thinking SKILL.md skillA
thinking from n-n-code/n-n-code-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add n-n-code/n-n-code-skills/thinking@git:20260818.1d7259ePins git:20260818.1d7259e in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- n-n-code/n-n-code-skills
- Path
.agents/skills/thinking/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260818.1d7259e, committed Aug 18, 2026
- First version recorded
- Apr 1, 2026
- Size
- 5,159 bytes
- Repository stars
- 4
- License
- MIT
Decision-framing workflow for turning an ambiguous problem or open choice into a recommendation, experiment, or concrete next move. Use when the user wants to explore a vague idea, compare plausible approaches, understand system trade-offs, or decide what to do. Do not use for sustained brainstorming, when the decision is already settled and the remaining work is only implementation, or adversarial review of an existing candidate (use recursive-thinking).
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
# Thinking Move from ambiguity to a decision that is specific enough to act on and test. Use this as an orthogonal workflow skill alongside any relevant domain or repository skills. It does not replace security review, test strategy, prompt work, story preparation, documentation, or implementation guidance. Family boundary: **thinking** forms a candidate; **recursive-thinking** stress-tests an existing candidate; **dream-thinking** is an explicitly requested creative retrospective after experience. None requires the others to run first. ## Core cadence Run the skill through one simple loop: - understand what is stuck - explore only enough to improve the decision - identify what matters - choose what changes next ## Route by bottleneck - **Problem framing:** the goal, affected stakeholder, constraint, or success signal is unclear. - **Option discovery:** the problem is clear but the plausible approaches are not. - **Assumption testing:** no candidate has won yet, and the choice depends on uncertain beliefs or missing evidence. - **Systems analysis:** incentives, feedback loops, dependencies, or second-order effects could make a local improvement harmful overall. …
Read the whole file at its exact version.
How to install
mdr add n-n-code/n-n-code-skills/thinking@sha256:1601dfab498eb249The line at the top of this page pins the label git:20260818.1d7259e, 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.
[](https://markdownregistry.com/a/art_msw7mnkmuqcu2iis)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Apr 1, 2026 and Aug 18, 2026, about one every 35 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260818.1d7259e latest | 2026-08-18 | 1d7259e | 5,159 B | A | view · diff |
| git:20260423.b0aeb97 | 2026-04-23 | b0aeb97 | 9,872 B | A | view · diff |
| git:20260405.fb5650f | 2026-04-05 | fb5650f | 9,781 B | A | view · diff |
| git:20260405.002addc | 2026-04-05 | 002addc | 4,271 B | A | view · diff |
| git:20260401.57655a4 | 2026-04-01 | 57655a4 | 4,340 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5159 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
n-n-code/n-n-code-skills · 4 stars · license MIT · pushed 2026-11-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_msw7mnkmuqcu2iis GET https://markdownregistry.com/api/v1/resolve?ref=n-n-code/n-n-code-skills/thinking GET https://markdownregistry.com/api/v1/blob/1601dfab498eb249d57e3edbc3e1bacfd98dc40ae1582c1c144b28c647bb0ac3
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 n-n-code/n-n-code-skills
Every file in n-n-code/n-n-code-skills