to-prd

Turn the current conversation into a PRD and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.

0.00x

Quality

53%

Does it follow best practices?

Impact

0.00x

Average score across 1 eval scenario

Securityby

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/to-prd/SKILL.md

Quality

Content

50%Scale 1-3

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

This skill provides a reasonable workflow for synthesizing a PRD from conversation context, with a useful template and a good checkpoint at the seam-identification step. However, it lacks concrete tool/command specifics for publishing to the issue tracker, includes some unnecessary verbosity in the template instructions, and misses validation steps after the publishing action. The inline template bloats the file when it could be referenced separately.

Suggestions

Add concrete commands or tool invocations for publishing to the issue tracker (e.g., specific GitHub CLI commands or MCP tool calls) rather than the vague 'publish it to the project issue tracker'.

Add a validation step after publishing (e.g., 'Confirm the issue was created and the `ready-for-agent` label was applied by reading back the issue').

Extract the PRD template into a separate file (e.g., PRD_TEMPLATE.md) and reference it from the skill to improve conciseness and progressive disclosure.

Remove the explanatory padding in the template (e.g., 'This list of user stories should be extremely extensive and cover all aspects of the feature') — Claude understands thoroughness from the format itself.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient but has some unnecessary verbosity — the user story example is somewhat redundant given Claude's knowledge, and phrases like 'A LONG, numbered list' and 'This list of user stories should be extremely extensive' are padding. The template section is reasonably lean but could be tighter.	2 / 3
Actionability	The process steps are clear but lack concrete executable commands — 'publish it to the project issue tracker' and 'Apply the ready-for-agent triage label' are vague without specifying which tool/command to use (e.g., a specific CLI command or API call). The PRD template is concrete and well-structured, but the process around it relies on assumed context (issue tracker setup, `/setup-matt-pocock-skills`).	2 / 3
Workflow Clarity	The 3-step process is clearly sequenced with a user checkpoint at step 2 (checking seam expectations), which is good. However, there's no validation after publishing the PRD (e.g., confirming the issue was created successfully, verifying the label was applied), and the prerequisite check ('run /setup-matt-pocock-skills if not') is vague rather than an explicit validation step.	2 / 3
Progressive Disclosure	The PRD template is inline rather than in a separate referenced file, which makes the SKILL.md longer than necessary. The skill references external setup (`/setup-matt-pocock-skills`) and mentions domain glossary/ADRs but doesn't clearly signal where these live. For a standalone skill with no bundle files, the inline template is acceptable but the organization could be improved.	2 / 3
	Total	8 / 12 Passed

Description

57%Scale 1-3

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 communicates a clear and distinctive action — synthesizing a conversation into a PRD and publishing it — but lacks an explicit 'Use when...' clause and misses common trigger term variations like 'product requirements document', 'spec', or specific tracker names. It's concise and uses third person voice appropriately, but would benefit from expanded trigger coverage and explicit usage guidance.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to write up, summarize, or formalize what was discussed into a PRD or product requirements document.'

Include common trigger term variations such as 'product requirements document', 'spec', 'requirements doc', 'write up our discussion', and specific tracker names like 'Jira', 'Linear', or 'GitHub Issues' to improve matching.

Dimension	Reasoning	Score
Specificity	It names a specific action ('Turn the current conversation into a PRD and publish it to the project issue tracker') and mentions synthesis, but doesn't list multiple concrete sub-actions beyond the high-level flow. The 'no interview, just synthesis' clause adds some specificity about the approach.	2 / 3
Completeness	The 'what' is reasonably clear (synthesize conversation into a PRD and publish to issue tracker). However, there is no explicit 'Use when...' clause or equivalent trigger guidance — the when is only implied by the description of the action itself.	2 / 3
Trigger Term Quality	Includes relevant terms like 'PRD', 'issue tracker', 'conversation', and 'synthesis', which users might naturally use. However, it misses common variations like 'product requirements document', 'spec', 'requirements', 'Jira', 'Linear', 'GitHub issues', or 'write up what we discussed'.	2 / 3
Distinctiveness Conflict Risk	The combination of conversation-to-PRD synthesis plus publishing to an issue tracker is a fairly distinct niche. The 'no interview, just synthesis' qualifier further distinguishes it from skills that might conduct a PRD interview or simply create documents without publishing.	3 / 3
	Total	9 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: coder/agent-tty
Path: .agents/skills/to-prd/SKILL.md
Commit: ebff2c2

Reviewed: 1 day 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.