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

—

Does it follow best practices?

Impact

99%

1.02x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is lean, concrete, and well-structured for an instruction-only workflow skill, with exact file conventions and clear sectioning. Its main weakness is the absence of explicit validation/verification checkpoints for destructive and shared-write operations.

Suggestions

Add an explicit verification step before deleting an inflight file (e.g., confirm the matching /done/ entry was written and reads back correctly) to close the destructive-operation loop.

Add a verification checkpoint after appending to shared files (/prd.md, /questions.md) — e.g., re-read the appended block to confirm it landed intact — since these are live, concurrent-edit files.

Specify what to do if a validation/verification check fails (a fix-and-retry path) rather than only describing the happy-path write sequence.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept explanations Claude already knows and no padding; every section (layout, rules, identity, workflows) earns its place.	3 / 3
Actionability	Provides concrete file paths and exact formats (e.g. '/inflight/<handle>/<slug>.md', '<!-- @<handle> YYYY-MM-DD STATUS: open -->') with specific file_replace instructions; concrete and actionable instruction-only guidance.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced, but destructive and shared-write operations (deleting the inflight file, appending to shared files) lack explicit validation/verification feedback loops, capping clarity at 2.	2 / 3
Progressive Disclosure	Self-contained, well-organized into clearly labeled sections with no nested or deeply-referenced bundle files; appropriate structure for a compact, single-purpose workflow skill.	3 / 3
	Total	11 / 12 Passed

Description

100%

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 third-person, concise, and clearly states both capabilities and explicit trigger conditions for a well-scoped niche. It is a strong, low-conflict description.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete actions ('Read and update the team's shared PRD', 'start a new work item, mark something complete, or add an open question'), matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly states both what it does ('Read and update the team's shared PRD') and when to use it via an explicit 'Trigger when' clause, satisfying the what-AND-when anchor.	3 / 3
Trigger Term Quality	Uses natural user phrasings ('asks about current/inflight/done work', 'wants to start a new work item', 'mark something complete', 'add an open question') with broad coverage, matching the strong trigger-term anchor.	3 / 3
Distinctiveness Conflict Risk	The niche is sharply scoped to the 'team-prd AFS workspace' with per-dev subdir isolation, giving it clear distinct triggers unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 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
Commit: 990b8eb

Reviewed: 3 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.