qa-iteration SKILL.md skillA

qa-iteration from blisspixel/primr is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add blisspixel/primr/qa-iteration@v1.1.0

Pins v1.1.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
blisspixel/primr
Path
skills/qa-iteration/SKILL.md
Versions recorded
5
Latest version
v1.1.0, committed Mar 27, 2026
First version recorded
Feb 3, 2026
Size
1,253 bytes
Repository stars
3
License
Apache-2.0

Assess and improve Primr output quality. Use when the user asks to review, grade, refine, or troubleshoot a report or strategy document.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# QA Iteration

## Purpose

Use this skill after research or strategy generation to evaluate output quality and identify the next corrective action.

## Workflow

1. Read `primr://output/latest` when the user does not specify a path.

2. Run `run_qa` on the concrete report path.

3. Summarize the weakest sections first.

4. If the user wants a different deliverable rather than a rewrite, read `primr://strategies/available`, call `estimate_strategy`, and get approval before `generate_strategy`.

## Operating Rules

- Treat QA as a decision aid, not a final verdict.

- Prioritize factual gaps, missing citations, and thin strategic interpretation.

- Do not recommend regeneration until you can explain what is weak.

- Keep the follow-up action specific: rerun research, generate a strategy, or revise the report.

## Example

```text

run_qa(report_path="output/exampleco/report.md")

```

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add blisspixel/primr/qa-iteration@sha256:3193dd2d6eec7ba2

The line at the top of this page pins the label v1.1.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_7rrartridf4hv47y.svg)](https://markdownregistry.com/a/art_7rrartridf4hv47y)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Feb 3, 2026 and Mar 27, 2026, about one every 13 days.

versioncommittedcommitsizeaudit
v1.1.0 latest2026-03-27 66876fa 1,253 BA view · diff
v1.0.02026-02-06 518b111 2,926 BA view · diff
v1.0.02026-02-06 22a2e9a 2,922 BA view · diff
git:20260206.7ccb4682026-02-06 7ccb468 2,827 BA view · diff
v2.0.02026-02-03 9762195 6,000 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (1253 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

blisspixel/primr · 3 stars · license Apache-2.0 · pushed 2026-11-03 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_7rrartridf4hv47y
GET https://markdownregistry.com/api/v1/resolve?ref=blisspixel/primr/qa-iteration
GET https://markdownregistry.com/api/v1/blob/3193dd2d6eec7ba2f5a085c04994e618c12974812706b7cc89e80f9fbf08de72

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from blisspixel/primr

primr-zero SKILL.md skill
blisspixel/primr · .agents/skills/primr-zero/SKILL.md · Build a substantial, sourced Primr-style company dossier with zero Primr model API spend by combining keyless evidence…
git:20261020.8f5b842 · audit A · 3 stars
primr-zero SKILL.md skill
blisspixel/primr · .claude/skills/primr-zero/SKILL.md · Build a substantial, sourced Primr-style company dossier with zero Primr model API spend by combining keyless evidence…
git:20261020.8f5b842 · audit A · 3 stars
primr SKILL.md skill
blisspixel/primr · .claude/skills/primr/SKILL.md · Route and run Primr company research from an agent host. Use for a bare Primr company-and-URL request, named Primr…
git:20261102.c6375ec · audit A · 3 stars
AGENTS.md AGENTS.md file
blisspixel/primr · AGENTS.md
git:20261028.5513d0a · audit A · 3 stars
CLAUDE.md CLAUDE.md file
blisspixel/primr · CLAUDE.md
git:20261028.311ecdd · audit B · 3 stars
primr-zero SKILL.md skill
blisspixel/primr · agent-plugin/skills/primr-zero/SKILL.md · Build a substantial, sourced Primr-style company dossier with zero Primr model API spend by combining keyless evidence…
git:20261020.8f5b842 · audit A · 3 stars
primr SKILL.md skill
blisspixel/primr · agent-plugin/skills/primr/SKILL.md · Route and run Primr company research from an agent host. Use for a bare Primr company-and-URL request, named Primr…
git:20261102.c6375ec · audit A · 3 stars
company-brief SKILL.md skill
blisspixel/primr · claude-code/skills/company-brief/SKILL.md · Produce a primr-style strategic company brief using ONLY the host agent's own tools (web search, page fetch, shell DNS…
git:20261103.b1719d1 · audit A · 3 stars
primr-zero SKILL.md skill
blisspixel/primr · claude-code/skills/primr-zero/SKILL.md · Build a substantial, sourced Primr-style company dossier with zero Primr model API spend by combining keyless evidence…
git:20261020.8f5b842 · audit A · 3 stars
primr SKILL.md skill
blisspixel/primr · claude-code/skills/primr/SKILL.md · Route and run Primr company research from an agent host. Use for a bare Primr company-and-URL request, named Primr…
git:20261102.c6375ec · audit A · 3 stars
primr-qa SKILL.md skill
blisspixel/primr · openclaw/skills/primr-qa/SKILL.md · Review Primr outputs and diagnose integration issues. Use when the user wants report quality assessment, output review…
v1.1.0 · audit A · 3 stars
primr-research SKILL.md skill
blisspixel/primr · openclaw/skills/primr-research/SKILL.md · Run and monitor company research through Primr MCP. Use when the user wants a new research run, asks for status, or…
v1.1.0 · audit A · 3 stars

Every file in blisspixel/primr

Other files named qa-iteration

qa-iteration SKILL.md skill
pueo-labs/primr · skills/qa-iteration/SKILL.md · Assess and improve Primr output quality. Use when the user asks to review, grade, refine, or troubleshoot a report or…
v1.1.0 · audit A · 3 stars

Browse by kind, by grade A, or by owner.