AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Praxis

skill-mfarzanansari-praxis-workflow-os-praxis · by mfarzanansari

Use when a person wants to design, install, operate, review, or improve a customized AI-assisted workflow, personal operating system, Obsidian knowledge architecture, or reusable skill system—even when they describe it as productivity, memory, process, SOP, second brain, agent workflow, or "how I work.

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

Install

$ agentstack add skill-mfarzanansari-praxis-workflow-os-praxis

✓ 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.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-mfarzanansari-praxis-workflow-os-praxis)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
21d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Praxis? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Praxis

Core principle

Route the person to the smallest lifecycle capability that changes the current outcome. Do not load or recreate the whole system for every task.

Praxis treats a workflow as a versioned operating model:

> Trigger → Evidence → Decisions → Actions → Deliverable → Verification → Durable learning

Route by lifecycle stage

| Current need | Use | |---|---| | Understand the person and their real work | praxis-interview | | Convert an approved profile into an architecture | praxis-blueprint | | Create vault files and personalized skills | praxis-setup | | Preserve useful residue from completed work | praxis-distill | | Review evidence and improve the operating system | praxis-retrospective | | Create or evolve a reusable skill | praxis-skill-forge | | Materialize an approved contract for a named model | Optional prompt-polish companion, when installed or explicitly requested |

When more than one stage is requested, preserve this order:

interview → blueprint approval → setup → real use → distillation → retrospective → skill evolution

Routing procedure

  1. Inspect the conversation and available artifacts. Reuse facts already known.
  2. Identify the current lifecycle stage and the deliverable the user expects now.
  3. Load only the matching skill.
  4. State the route in one sentence, then execute it.
  5. When the selected skill reaches an approval gate, stop. Do not silently continue into the next stage.

Optional Prompt Polish handoff

Praxis owns intent, workflow structure, deliverables, quality gates, and human approval boundaries. When those are already approved and the user names a target model, prompt-polish may optionally turn that stable contract into a model-specific execution prompt.

Use the companion only when it is installed or explicitly requested. Pass the approved contract, target model, task form, constraints, and done-condition. Never ask Prompt Polish to invent or redefine the workflow, and never make core Praxis operation depend on it.

Hard gates

  • Do not scaffold a workflow before the profile and blueprint are approved.
  • Do not create a new skill merely because a task exists once.
  • Do not write raw transcripts into durable memory.
  • Do not move, rename, delete, or overwrite a person's existing vault by default.
  • Do not treat third-party skills as trusted because they are popular.
  • Do not automate an action beyond the person's approved risk boundary.

Existing-system mode

When the person already has a vault, prompts, SOPs, or skills:

  1. inventory what exists;
  2. infer the current architecture and naming conventions;
  3. identify strengths worth preserving;
  4. locate duplication, missing gates, stale references, and retrieval failures;
  5. propose an augmentation path rather than a replacement.

Completion contract

A routed Praxis task is complete when:

  • the correct lifecycle skill was used;
  • its artifact or decision was produced;
  • unresolved assumptions are visible;
  • any required human approval was obtained;
  • the next lifecycle stage is named but not automatically executed.

Common routing mistakes

| Mistake | Correction | |---|---| | Asking the entire interview in one message | Use praxis-interview; one consequential question per turn. | | Creating folders before understanding the work | Blueprint and approval first. | | Building a giant profession persona | Generate a small skill graph from work streams and shared primitives. | | Saving everything as memory | Distill only future-useful residue. | | Editing skills based on taste | Use evidence and praxis-skill-forge. | | Loading every skill “just in case” | Route narrowly; progressive disclosure is part of the architecture. |

See [references/lifecycle.md](references/lifecycle.md) for the artifact contracts between stages.

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.