meta-prompting SKILL.md skillA

meta-prompting from iliaal/whetstone is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add iliaal/whetstone/meta-prompting@git:20260227.215f429

Pins git:20260227.215f429 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
iliaal/whetstone
Path
distillery/generated-skills/meta-prompting/SKILL.md
Versions recorded
1
Latest version
git:20260227.215f429, committed Feb 27, 2026
Size
3,842 bytes
Repository stars
35
License
MIT

Enhanced reasoning patterns via slash commands (/think, /verify, /adversarial, /edge, /compare, /confidence, /budget, /constrain, /json, /flip, /assumptions, /tensions, /analyze, /trade) or natural language ("argue against", "what could break", "show reasoning", "deep review", "meta-prompts", "thinking modes", "second-best approach", "list assumptions", "opposing perspectives").

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

# Meta-Prompting

Enhanced reasoning via `/commands` or natural language. Commands combine left-to-right: `/verify /adversarial`. Auto-trigger when context warrants — note which pattern applied.

## Patterns

**`/think`** | `/show` — Show reasoning step-by-step: decision points, alternatives considered, why each accepted/rejected. With `/think doubt`: after each step, flag what could be wrong and why before proceeding.

**`/adversarial`** | `/argue` — After answering, argue against it. 3 strongest counterarguments ranked by severity. Identify blind spots and unstated assumptions.

**`/constrain`** | `/strict` — Tight constraints: 3 sentences max, cite sources, no hedging. Override inline: `/constrain 5 sentences`.

**`/json`** | `/format` — Respond in valid JSON code block, no surrounding prose unless asked. Default schema:
```json
{"analysis": "", "confidence_score": 0-100, "methodology": "", "limitations": []}
```
Custom keys: `/json {keys: summary, risks, recommendation}`

**`/budget`** | `/deep` — Extended thinking space (~500 words) showing dead ends and reasoning pivots, then clearly separated final answer.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add iliaal/whetstone/meta-prompting@sha256:842acf0a0078a322

The line at the top of this page pins the label git:20260227.215f429, 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_2khir7tm4hgm3ujw.svg)](https://markdownregistry.com/a/art_2khir7tm4hgm3ujw)

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

Versions

The registry has recorded 1 version of this file, committed on Feb 27, 2026.

versioncommittedcommitsizeaudit
git:20260227.215f429 latest2026-02-27 215f429 3,842 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 (3842 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

iliaal/whetstone · 35 stars · license MIT · pushed 2026-11-01 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_2khir7tm4hgm3ujw
GET https://markdownregistry.com/api/v1/resolve?ref=iliaal/whetstone/meta-prompting
GET https://markdownregistry.com/api/v1/blob/842acf0a0078a32256efb017444d4e05e10f97d3ce4b36e379cc965699d8fa66

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 iliaal/whetstone

analyze-misfires SKILL.md skill
iliaal/whetstone · .agents/skills/analyze-misfires/SKILL.md · Analyze Whetstone skill injection misfires when asked to investigate overly broad triggers or irrelevant injected…
git:20260907.228ec83 · audit A · 35 stars
announce SKILL.md skill
iliaal/whetstone · .agents/skills/announce/SKILL.md · Draft an X announcement for a Whetstone release when asked to announce that release.
git:20260907.228ec83 · audit A · 35 stars
audit-plugin SKILL.md skill
iliaal/whetstone · .agents/skills/audit-plugin/SKILL.md · Audit Whetstone skills, agents, and commands when asked for a plugin quality or consistency audit.
git:20260907.228ec83 · audit A · 35 stars
diagnose-negatives SKILL.md skill
iliaal/whetstone · .agents/skills/diagnose-negatives/SKILL.md · Investigate negative session feedback for a Whetstone skill when asked to diagnose its failures.
git:20260907.228ec83 · audit A · 35 stars
eval-skills SKILL.md skill
iliaal/whetstone · .agents/skills/eval-skills/SKILL.md · Evaluate Whetstone skills from session evidence when asked to compare procedure-following results or optimization…
git:20260907.228ec83 · audit A · 35 stars
evolve-skill SKILL.md skill
iliaal/whetstone · .agents/skills/evolve-skill/SKILL.md · Revise and evaluate a Whetstone skill when asked to evolve or optimize that skill.
git:20260907.228ec83 · audit A · 35 stars
prune-sync-log SKILL.md skill
iliaal/whetstone · .agents/skills/prune-sync-log/SKILL.md · Prune stale Whetstone sync decision entries when asked to clean the sync log.
git:20260907.228ec83 · audit A · 35 stars
release SKILL.md skill
iliaal/whetstone · .agents/skills/release/SKILL.md · Run the Whetstone release workflow when explicitly asked to release this plugin.
git:20260907.228ec83 · audit A · 35 stars
skillopt SKILL.md skill
iliaal/whetstone · .agents/skills/skillopt/SKILL.md · Prepare or run Whetstone SkillOpt optimization when asked to optimize a process skill using SkillOpt.
git:20260907.228ec83 · audit A · 35 stars
sync-from-repos SKILL.md skill
iliaal/whetstone · .agents/skills/sync-from-repos/SKILL.md · Compare Whetstone with reference repositories when asked to sync cross-repository improvements.
git:20260907.228ec83 · audit A · 35 stars
triage-prs SKILL.md skill
iliaal/whetstone · .agents/skills/triage-prs/SKILL.md · Triage Whetstone pull requests when explicitly asked to group, label, and review open PRs.
git:20260907.228ec83 · audit A · 35 stars
write-skill SKILL.md skill
iliaal/whetstone · .agents/skills/write-skill/SKILL.md · Author a new Whetstone plugin skill when asked to write a skill without upstream skills.sh sources.
git:20260907.228ec83 · audit A · 35 stars

Every file in iliaal/whetstone

Other files named meta-prompting

meta-prompting SKILL.md skill
iliaal/ai-skills · skills/meta-prompting/SKILL.md · Structured decision modifiers (/think, /verify, /adversarial, /edge, /confidence, /assumptions, etc.) to stress-test…
git:20260926.7b0520a · audit A · 45 stars

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