, and specific file_replace instructions for shared-file edits.	5 / 5
Workflow Clarity	Start-item, mark-done, and add-question workflows are clearly sequenced with guardrail checkpoints ('read existing files under /inflight/ to make sure nobody else is already working on it', 're-read the relevant shared file'), but the destructive delete in 'marking done' and the file_replace edit lack an explicit post-write verification step, leaving a minor validation gap.	4 / 5
Progressive Disclosure	A single well-organized overview file with clear section headers and no nested references; the skill has no need for external bundle files, so the one-level structure is appropriate and easy to navigate.	5 / 5
	Total	19 / 20 Passed

Description

92%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, concrete description that names specific actions, an explicit trigger clause, and a distinguishing mechanism. The only minor gap is breadth of natural trigger synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Read and update', 'start a new work item', 'mark something complete', 'add an open question' — plus the concrete mechanism of 'per-dev subdir isolation to avoid write conflicts', giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Clearly states what the skill does ('Read and update the team's shared PRD... Enforces per-dev subdir isolation') and explicitly answers when with concrete trigger phrases ('Trigger when the user asks about...').	5 / 5
Trigger Term Quality	Natural trigger phrasing is explicit ('Trigger when the user asks about current/inflight/done work, wants to start a new work item, mark something complete'), matching what a user would say; a few common variations (e.g. 'what is everyone working on') are not covered, keeping it just short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (the team-prd AFS workspace, per-dev subdir isolation) with distinct, specific triggers that are unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 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: redis/agent-filesystem
Path: examples/plugins/afs-team-prd/skills/team-prd/SKILL.md
Commit: c23daa6

Reviewed: 13 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.