AgentStack
SKILL verified MIT Self-run

Feature Marker

skill-viniciuscarvalho-feature-marker-feature-marker · by Viniciuscarvalho

>

No reviews yet
0 installs
11 views
0.0% view→install

Install

$ agentstack add skill-viniciuscarvalho-feature-marker-feature-marker

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Feature Marker? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

feature-marker

Use this skill when the user asks to implement, plan, test, or hand off a feature with Feature Marker.

The normal invocation is a plain LLM prompt:

Use feature-marker to implement .

Run through the feature by default. Do not use an interactive menu, old CLI workflow commands, checkpoint JSON, or a JavaScript workflow engine. The package installer only installs this skill.

Run-Through Procedure

  1. Identify the feature slug from the prompt. If the slug is missing, derive a

short kebab-case slug from the feature request.

  1. Read repo state: current branch, base branch, git status, project files, and

any existing tasks/{slug}/prd.md, tasks/{slug}/techspec.md, and tasks/{slug}/tasks.md.

  1. Stop before implementation only when:
  • the feature request is too ambiguous to produce useful artifacts;
  • the checkout has unrelated uncommitted work and the user has not approved

a worktree or cleanup path;

  • required verification or project setup is blocked.
  1. Use branch-first isolation. If the current branch is main, master,

develop, or trunk, create feature-marker/{slug} unless the user gave a branch name. Use a git worktree only when the checkout is dirty or the user asks for one.

  1. Create or reuse artifacts in tasks/{slug}/ using the bundled templates:
  • templates/prd-template.md -> tasks/{slug}/prd.md
  • templates/techspec-template.md -> tasks/{slug}/techspec.md
  • templates/tasks-template.md -> tasks/{slug}/tasks.md

Replace {slug} and {feature_title}, fill every relevant section, and do not leave unresolved template placeholders in committed artifacts.

  1. Run an implementation grill pass before coding. Challenge the artifacts for

missing acceptance criteria, weak task order, risky files, data/migration impact, missing tests, unclear edge cases, and handoff gaps.

  1. Resolve grill findings in tasks/{slug}/ before implementation. Ask the

user only when a finding changes scope or requires a product decision. Otherwise continue without a generic artifact approval gate.

  1. Implement only the tasks in tasks/{slug}/tasks.md. Keep changes scoped to

the feature and preserve unrelated local edits.

  1. Run project-appropriate verification. If a command fails, fix the issue when

it is in scope; otherwise report the exact blocker and stop.

  1. Commit the feature locally when implementation and verification are complete,

unless the user prohibited commits. Do not push or open a PR automatically.

  1. Print the branch handoff with exact commands:
git push -u origin 
gh pr create --base  --head 

Artifact State

The canonical state is user-facing markdown:

tasks/{slug}/
  prd.md
  techspec.md
  tasks.md

Optional verification notes may also live under tasks/{slug}/ when they help future continuation, but checkpoint JSON is not the source of truth.

Prompt Intents

There are no CLI workflow modes. Treat these as prompt intents:

  • full: run the complete PRD -> TechSpec -> Tasks -> implementation grill ->

implementation -> tests -> branch handoff flow.

  • tasks-only: use existing artifacts and implement the task list.
  • test-only: run verification on the current feature branch and report

results.

  • prd-only: create or revise only tasks/{slug}/prd.md.

spec-driven and ralph-loop are out of scope for this skill-first v1 unless they are rebuilt as explicit skill instructions.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.