CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

aet-req-analysis

Requirements analysis skill - transforms raw requirements into structured specifications through Socratic dialogue, behavior analysis, and requirement specification design. Use when: (1) requirements are unclear or need decomposition, (2) you need to produce a requirements analysis specification from user input, (3) you need structured functional and non-functional requirements with priority labels, (4) you need acceptance criteria and test case definitions, or any requirements clarification and specification generation tasks.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./jiuwenclaw/jiuwenswarm/agents/harness/code/rails/sdd/design_rail/skills/aet-req-analysis/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

52%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 skill body presents a clear, well-gated three-stage pipeline with concrete tool invocations and unusually precise skip/error semantics, and it largely avoids teaching Claude things it already knows. Its main weaknesses are moderate redundancy in the rule sections and a bundle-navigation failure: the workflow SOPs it depends on are absent while every real bundle file (references/, scripts/) is left unreferenced and undiscoverable.

Suggestions

Fix the bundle references: either add the workflows/sop-*.md files to the bundle or remove the "absolute path in the Skill File Index section below" pointers and add an actual file index section listing real paths (workflows/, references/deliverable-review.md, scripts/assemble-*.mjs, scripts/_templates/).

Reference and signpost the existing bundle files from SKILL.md — e.g., link references/deliverable-review.md from the A3 review stage and note the scripts/ template-assembly utilities — so present content is discoverable rather than buried.

Tighten the rule sections: merge the duplicated skip-handling bullets in A1 with the related NEVER rules in <guideline>/<constraint>, and trim padded phrasing like "shifting the output from merely descriptive to rigorously normative" from the EARS paragraph.

DimensionReasoningScore

Conciseness

The body is mostly operational and dense, but contains unnecessary or tighten-able material: the EARS paragraph ends in padded phrasing ("shifting the output from merely descriptive to rigorously normative"), and the skip-handling and NEVER rules are repeated across the A1 section, <guideline>, and <constraint> (e.g., "NEVER re-ask a question" restated in several forms). This matches "mostly efficient but includes some unnecessary explanation or could be tightened" rather than the minor-trim profile of anchor 4.

3 / 5

Actionability

There is genuinely concrete guidance — exact tool calls ("Use `read_file` to load `workflows/sop-elicitation.md`"), a copy-paste-ready JSON structured-question example, exact `sdd_advance` stage arguments, and a 3000-character chunked-write rule. However, the actual elicitation/template/generation procedures are delegated to `workflows/sop-*.md` files that do not exist anywhere in the bundle, and the promised "Skill File Index" section with absolute paths is absent — key executable content is missing, which is the anchor-3 pattern (concrete but incomplete, missing key details), not anchor 2 since the in-file guidance is specific rather than high-level hints.

3 / 5

Workflow Clarity

The A1→A2→A3 sequence is explicit, each stage has stated completion criteria ("Clarity — no unresolved ambiguities remain", "template-conformant output produced at target path"), skip semantics are precisely defined, and <condition> lays out execution precedence and refusal paths. This fits "clear sequence with most checkpoints present"; it is not a 5 because there are no verification checkpoints on the produced document itself within this file (review is deferred to the A3 stage's external pipeline) and the per-stage SOP detail is unresolvable.

4 / 5

Progressive Disclosure

Scored against the actual bundle: the three referenced workflow SOP files (workflows/sop-elicitation.md, sop-load-template.md, sop-generation.md) are missing from the bundle, and the referenced "Skill File Index" section does not exist in SKILL.md. Conversely, the real bundle files — references/deliverable-review.md, scripts/assemble-template.mjs, scripts/assemble-checklist.mjs, and scripts/_templates/ — are never mentioned or signaled anywhere in the body. Navigation is broken in both directions (dangling references plus buried, undiscoverable content), matching anchor 2's "references are buried" / minimal usable structure rather than anchor 3's "references present but not clearly signaled", since here the signaled ones are absent and the present ones are unsignaled.

2 / 5

Total

12

/

20

Passed

Description

83%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 strong: it states concrete capabilities in third person and pairs them with an explicit, well-structured "Use when" trigger list. Trigger coverage is good though it misses a few natural synonyms, and it has minor overlap risk with adjacent specification-writing skills.

DimensionReasoningScore

Specificity

Lists several concrete actions — "transforms raw requirements into structured specifications through Socratic dialogue, behavior analysis, and requirement specification design", "structured functional and non-functional requirements with priority labels", "acceptance criteria and test case definitions" — matching the several-specific-actions anchor. It falls short of the comprehensive anchor 5 because later lifecycle steps (review/revision, deliverable verification) are not mentioned.

4 / 5

Completeness

It explicitly answers both questions: the "what" ("transforms raw requirements into structured specifications...") and a numbered "Use when:" clause with four concrete trigger scenarios plus a catch-all ("any requirements clarification and specification generation tasks"). This clearly matches the anchor-5 example structure of stating capabilities followed by explicit use-when trigger phrases; anchor 4 would require the when to be less explicit, which it is not.

5 / 5

Trigger Term Quality

Natural phrases users would say are well covered: "requirements are unclear", "need decomposition", "requirements analysis specification", "acceptance criteria", "test case definitions", "requirements clarification". A few common natural terms are missing (e.g., "user stories", "PRD", "requirements gathering"), which is the anchor-4 pattern rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

"Requirements analysis" with triggers like "requirements analysis specification" and "acceptance criteria and test case definitions" carves out a mostly distinct niche with minimal overlap risk. It is not a 5 because adjacent skills (spec writing, PRD/product-management, design-document skills) share some trigger territory, e.g., "structured functional and non-functional requirements".

4 / 5

Total

17

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

XiaoLuoLYG/GOD

Path

jiuwenclaw/jiuwenswarm/agents/harness/code/rails/sdd/design_rail/skills/aet-req-analysis/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.