Back to catalog
Human reviewedWriting

Skill dossier

feature-forge

Source declaration

Conducts structured requirements workshops to produce feature specifications, user stories, EARS-format functional requirements, acceptance criteria, and implementation checklists. Use when defining new features, gathering requirements, or writing specifications. Invoke for feature definition, requirements gathering, user stories, EARS format specs, PRDs, acceptance criteria, or requirement matrices.

The author's original description, preserved in English. It describes intent, not verified performance.

Conducts structured requirements workshops to produce feature specifications, user stories, EARS-format functional requirements, acceptance criteria, and implementation checklists. Use when defining new features, gathering requirements, or writing specifications. Invoke for feature definition, requirements gathering, user stories, EARS format specs, PRDs, acceptance criteria, or requirement matrices.

referenceswriting

Research summary

Human reviewed

Skill Atlas editorial review · editorial-preview-1.0.0

A requirements Skill that runs a structured interview from product and developer perspectives and produces an EARS-format specification with acceptance criteria and an implementation checklist.

Review scope

Deterministic static analysis of collected SKILL.md and supporting text/code. Machine-assisted candidates and findings await human editorial review; no dynamic behavior or effect is assessed.

Observable capabilities

  • Interviews the user with AskUserQuestions to clarify goals, users, priority and scope.
  • Writes functional requirements in EARS format plus non-functional requirements.
  • Produces acceptance criteria in Given/When/Then form and an error handling table.
  • Saves the specification as specs/{feature_name}.spec.md with an implementation TODO checklist.

Limitations & scope

  • Depends on the AskUserQuestions tool and on a stakeholder who can answer the interview.
  • Produces a design document only; it does not implement the feature.
  • Specification quality has not been evaluated here.

Relevant for

  • Product managers and engineers defining new features
  • Teams that want written, testable requirements before coding

What ships with the skill

The file inventory comes from the collected source at the recorded commit. Paths and sizes are structural observations, not a measure of quality.

files
6
Markdown files
6
scripts
0
references
5
Size
19.8 KB
Structural complexity
Low

File inventory

PathTypeBytes
skills/feature-forge/references/acceptance-criteria.mdReference2.9 KB
skills/feature-forge/references/ears-syntax.mdReference2.6 KB
skills/feature-forge/references/interview-questions.mdReference5.4 KB
skills/feature-forge/references/pre-discovery-subagents.mdReference2 KB
skills/feature-forge/references/specification-template.mdReference2.5 KB
skills/feature-forge/SKILL.mdInstruction4.4 KB

SKILL.md frontmatter

{
  "name": "feature-forge",
  "description": "Conducts structured requirements workshops to produce feature specifications, user stories, EARS-format functional requirements, acceptance criteria, and implementation checklists. Use when defining new features, gathering requirements, or writing specifications. Invoke for feature definition, requirements gathering, user stories, EARS format specs, PRDs, acceptance criteria, or requirement matrices.",
  "license": "MIT",
  "metadata": {
    "author": "https://github.com/Jeffallan",
    "company": "https://synergetic.solutions",
    "version": "1.1.0",
    "domain": "workflow",
    "triggers": "requirements, specification, feature definition, user stories, EARS, planning",
    "role": "specialist",
    "scope": "design",
    "output-format": "document",
    "related-skills": "fullstack-guardian, spec-miner, test-master"
  }
}

A reading of the operating sequence

This workflow reconstructs the apparent sequence from source material. Unless controlled evaluation is explicitly recorded, it is provisional—not an observed trace.

  1. 01
    Input

    Discover the goal

    Use AskUserQuestions to understand the feature goal, target users and user value.

  2. 02
    Action

    Interview and document

    Question systematically from PM and Dev perspectives, then write EARS-format requirements.

  3. 03
    Decision

    Validate with the stakeholder

    Review acceptance criteria with the stakeholder, presenting key trade-offs as structured choices.

  4. 04
    Output

    Deliver the specification

    Save the spec with overview, requirements, acceptance criteria, error table and TODO checklist as specs/{feature_name}.spec.md.

