CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

to-prd

Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

78%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 a lean, well-structured instruction skill: it forbids unnecessary user interviews, gives a concrete PRD template, and includes a user checkpoint mid-workflow. Its only real weaknesses are minor redundancy in the user-stories section and the unspecified publish mechanics, which depend on an external setup skill.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence — no basic concepts are explained, and the PRD template is the actual deliverable spec, earning its tokens. Minor trims exist: the worked user-story example duplicates the already-given format line, and "extremely extensive and cover all aspects" repeats "A LONG, numbered list".

4 / 5

Actionability

As an instruction-only skill the guidance is concrete: a copy-paste PRD template with per-section directives, a specific label to apply ('ready-for-agent'), and a clear seam-selection strategy. The main gap is that publishing mechanics to the issue tracker are delegated entirely to an external setup skill, leaving the publish step itself without executable detail.

4 / 5

Workflow Clarity

The three-step process (explore repo → sketch seams → write and publish) is clearly sequenced, with an explicit mid-flow checkpoint: 'Check with the user that these seams match their expectations.' There is no post-publish verification step, so it lands on 'clear sequence with most checkpoints present' rather than the explicit-validation level 5.

4 / 5

Progressive Disclosure

This is a single-purpose, self-contained skill with no bundle files and no content that belongs in separate files — the template legitimately lives inline. Sections (Process, template, What happens next) are well-organized and easy to navigate, and the referenced commands (/setup-matt-pocock-skills, /to-tickets, /implement) are clearly signaled rather than buried.

5 / 5

Total

17

/

20

Passed

Description

62%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 concise, in third person, and answers both what the skill does and when to use it. Its main weaknesses are limited action coverage (two verbs) and thin trigger-term vocabulary — only "PRD" appears, with no synonyms or spelled-out forms to catch varied user phrasing.

Suggestions

Add one or two more concrete actions to the capability list, e.g., 'apply the ready-for-agent triage label' or 'synthesize codebase context into user stories', to move specificity beyond two verbs.

Broaden trigger terms to include natural synonyms such as 'product requirements document', 'requirements doc', or 'write a spec', so the skill fires on varied user phrasing.

Make the when-clause more distinctive by tying it to the workflow handoff, e.g., 'Use when the user wants to turn the current discussion into a PRD before implementation, not when they want tickets or code.'

DimensionReasoningScore

Specificity

The description names two concrete actions — "Turn the current conversation context into a PRD" and "publish it to the project issue tracker" — which matches the 1-2 concrete actions anchor. It does not list several specific actions (e.g., applying triage labels, synthesizing codebase context), so it falls short of the level-4 anchor.

3 / 5

Completeness

The description has a clear 'what' (synthesize a PRD from context and publish it) and an explicit 'Use when user wants to create a PRD from the current context' clause. However, the when-clause is a single trigger that largely restates the what rather than providing concrete distinct trigger phrases, placing it between the level-4 and level-5 anchors — closer to 4.

3 / 5

Trigger Term Quality

"PRD" and "create a PRD" are natural terms a user would say, but coverage stops there — no common variations or synonyms such as "product requirements document", "requirements doc", or "spec" are included. This matches the 'some relevant keywords but missing common variations' anchor rather than the good-coverage level 4.

3 / 5

Distinctiveness Conflict Risk

"Turn the current conversation context into a PRD and publish it to the project issue tracker" carves out a clear niche with a distinct trigger ("create a PRD"). There is minor overlap risk with closely related planning skills in the same kit (e.g., to-tickets, implement), which matches the 'mostly distinct; minor overlap risk' anchor rather than the minimal-conflict level 5.

4 / 5

Total

13

/

20

Passed

Validation

100%

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

agranado2k/ai-report-platform

Path

.agents/skills/to-prd/SKILL.md

Reviewed

Table of Contents

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.