CtrlK
BlogDocsLog inGet started
Tessl Logo

prd-writing

Rigorous PRD-writing methodology — challenge the idea, verify every claim against actual code, trace every downstream consumer of a mechanism, evaluate performance impact against the schema/indexes that actually exist, record rejected alternatives and open-issue decisions explicitly, and do a dedicated final-check pass before calling it done. Use this when asked to write, draft, or review a PRD, design doc, or feature proposal for this codebase.

71

Quality

86%

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

The canonical home for this skill is prd-writing in netalertx/NetAlertX

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 rigorous, well-structured methodology skill with excellent workflow sequencing and a genuine final-check validation pass. It is actionable and avoids basic-concept padding, though step 9's performance guidance is dense enough that it could be tightened or split into a reference file.

Suggestions

Move the detailed performance/index reasoning in step 9 into a references/ file (e.g. PERFORMANCE.md) and summarize the rule inline, reducing body length while keeping the detail one level deep.

Tighten step 9 by leading with the actionable rule ('grep every CREATE INDEX on the tables involved; check EXPLAIN QUERY PLAN against the full real index set at production scale') and demoting the illustrative index names to an example.

DimensionReasoningScore

Conciseness

Mostly efficient methodology prose that assumes Claude's competence and avoids explaining basic concepts, but step 9 is a long wall of codebase-specific detail that could be trimmed without losing the load-bearing guidance.

4 / 5

Actionability

Gives concrete, executable guidance — naming real files/functions ('server/scan/presence.py', 'current_scan_presence_condition()', 'test/db_test_helpers.py') and specific commands ('EXPLAIN QUERY PLAN', 'grep CREATE INDEX') — with only minor gaps typical of process guidance rather than copy-paste code.

4 / 5

Workflow Clarity

Eleven clearly sequenced process steps culminating in a dedicated final-check pass (step 10) with an explicit checklist and a re-verify feedback loop, plus a correction-trail step — matching the anchor for explicit validation and checklists.

5 / 5

Progressive Disclosure

No bundle files exist, so structure is judged on the body itself; it is well-sectioned (When to use, Core principle, Process, Structure, Before starting, Where to save) and self-contained, with only minor organization gaps such as the lengthy step 9 that could live in a reference file.

4 / 5

Total

17

/

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, specific description that clearly states both capability and trigger conditions in third person. It is dense but every clause names a concrete action rather than vague fluff. The only gap is a missing natural synonym ('spec') the body itself treats as a trigger.

Suggestions

Add 'spec' or 'spec out' to the trigger clause in the description, since the body already lists 'spec out this feature' as a trigger phrase.

Consider tightening the long action list into a shorter lead clause plus examples to reduce density without losing specificity.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'challenge the idea, verify every claim against actual code, trace every downstream consumer of a mechanism, evaluate performance impact against the schema/indexes that actually exist, record rejected alternatives and open-issue decisions explicitly, and do a dedicated final-check pass' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both what (the rigorous methodology and its concrete actions) and when ('Use this when asked to write, draft, or review a PRD, design doc, or feature proposal for this codebase').

5 / 5

Trigger Term Quality

Includes natural phrases users say ('write, draft, or review a PRD, design doc, or feature proposal') with good synonym coverage, but omits 'spec' even though the body lists 'spec out this feature' as a trigger, leaving a few natural terms missing.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (PRD/design-doc writing scoped to this codebase) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

19

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
netalertx/NetAlertX
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.