Potential risk surfaces

Static findings identify points to inspect before installation. They do not establish that a skill is safe, malicious, or effective.

Items warrant review

11 deterministic lexical finding(s) require review across the collected text. Findings can occur in documentation and do not prove execution or exploitability; binary-only files were not scanned.

Network accessObserved
File writesObserved
Credential useNot observed
Note

File modification is described or implemented

7 occurrences

This line contains a possible file-write or redirection operation. Check destination paths and overwrite behavior; the static review did not write any file. This rule matched 7 location(s) in the collected text; 3 representative location(s) are cited. Matching text may be documentation, and the analyzer did not execute it.

Medium

Network access is mentioned

4 occurrences

A URL or network client appears in this source line. Review destinations, data sent, and trust boundaries; static text cannot establish actual network activity. This rule matched 4 location(s) in the collected text; 3 representative location(s) are cited. Matching text may be documentation, and the analyzer did not execute it.

Editorial security note

Check that the specification files it writes go to the intended specs directory and contain no sensitive business data you cannot share.

Where context can be spent

Discovery, activation, and resource layers have different meanings. Exact values appear only when the official token-counting method was run with a named model.

Exact token counts unavailable

All token values, including per-file inventory, are null until the pipeline performs an official exact count with an explicit model.

No token measurement was recorded with the required official method. This dossier does not substitute character counts, file sizes, or estimates.

Controlled evaluation

No controlled evaluation

This skill has only the evidence identified above. No task success, token efficiency, latency, or quality advantage is claimed.

Not tested

Use with the source in view

Install command
git clone https://github.com/Jeffallan/claude-skills.git cd claude-skills # Copy this skill directory into one of: # ~/.claude/skills/feature-forge # .claude/skills/feature-forge
  1. Open the pinned source at https://github.com/Jeffallan/claude-skills/blob/67c1961b180dc92cf08983344627109e983e8f51/skills/feature-forge/SKILL.md.
  2. Review the license, prerequisites and all bundled reference files.
  3. Copy the skill directory into a personal or project-level Claude Code skills directory.
  4. Restart or refresh Claude Code so the skill can be discovered.
Verify installation

Run it on a small feature and check that it asks structured questions before drafting any EARS requirements.

Prerequisites

  • Depends on the AskUserQuestions tool and on a stakeholder who can answer the interview.
  • Produces a design document only; it does not implement the feature.
  • Specification quality has not been evaluated here.

Example prompts

Representative task

Use the feature-forge skill to define a password-reset feature: interview me about users and priority, then write EARS requirements, Given/When/Then acceptance criteria and a TODO checklist in specs/password_reset.spec.md.

Inspect before use

Read the feature-forge skill at https://github.com/Jeffallan/claude-skills/blob/67c1961b180dc92cf08983344627109e983e8f51/skills/feature-forge/SKILL.md. Explain its workflow, required tools, permissions and the main risks before I decide whether to install it.

A decision, with its limits attached

Strengths

  • Forbids generating a spec without first conducting an interview.
  • Requires testable criteria and explicit security and error handling coverage.

Considerations

  • The interview adds time compared with writing a spec directly.
  • Multi-agent discovery for large features adds complexity and token use.
Research conclusion

A useful front-end for turning vague feature ideas into reviewable specifications before any code is written.

Traceable by construction

The dossier is a time-bound reading of a public artifact, not an endorsement. Use the source link to inspect the exact upstream material.

Jeffallanclaude-skillsskills/feature-forge
Source type
Community
Commit
67c1961b180dc92cf08983344627109e983e8f51
Collected
20 Nov 2026
Last checked
20 Nov 2026
Upstream license
MIT
Repository stars
12,464
Content basis

Deterministic lexical parsing, YAML frontmatter validation, file inventory, source-described workflow extraction, and heuristic provisional classification of the supplied files only. Generated by machine; no LLM, execution, dynamic testing, or human editorial approval.