CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

netalertx-prd-writing

Rigorous PRD-writing methodology for NetAlertX — 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.

68

Quality

85%

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

73%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 well-sequenced, highly actionable methodology with genuine validation gates and recovery loops — its strongest dimension. The main cost is token efficiency: repeated statement of the same rules and long anecdotes make it heavier than it needs to be, and some of that material belongs in reference files.

Suggestions

State the test-first/red-confirmation rule fully once (Process step 7) and cross-reference it from the Structure checklist and 'Implementing an approved PRD' sections instead of restating it three times.

Move the extended anecdotes (the 'settings still applying' story in 'When to use', the index-finding and fixture examples) into a references/gotchas.md file and keep one-line pointers inline, slimming the ~18KB body.

Trim the step 3 log-vs-alert digression to the rule plus a one-line example, and cut the duplicated rationale between the Structure 'Implementation checklist' bullet and the 'Implementing an approved PRD' section.

DimensionReasoningScore

Conciseness

The body is dense and entirely project-specific (no explanations of concepts Claude already knows), but it repeats the 'write the test first, confirm it fails red' rule in full three times (Process step 7, the Structure checklist bullets, and 'Implementing an approved PRD') and carries long anecdotal asides that could be tightened, matching the 'mostly efficient but could be tightened' anchor rather than the noticeably-verbose one.

3 / 5

Actionability

Guidance is consistently concrete for an instruction-only skill — named commands ('grep CREATE INDEX', 'EXPLAIN QUERY PLAN'), real files ('server/scan/presence.py', 'test/db_test_helpers.py'), and copy-ready templates ('### Rejected: X', the save path, '**Status:** Draft — pending review') — with minor gaps such as the vague 'EnterPlanMode or an equivalent written plan' and no example PRD snippet.

4 / 5

Workflow Clarity

A 13-step numbered process plus a document structure template, with explicit validation checkpoints (the dedicated final-check pass and its bullet checklist), a red-test-first gate, and a concrete error-recovery loop ('actually revert the implementation, confirm the test fails red... then reapply') — matching the top anchor's sequence, validation, feedback loops, and checklists.

5 / 5

Progressive Disclosure

Sections are clearly headed and coherent with no nested or buried references, but at ~75 dense lines the long inlined anecdotes and implementation detail could be split into a one-level-deep references file, fitting the 'good structure; minor organization gaps' anchor.

4 / 5

Total

16

/

20

Passed

Description

88%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 description: it comprehensively enumerates the methodology's concrete actions, uses third person, and pairs a clear what with an explicit when. Its only weaknesses are a few missing natural synonyms (e.g. 'spec') and minor trigger overlap with generic doc-writing requests.

DimensionReasoningScore

Specificity

The description lists six distinct 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' — comprehensively covering the methodology with no gaps, in third-person voice.

5 / 5

Completeness

It explicitly answers both what the skill does (the enumerated methodology actions) and when to use it ('Use this when asked to write, draft, or review a PRD, design doc, or feature proposal') with concrete trigger phrases — an exact match for the top anchor.

5 / 5

Trigger Term Quality

Natural trigger terms are present ('write, draft, or review a PRD, design doc, or feature proposal'), but common synonyms such as 'spec' or 'specification' are missing, which keeps it just short of the comprehensive-synonym coverage of the top anchor.

4 / 5

Distinctiveness Conflict Risk

'Rigorous PRD-writing methodology for NetAlertX' establishes a clear niche, but fairly generic trigger verbs like 'review a design doc' or 'feature proposal' create minor overlap risk with general design-doc/documentation skills, fitting the 'mostly distinct' anchor rather than the minimal-conflict one.

4 / 5

Total

18

/

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

netalertx/NetAlertX

Path

.github/skills/prd-writing/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.