agentleFS
EnigmaWUEnigmaWU/MyCodeAgentSkills/draft-srs-document/SKILL.md

draft-srs-document

Skill4 starsChanged 3 months agoMITView on GitHub

WHEN/WHERE/WHO: [Scheduling: Business analysts, systems engineers, or agents compiling requirements into a final specification.] HOW: [Structural: Use this SKILL to map scattered user stories, constraints, and UI notes into the formal IEEE-style SRS template.] WHY: [Scheduling: Unstructured documents lead to missing context. The SRS forces teams to state dependencies and quality attributes.]

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 7 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When this skill is activated, first load skill-common and apply the shared conventions it defines: canonical section order, frontmatter …

    line 13
  2. Distinctive:

    Transfer Check: Verify the workflow still works for partial documents, mixed requirement sources, and feature-heavy specs.

    line 50
  3. Distinctive:

    Stop Rule: If the input only contains visuals or missing functional logic, stop and ask before drafting the SRS.

    line 51
  4. Very specific:

    Do not invent requirements.

    line 54
  5. Distinctive:

    Write in verifiable, unambiguous language (e.g., replace "fast" with "sub-second response time").

    line 55
  6. Distinctive:

    If the input text only contains UI mockups, stop and inform the user that an SRS requires functional logic and data requirements, not just …

    line 58
  7. Distinctive:

    Read the input material and classify every statement: Is it a feature?

    line 62
  8. Distinctive:

    Verify that the document uses hierarchical numbering (1.1, 1.2, 3.1.1).

    line 85
  9. Very specific:

    Ensure no placeholder text remains unless explicitly marked as TBD.

    line 86

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Draft SRS Document

Common Contract (Load First)

When this skill is activated, first load skill-common and apply the shared conventions it defines: canonical section order, frontmatter rules, anti-pattern guidance, and the Review In Mind loop in review-in-mind. This skill adds only domain-specific rules below.

Who

Business Analysts, Systems Engineers, and AI Agents. The agent uses this skill to generate a structured, formal requirements baseline.

What

This skill implements the Software Requirements Specification (SRS) methodology from Software Requirements (3rd Edition). It takes raw inputs (interview transcripts, JIRA tickets, rough PRDs) and maps them into a strict 8-part template:

  1. Introduction
  2. Overall Description
  3. System Features
  4. Data Requirements
  5. External Interface Requirements
  6. Quality Attributes
  7. Internationalization
  8. Other Requirements

When

Invoke this skill at the end of the requirements elicitation phase, before handing off to development and QA for implementation and testing. Trigger phrases include: "draft an SRS," "compile these requirements," "create a specification document," or "format this as an SRS."

Where

Applies to project documentation folders, wikis, or formal contract deliverables.

Why

A pile of 100 user stories is not a specification. Developers need to know the operating environment (Section 2), the data models (Section 4), and the performance constraints (Section 6). The SRS template forces you to fill in these blanks.

Inputs

  • Raw requirements, user stories, transcripts, or existing vision documents.

Output (Logical Evidence)

  • A markdown document formatted using the SRS Template.

Optimization Readiness

  • Failure Signals: Requirements are invented, placeholders are left unmarked, hierarchical numbering breaks, or the draft omits major sections without flagging the gap.
  • Evidence To Collect: Input classification notes, drafted SRS sections, open-question lists, and examples where the wording was made verifiable instead of vague.
  • Safe Mutation Boundaries: Refine categorization prompts, section-filling guidance, numbering checks, and gap-analysis rules without changing the core template-driven drafting workflow.
  • Acceptance Criteria: Accept revisions only if the SRS stays grounded in the source material, uses hierarchical numbering correctly, and marks unrecoverable gaps as TBD instead of inventing content.
  • Rejected Revision Handling: Record invented requirements, poor numbering patterns, and overly generic wording so they are not repeated.
  • Transfer Check: Verify the workflow still works for partial documents, mixed requirement sources, and feature-heavy specs.
  • Stop Rule: If the input only contains visuals or missing functional logic, stop and ask before drafting the SRS.

Constraints (Logical Boundaries)

  • Do not invent requirements. If a section of the SRS cannot be filled from the provided input, mark it as TBD (To Be Determined) and list it as an open question.
  • Write in verifiable, unambiguous language (e.g., replace "fast" with "sub-second response time").

One More Thing

If the input text only contains UI mockups, stop and inform the user that an SRS requires functional logic and data requirements, not just visual designs.

How (Structural Workflow)

Phase 1: Categorization

  1. Read the input material and classify every statement: Is it a feature? A constraint? A user class? A performance goal?

Phase 2: Drafting

  1. Populate the SRS Template section by section.
  2. For Section 3: System Features, group related functional requirements together. Number them logically (e.g., 3.1, 3.1.1).
  3. Extract Non-Functional Requirements (NFRs) into Section 6: Quality Attributes.

Phase 3: Gap Analysis

  1. Review the drafted SRS. If major sections (like "Data Requirements" or "External Interfaces") are completely empty, highlight this as a risk in your response.

Resources

  • SRS Template

Review In Mind (ReviewInMindGenie)

Execute the common review loop in review-in-mind before delivering.

Review lens for this skill:

  • Does the SRS cover all 8 required sections with traceable, testable requirements?
  • Are requirements free of ambiguous words and implementation-biased constraints?
  • Is every stakeholder need mapped to at least one requirement (or explicitly out of scope)?

Validation

  1. Verify that the document uses hierarchical numbering (1.1, 1.2, 3.1.1).
  2. Ensure no placeholder text remains unless explicitly marked as TBD.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.