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

63%

Does it follow best practices?

Impact

0.00x

Average score across 1 eval scenario

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/to-prd/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 content is lean, actionable, and well-structured around a clear four-step process with an inlined PRD template. The main gap is the absence of a validation/feedback loop for the outward-facing publish step, which caps workflow clarity.

Suggestions

Add a post-publish verification step (e.g., confirm the issue was created with the 'ready-for-agent' label and that the PRD renders correctly) to satisfy the batch/destructive-operation feedback-loop requirement.

Tighten the seam-selection explanation so the rationale is as terse as the rest of the body.

Consider an explicit 'abort and re-check with the user' branch if the seam check fails, to make the existing checkpoint a true feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is lean and directive ('Do NOT interview', 'Use the highest seam possible', 'Do NOT include specific file paths') without over-explaining concepts Claude already knows; only minor sentences (the seams rationale) could be trimmed further.	4 / 5
Actionability	As an instruction-only skill it provides a concrete inlined PRD template with explicit sections and a worked user-story example, plus specific commands like applying the 'ready-for-agent' triage label; the seam-selection step is slightly more abstract, leaving a minor gap.	4 / 5
Workflow Clarity	The four steps are clearly sequenced with a pre-publish user checkpoint on seams, but publishing a PRD to the issue tracker is an outward-facing/batch action with no post-publish verification or feedback loop, so workflow clarity is capped at 3 per the batch-operation guideline.	3 / 5
Progressive Disclosure	No bundle files are present and none are needed; the self-contained body is well-organized with clear sections and a single appropriately inlined PRD template, meeting the simple-skill exception for a 5.	5 / 5
	Total	16 / 20 Passed

Description

53%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 clearly states what the skill does and stakes out a distinct PRD-synthesis niche, but lacks an explicit invocation trigger ('Use when...') and broader keyword coverage. Adding a when-clause and a few synonyms would lift the weaker dimensions.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when the user asks to turn a conversation into a PRD or feature spec').

Include common synonyms such as 'product requirements doc', 'spec', or 'feature doc' alongside 'PRD' for broader trigger coverage.

Optionally enumerate a couple more concrete actions (e.g., 'draft user stories', 'publish to the issue tracker with a ready-for-agent label') to strengthen specificity.

Dimension	Reasoning	Score
Specificity	Names the domain ('PRD') and two concrete actions ('Turn the current conversation into a PRD' and 'publish it to the project issue tracker'), but coverage is limited to those two actions rather than comprehensive.	3 / 5
Completeness	Has a clear 'what' (synthesize a PRD and publish it), but no explicit 'Use when...' or equivalent trigger clause, so completeness is capped at 3 per the judging guideline.	3 / 5
Trigger Term Quality	Includes relevant terms like 'PRD', 'conversation', and 'issue tracker' that a user might say, but misses common synonyms and variations such as 'product requirements doc', 'spec', or 'feature doc'.	3 / 5
Distinctiveness Conflict Risk	The combination of 'PRD' and 'project issue tracker' defines a mostly distinct niche with only minor overlap risk against related writing/spec skills.	4 / 5
	Total	13 / 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: coder/agent-tty
Path: .agents/skills/to-prd/SKILL.md
Commit: ebff2c2

Reviewed: ~14 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.